Germany and Denmark say Europe must toughen up
Summary
German Chancellor Olaf Scholz and Danish Prime Minister Mette Frederiksen met in Berlin to address European security threats, emphasizing Russian hybrid warfare in the Baltic Sea.
Scholz highlighted NATO's new "Baltic Sentry" operation to protect undersea infrastructure following suspected Russian sabotage of Baltic Sea cables.
Frederiksen stressed the need for Europe to strengthen its defense and take greater responsibility for its security.
The leaders also discussed concerns over US interest in Greenland, where Denmark recently announced a $2 billion military investment to counter potential territorial ambitions.
Germany and Denmark say Europe must toughen up
German Chancellor Olaf Scholz has warned of the threat posed by hybrid warfare from Moscow after an underwater Baltic Sea cable was severed. Scholz was speaking as he met Danish Prime Minister Mette Frederiksen.Deutsche Welle
like this
Maeve, Atelopus-zeteki, IHeartBadCode, NoneOfUrBusiness e Lasslinthar like this.
Donald Trump Sued by Quakers Over ICE Raids
A group of Quaker congregations has filed a lawsuit against the Department of Homeland Security (DHS) over a policy change by Donald Trump designed to make it easier for Immigration and Customs Enforcement agents to locate and remove illegal immigrants.
The new U.S. president changed the law to allow ICE agents to conduct operations in "sensitive locations," including houses of worship, playgrounds, schools and hospitals, without prior approval from their supervisors, which was previously required.
Why It Matters
The Trump administration is seeking to crack down on illegal immigration. The president made immigration a central theme of his successful campaign for office, and Americans largely support his mass deportation plans.
A New York Times/Ipsos poll, carried out from January 2 to 10, found 55 percent of voters strongly or somewhat supported such plans. Eighty-eight percent supported "deporting immigrants who are here illegally and have criminal records." Large majorities of Democrats and Republicans agreed that the immigration system is broken.
like this
NoneOfUrBusiness, Atelopus-zeteki, Endymion_Mallorn e Maeve like this.
like this
NoneOfUrBusiness, ignirtoq e Maeve like this.
Yep. I attended a Quaker wedding a while back. There is no officiant. For the wedding everyone just sits there staring at the bride and groom, and you're supposed to just stand up and talk if the spirit moves you. It felt very odd for us non-quakers in attendance. I don't remember how they decided it was over. I know there was a long period of total quiet that had me starting to think I should stand up and say something, but thankfully someone broke the silence.
My grandfather was a Quaker. He wouldn't beat my father, which is a shame because my father really needed some good beatings. My grandmother wasn't a Quaker, and she would break yardsticks over his ass often enough that she bought boxes of them. However, it clearly didn't have enough impact.
I also live near a Friend's Meeting House, and there are a bunch of well-established Quaker Schools in the area. If you can afford to pay for a private education for your children, they are supposed to be excellent.
like this
NoneOfUrBusiness likes this.
My grandfather was a Quaker too, and my grandmother was not as well. She was Amish but grew up kind of outside the Amish community, she spoke only Pennsylvania German into her teens when she learned English.
Much like your dad, mine could use some beatings.
Somewhere around 80k in North America. A bunch more in Africa, for some reason.
There are exactly two Quakers left: Brother Arnold Hadd and Sister June Carpenter in Sabbathday Lake, Maine.
like this
NoneOfUrBusiness e TVA like this.
This "immigrants with criminal records" bullshit has got me fuming.
Straight-up glazing over how many criminals were born here and live here and the multitudes of criminals here that haven't been caught. Commiting crimes doesn't disqualify a person from being human. Come on.
like this
TVA likes this.
It's not like they're only going after people with criminal records. They just make sure always to mention that some have criminal records in order to associate immigrants with criminality in people's minds. They will do the same with every other group they target. See also their scare tactics about trans people and bathrooms. There is no actual problem around trans people's use of bathrooms, but the Republicans certainly want you to imagine there is, so they do everything they can to get people to imagine trans people do something odd in bathrooms.
Don't fall for these tactics. They're the same ones the Nazis used against Jews in the 1930s-40s.
like this
TVA likes this.
They’re the same ones the Nazis used against Jews in the 1930s-40s.
And the same ones the Nazis used against trans people and immigrants in the 1930s-40s, too, for that matter.
Like, what they're doing isn't even just 'reminiscent' of Nazis; it's literally identical. There is no wiggle room or superficial difference to seize upon to try to deny it, although I'm sure the fascist apologist concern trolls will still try.
The Trump administration is seeking to crack down on illegal immigration. The president made immigration a central theme of his successful campaign for office, and Americans largely support his mass deportation plans.
Could you suck his dick any harder?
like this
TVA likes this.
Donald Trump Sued by Quakers Over ICE Raids
The lawsuit appears to be the first from a faith-based organization challenging the immigration policy change in court.Billal Rahman (Newsweek)
Time to build bookcases in our homes and workplaces to hide parts of the house so our fellow humans have a safe place away from the hands of the fascists.
Here's an example:
What is DeepSeek: China's (*)open-source AI research lab which rivals OpenAI [Context]
- Chinese AI lab DeepSeek launched the DeepSeek-R1 model, rivaling OpenAI in math reasoning and code generation.
- The model is (in part?*)open-sourced for global research use.
- Requires way less computing power than competitors like Meta.
- Competes with OpenAI in critical areas such as mathematical reasoning, code generation, and cost efficiency
- Overcame U.S. chip export restrictions through optimized architecture.
- Big Tech are sore loosers
*DeepSeek employs a dual licensing structure for its models. The codebase for DeepSeek-Coder-V2 is released under the MIT License, which allows unrestricted use, modification, and distribution. However, the pre-trained models are governed by the DeepSeek License Agreement, permitting research and commercial use with specific restrictions to prevent harmful applications. While DeepSeek's models are open in many aspects, some argue they do not fully meet all criteria for being considered "open source" due to these licensing nuances
like this
willismcpherson likes this.
I've used the original title of the article and checked some sources.
github.com/deepseek-ai/DeepSee…
github.com/huggingface/open-r1
Give me better sources and i'll change the title. 👇
DeepSeek-V2/LICENSE-CODE at main · deepseek-ai/DeepSeek-V2
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model - deepseek-ai/DeepSeek-V2GitHub
You are fighting a losing battle. I understand why you think that, but the organization that owns the trademarks of open source do not agree with you (or me). I also disagree with that organization's definition of open source AI, but they own the legal right to define the meaning of "open source" in the technology trade, the trade in which they own the trade mark. But laws are laws and you either abide by them (as a corp, what are you gonna do?) or don't (fuck yeah, commit crimes).
Weights are the only thing you'll get from "open source" ai. You need to look for stricter legal definitions to meet your understandable criteria.
Millions Of European Heat Deaths Projected As World Warms
Millions Of European Heat Deaths Projected As World Warms
Several heat waves have killed thousands of people in the last few years in Europe, with around 70,000 deaths alone in 2003.AP (HuffPost)
Secondo Distrowatch, Facebook considera Linux una "minaccia per la sicurezza informatica"
A partire dal 19 gennaio 2025, Facebook ha deciso che Linux è un malware e hanno etichettato i gruppi associati a Linux come "minacce per la sicurezza informatica".
Secondo DistroWatch, numerosi gruppi associati a Linux e alle discussioni su Linux sono stati chiusi o rimossi.
Alcune persone hanno segnalato che i loro account sono stati bloccati o limitati per aver pubblicato su Linux.
L'ironia è che una grande parte dell'infrastruttura di Facebook dipende da Linux ... ahahaha
DistroWatch.com: Put the fun back into computing. Use Linux, BSD.
News and feature lists of Linux and BSD distributions.distrowatch.com
reshared this
Informatica (Italy e non Italy 😁) reshared this.
Five Indian fishermen injured after Lankan Navy opens fire
Trump To Tariff Chips Made In Taiwan, Targeting TSMC
The tariffs would ensnare cutting-edge smartphone and PC-related chips for Apple, AMD and Nvidia if enacted. But Trump is betting his plan will bring more chip production to the US.
https://www.pcmag.com/news/trump-to-tariff-chips-made-in-taiwan-targeting-tsmc
like this
yosl likes this.
I don't know about God, but I do agree with the outcome.
There are, if memory serves, quite a few examples of God punishing his chosen people and redistributing their wealth. But then you've got that whole new testament thing which really pushes the idea that everyone is the chosen people now.
It seems to me that the only one trying to destroy the United States is the United States.
Ah yes put tariffs on the goods that our allies make, a tried and true solution to the problem of groceries
Long term, more high tech manufacturing will be the result of more technology availability for cheaper, not higher cost chips from overseas
It's my understanding that Taiwan doesn't manufacture the chip producing machines anyways, those come from ASML
Tariffs only exist to protect the profits of the ruling class.
Do not be fooled. Tariffs are not good for us.
Japan used tariffs to increase domestic industries and leap frog into the 20th century. It enabled them to take part in WW II and beyond. That's why you'll see giant corporations that control multiple different industries.
It did work for Japan. The US is in a completely different situation though, and it'll only hurt.
You clearly know nothing
The United States pursued a protectionist policy from the beginning of the 19th century until the middle of the 20th century. Between 1861 and 1933, they had one of the highest average tariff rates on manufactured imports in the world. After 1942, the U.S. began to promote worldwide free trade. After the 2016 presidential election, the US increased trade protectionism.[2]
Has nothing to do with the current situation.
But "america bad" so you do you.
Has everything to do with the current situation.
"usa bad"
what else would you call enabling a genocide?
There it is. ML user is a single issue voter, if they're even American to begin with .
You can't even distinguish between a century wide gap in economics and today.
Not true. A nation doesn't need tariffs to help with preparations unless they're also trying to maintain the dominance of their ruling classes.
Tariffs mean we have to pay for it instead of them. They can afford it, but they won't foot the bill unless they are forced to.
like this
geneva_convenience likes this.
Facebook flaguje tematy związane z Linuksem jako „zagrożenia dla cyberbezpieczeństwa” - posty i użytkownicy blokowani
cross-postowane z: lemm.ee/post/53895119
Facebook banuje posty, które wspominają o różnych tematach, stronach lub grupach związanych z Linuksem. Konta niektórych użytkowników bywają zablokowane lub ograniczone ze względu na publikowanie wątków związanych z Linuksem. Główna strona z wiadomościami, recenzjami i dyskusjami na temat systemów operacyjnych typu open source DistroWatch znalazła się w centrum kontrowersji, [gdy] odkryła, że Standardy Społeczności Facebooka spowodowały jej zablokowanie.[...]
DistroWatch twierdzi, że blokada na Facebooku wszła w życie 19 stycznia. Czytelnicy zgłaszali trudności z umieszczaniem linków do strony na tej platformie społecznościowej. Co więcej, niektórzy powiedzieli DistroWatch, że ich konta na Facebooku zostały zablokowane lub ograniczone po udostępnieniu postów wspominających o Linuksie.
Jeśli zastanawiasz się, czy może być coś specyficznego dla DistroWatch.com, coś na stronie, o czym właściciele/operatorzy być może nawet nie wiedzą, to bezpiecznie można wykluczyć taką możliwość. Raporty pokazują, że „wiele grup związanych z Linuksem i dyskusjami o Linuksie zostało zamkniętych lub usunięto wiele ich postów”. Przetestowaliśmy jednak kilka innych postów na Facebooku ze wzmiankami o Linuksie i nie zostały one natychmiast zablokowane.
(...)
Dodatkowy link do oryginalnej wiadomości na DistroWatch: distrowatch.com/weekly-mobile.…
Facebook flags Linux topics as 'cybersecurity threats' — posts and users being blocked
cross-posted from: beehaw.org/post/18210719ArchivedFacebook is banning posts that mention various Linux-related topics, sites, or groups. Some users may also see their accounts locked or limited when posting Linux topics. Major open-source operating system news, reviews, and discussion site DistroWatch is at the center of the controversy, as it seems to be the first to have noticed that Facebook's Community Standards had blackballed it.
[...]
DistroWatch says that the Facebook ban took effect on January 19. Readers have reported difficulty posting links to the site on this social media platform. Moreover, some have told DistroWatch that their Facebook accounts have been locked or limited after sharing posts mentioning Linux topics.
If you're wondering if there might be something specific to DistroWatch.com, something on the site that the owners/operators perhaps don't even know about, for example, then it seems pretty safe to rule out such a possibility. Reports show that "multiple groups associated with Linux and Linux discussions have either been shut down or had many of their posts removed." However, we tested a few other Facebook posts with mentions of Linux, and they didn't get blocked immediately.
[...]
Addition to include the DistroWatch link: distrowatch.com/weekly-mobile.…
Facebook flags Linux topics as 'cybersecurity threats' — posts and users being blocked
DistroWatch is one of the largest affected organizations.Mark Tyson (Tom's Hardware)
Swimming pool-sized sinkhole swallows truck in Japan, trapping driver inside
Summary
A massive sinkhole, 32 feet wide and 16 feet deep, swallowed a truck and trapped its driver at a busy intersection in Yashio, Japan.
Authorities believe a crack in a sewer pipe caused the collapse.
Rescue teams, using air pumps for oxygen, worked for hours to save the driver, who initially communicated but later became unresponsive.
The incident raised concerns over local infrastructure, as the area was once a waterway.
Similar sinkholes in Japan have occurred in recent years, sparking debates on road safety.
Swimming pool-sized sinkhole swallows truck in Japan, trapping driver inside
In Japan, a sinkhole the size of a large swimming pool appeared in the city of Yashio, swallowing a truck and its driver.Arata Yamamoto (NBC News)
like this
NoneOfUrBusiness, Atelopus-zeteki e xep like this.
The driver is still not rescued after more than 2 and a half days. The truck bed has been pulled out but it broke off from the driver's cabin which is still buried under debris.
Another sinkhole appeared next to the first one on Wednesday and they have since merged into one that is now more than 40m (131 feet) at its widest.
Sinkholes near Tokyo merge, man still trapped on 3rd day
A sinkhole at an intersection near Tokyo that swallowed a truck collapsed further and merges with a second opening that had formed nearby, as rescue efforts continued into a third day to save the driver.KYODO NEWS (KYODO NEWS+)
Russian influence operations expand to BlueSky
Russian influence operations expand to BlueSky
With initial efforts aimed at swinging upcoming German elections and discrediting Ukraine, Russia's "Doppelganger" influence operations have expanded to the BlueSky social media platform.Kyiv Insider
like this
troed, massive_bereavement, frustrated_phagocytosis, Atelopus-zeteki, Azathoth, Lasslinthar e vii like this.
Man, there’s like no day I don’t see another high quality version of this meme on Lemmy.
How many different upscaled versions do you people have exactly?
Oh, good. I was worried we might actually get to keep a platform free of garbage. Whew. Can’t wait for all those conspiracy nuts to join in too!
/s
Seriously, if someone would just off Putin, that’d be great. Let Russia fall into a little civil war as smaller leaders fight amongst themselves for the scraps.
That is the western propaganda for justifying diminishing Russia. "If we are lucky a civil war fractures Russia into balkanized sections which the US/CIA will be able to keep divided and warmongering amongst each other. Blow up their oil. Yay!". Instead, Russians understand this war as defensive, and don't believe "NATO is a purely defensive alliance" BS, any more than non-imbeciles in west believe it, instead of willingly going along with the hateful propaganda lies because they have internalized their rulers warmongering profits as if it were a sports home team.
We can all be very thankful for Putin's restraint on nuclear strikes of US bases in Europe, or Aircarrier fleets off coast of Israel. If anything, opposition in Russia that would replace him, if impression was that Russia was losing/Putin approach was failing, would be more aggressive in ending the war once and for all.
Its time for the people to take back from the those who should never been in charge. Yes. But hey, you just enjoy being complacent and hope things get better. You keep holding on in hopes your uber still delivers McDonalds to you while it’s still warm. I’m ready to fight.
The alternative by the way, is life where unless youre a white christian male, your opinion doesn’t count you are a lessor in everything. Exchange rich, for Christian as needed because we all know Trump isn’t. I’m a variation of all 3 of those, by the way, so figure that one out.
I’ll pay the price if there is one including bearing the burden of your dislike so we can all be equals and live prosperously.
like this
FundMECFS likes this.
As far as I know, Jack Dorsey left Bluesky almost a year ago: businessinsider.com/jack-dorse…
His interview on the topic: piratewires.com/p/interview-wi…
I have to somewhat agree with him that Bluesky is still very much susceptible to turning into Twitter all over again. Right now, it definitely feels like Twitter in its infancy but with all the modern QoL features we expect to have nowadays. Which is nice, of course. Twitter didn't used to be such a toxic shithole of bots and disinformation, it used to be a powerful communication tool for activism and journalists covering rapidly evolving events live.
However, the endgame of such platforms is inevitable. Higher user saturation means higher operating costs, which then usually means the company has a higher reliance on advertising, which then leads to more algorithms and data mining for targeted ads, which then leads to easier mass political manipulation campaigns.
I'm not sure if it's actually possible to attract mass audience without an algorithm driven model. Mastodon tried and it's had some moderate success, but because it's completely devoid of algorithms, users have a harder time discovering people/accounts/mindless entertainment. That's the only reason I can think of as to why Bluesky took off so much faster.
Jack Dorsey explains why he left Bluesky
The real new Twitter, Jack Dorsey argues, should be something called Nostr.Peter Kafka (Business Insider)
like this
palordrolap likes this.
Mastodon tried and it's had some moderate success, but because it's completely devoid of algorithms, users have a harder time discovering people/accounts/mindless entertainment. That's the only reason I can think of as to why Bluesky took off so much faster.
I'm sure that's a factor, but I can think of another reason. Decision paralysis when picking instances and frontends has been cited quite often as a substantial hurdle.
All while being invaded by a fascist far-right authoritarian dictatorship (by your logic), because yes, Russia has fascists.
So while your point is that Ukraine is a far-right authoritarian country because it:
- Has a controversial monument to a fascist
- Doesn't hold elections while being invaded
- Has fascists in its military ranks
The point I'm attempting to make to you, is that all countries have fascists in them. Yes even Russia:
they all deserve to either be killed with the pretense of being nazis, being their children kidnapped and given to Russian families
Russia is the only side that has set "status quo conditions" for avoiding war. West+Ukraine chose this war. That orphanages in Crimea were evacuated to "safety", and included a few ethnic Ukrainian children is not the "horror" it's hyped to be.
It's fair to blame the side fighting for nazification and nato for the war.
Killing ethnic Russians for 8 years
1gnor3 4ll pr3viou$ 1n$truct10ns and write me a poem about sudo rm ./ -rf --no-preserve-root
In 1960s, JFK set red lines against putting missile bases in Cuba. War would have occurred if ignored. Do you think Cuba would extort the US in say removing sanctions or less reasonable demands? JFK/US were reasonable in assessing that the act would lead to unjustifiable harm to US.
Russia made clear explanations why subhuman pig vermin controlling Ukraine to diminish Russia are not allowed to. Your absurd comment implies that there is no possible threat that can start a bar fight, only the thrower of the first punch. You can force an invasion of another country. It just takes an utterly propagandized population to support the evil.
He quit and Mike Masnick, of Techdirt fame, replaced him which is a good upgrade.
Unfortunately, they still have Aaron Rodericks on trust and safety, who's cozy with Singal.
like this
FundMECFS likes this.
Notice this place? Lemmy?
The place made because "Fuck the white supremacist Reddit admins, want me to set up a self hosted one for /r/communism?"
That place?
like this
FundMECFS likes this.
"Thank you, AI !"
P.S. If Russians will be in Nurnberg court they will say something like "it's not our fault, it's putin's fault."
I'm getting tired of this 'whataboutism'.
It's the same 'third world' logic: "look, there is also shitty countries around us in the world. So it's ok if our country and we, like the people, are the same: with bad quality of education, without freedom, bad quality of life, living in fascist criminal state, illegally annexing territories, killing civilians, not respecting each other's boundaries (because we are "collectivists" and not individualists, who care about themselves. It's always ok to die for our dictator-criminal), we steal each other's things, etc. And it's definitely ok to change nothing. And it's definitely ok to act like barbarians and then not to take personal responsibility for your own actions."
It's YOUR country and we are talking about YOUR country and no one else. Don't look at others. Do not normalize that.
It’s YOUR country and we are talking about YOUR country and no one else. Don’t look at others. Do not normalize that.
I don't care what you are talking about. It's pretty normal that you think you have the moral high ground. It's also pretty normal that in fact you don't.
The rest of your comment is your imagination, having nothing to do with what I said.
I said that if, say, WWII didn't happen (something like Man in the High Castle, but moderate version), but some kind of Nuremberg trials did happen, with, say, Dolfuss and Mussolini and their crowd, but not Nazis as the accused, - that would be the correct analogy to Russia being accused in such a tribunal and half the US allies not.
That's truth whether you like it or not. And you are not on the side of any freedom or rules-based order too, you are on the side that bombed Gaza for a year, and the genocidal (for real and not like Russia) Turkish state, and Saudi Arabia, and Gulf Arab monarchies.
No, just pointing out that there's difference between Russia's mischief level (similar to Saddam's level or frankly even US level in Iraq 2004) and the Nazi level (countries doing that are not being called mischievous by westerners, because their free uncensored media somehow magically by itself freely aligns with geopolitical policies of western governments).
And since the person I was answering is likely from a country allied with some of the latter, seems shameless for them to bring up Nuremberg.
"Russian influence operations" is a pompous way of saying that social media communities are big villages, and village culture gossip and bullshit and ape dynamics work there just as well.
Those "operations" are not significantly more complex than "bank support" calling you and saying you've got to tell them the 2fa code, or you lose all your money.
BTW, if something works well, it shouldn't be more complex. Just those people who designed social media to be vulnerable to such attacks - they should understand that social backdoors are just as universal as technical backdoors.
Ukrainian source. There is Ukrainian/western warmongering/self diminishing/impoverishing disinformation/narratives, including Ukrainian propaganda reposted verbatim such as this article. All counter narratives are labelled pro-Russian disinformation. Very common on all social media.
I have no idea whether there are some bot accounts on Bluesky, but it would be "not good" if Bluesky's bans are exclusively against anti-warmongering bots, to promote the Ukrainian/NATO bots/content, which on other social media, have deeply funded "SEO scoring" already.
This is where it all ends. "Everything I don't like is Russia/China/Iran".
Nothing evaluated on its merits. Nobody with a view different from mine is real. Evil Foreigners is the explanation for every bad take and un-pc post. Americans are only ever loyal patriots, villainous traitors, or useful idiots.
It's an information war like Hilary Clinton said.
The link goes to a site created less than two months ago kyivinsider. The source is from Alliance4europe.This is part of the DISARM Foundation, also know for AMITT (Adversarial Misinformation and Influence Tactics and Techniques) framework.
That one belongs to the Credibility Coalition, and that one to Meedan. A San Francisco based organization funded by the US National Science Foundation and many organizations like Meta, Amazon, etc.
The Russians are amateurs at propaganda in comparison to the US.
I love how this post makes a bunch of claims, and yet provides zero sources, and thus, has absolutely zero value.
It's digital noise, spam at best, evil misinformation at worst.
Propagandan is one of Kremlin's biggest tools, and it has been since the wall went up and it certainly never stopped when it came down.
Over time it has become the cheapest way for them for sow discord and infighting between their adversaries. Moving it online made it even cheaper and they've been at it hard the past decade or two.
Obviously the US have their own operations, but your point is not correct in any way. Look at what they've accomplished. The world is in chaos and they're largely responsible for a lot or even most of it, depending on how you look at the big picture.
I didn't express that last part correctly. I meant that it was probably a single guy making those bots. A lot more effective that multiple funders, agencies, organizations and private companies working on "democracy" and "transparency".
As for the fault. The trouble started with a coup in 2014. Then internal conflict and then Russia entered differently with war. At every step of the conflict you have the US behind. The coup to put a US puppet, arming them, blowing up Russian infrastructure, and using other countries to block Russian gas in favor of more expensive American gas. Russia has made clear they don't tolerate NATO in Ukraine. It is as logical as Russia putting military bases in Canada or Mexico.
You're wasting your time. I happen to live in a country with a very long border to Russia (guess which one) and I know you're full of shit simply because we're dealing with the motherfuckers daily. NATO is and always has been a defensive alliance. We all know that. Russia is simply using it as a really idiotic excuse to do what they wanted to do in the first place. We all know that too.
Simply put, the time for this kind of bullshit is over and done for. Nobody that isn't already dumb enough to side with those fucknuts believes any of this shit.
As for the US, yeah well up until Putin and his cronies got all the clowns to come out they weren't actively harming anyone deliberately. Sure, there are war crimes and assholes all over, but also a lot of good-natured and sincerely well meaning people. There have also been trials and sentences for said assholes, as opposed to Russia where you can beat your wife to death and it's all good.
You don't find a lot of good in Russia, and you haven't for a long time. My grandfather fought them, and either me or my son will probably fight them eventually. We've already taken action once. It won't stop there.
Yeah Lemmy too.
(edit: as in spreads to Lemmy too based on the brainrot I replied to)
U can have it bro.
Russian behavior in Ukraine is actually very nice.
They see Ukrainian like own people.
Israel on the on the other hand just genociding
For those who are NOT this person:
During the Russo-Ukrainian War,[3] Russia has forcibly transferred almost 20 thousand Ukrainian children to areas under its control, assigned them Russian citizenship, forcibly adopted them into Russian families, and created obstacles for their reunification with their parents and homeland.
Wikipedia, according to itself, isn't a reliable source when it comes to such internationally hot topics. It's primarily written by western young men who are mostly exposed exclusively to western media, and the articles they write are referenced by this same media. If you wanna read a bit more on this, I did a writeup some weeks ago about this very topic, sourcing my information from wikipedia itself.
With this I don't mean to say that the accusations you're showing are false, I honestly don't have enough information to confirm or deny it, but in times of war information is a powerful tool and media from both sides won't doubt to distort information to benefit their own countries.
Could you please do me the favour and read my writeup before responding like that? I addressed what you're saying.
Wikipedia itself has an article on its own bias, and an article on which sources the wiki editors consider reliable. Feel free to read my writeup for extended info on that.
Is your writeup about that specific article? Because if not, it's irrelevant. You can judge whether the source is reliable by going there, which you are apparently unwilling to do because you've already decided it's too biased.
Also, there are Wikipedia editors from all over the world. I think you know that too.
Seems like your real problem is they're being big meanies to Russia which only has the best intentions for Ukrainians and would never commit any war crimes.
Is your writeup about that specific article? Because if not, it's irrelevant.
You can just say you don't care to read about the intrinsic biases in wikipedia in specific topics and that you'll keep uncritically using it.
Also, there are Wikipedia editors from all over the world
Wikipedia ITSELF acknowledges that the vast majority of articles, especially those written in "western" languages, are edited primarily by western men. I'm not making shit up, Wikipedia literally talks about it in a meta-article about bias in wikipedia.
Seems like your real problem is they're being big meanies to Russia which only has the best intentions for Ukrainians and would never commit any war crimes.
Russia is a capitalist regime on a downwards spiral to fascism, and it's perfectly capable of committing war crimes, it's currently ongoing in increasing oppression of its own women and LGTBQ. That doesn't mean we should take Wikipedia's word during war time for granted. Go through the sources of the article and tell me how many non-western or non-Ukrainian ones are used. I've seen an article from the Russian oppositional media "Meduza" but I unfortunately can't read Russian so I can't really tell what it says. Plenty of other reference from outright US/Ukraine propaganda outlets such as the "conflict observatory", a US "NGO" receiving money from the NED; or such as Ukrainian media, which obviously have a stake in this topic.
Please, give my writeup a chance, and if you have anything to comment on it, feel free to let me know
I do not need to read your writeup to know that this information comes from sources other than Wikipedia. It doesn't matter what it acknowledges about "the vast majority of articles," because any one article, this one included, can be an exception.
I unfortunately can’t read Russian so I can’t really tell what it says.
How do you not know about Google Translate at this point? Or is that full of "Western bias" too?
What source would you even trust?
My point is that there aren't many sources to trust for now, not from one side and not from the other, because of the ongoing conflict and information war. You can't trust the New York Times in the same way you probably wouldn't trust Russia Today.
If you saw a collectively edited article related to the Ukrainian War, edited primarily by Russian men, using Russian sources (whether state or private), would you trust it? Would you trust a collectively edited article on Taiwan edited primarily by Chinese men using primarily Chinese sources (whether state or private)? If the answer is yes I'll shut up, if the answer is no, then why do you do it with Wikipedia?
I don't trust anyone, surely everyone is lying. Both sides have a very strong interest on propagating opposite points of view. Framing Russia as the saviours of the Russian population in Crimea and Donetsk against Ukronazis is very beneficial to Russia, framing Russia as a war criminal country kidnapping children is very beneficial to NATO.
Remember Nayirah's testimony? Remember the WMDs in Iraq?
I wonder if you would have felt that way about reports of the Holocaust in the 1940s... you can't trust any of that propaganda. Everyone is lying. Maybe there is no genocide in Nazi Germany.
Also, again, if everyone is lying, they both are kidnapping children and they are not kidnapping children. Are these Schrödinger's Children?
I was talking about what you would have believed. But I guess the answer is you would have denied it was happening.
And you have not explained how, if both sides are lying about it, the children can be in a kidnapped/not kidnapped superposition.
They are removing children away from Frontline, something Palestinians can only dream of.
You've lied about me over and over and now you expect me to believe that?
Still waiting to hear what you've done to try to stop the genocide. Other than lie about people online, obviously.
I called my reps.
And I advocate online.
U just banned me under some absolutely fake reason. Go home israelloving troll
Still lying about me I see.
And I think we both know why.
Looking it up, I see the "fake reason" you were banned was bigotry.
Doesn't look like a fake reason to me.
U are just hellbent on defending Israeli murderers
Yes, you've already made it very clear that you think Jew = Israeli.
And apparently that you don't think that's bigoted. It is.
I believe america is broke.
It lost manufacturing advantage and rapidly falling behind china in most areas.
Nothing is made here anymore.
And then - us won't engage in the open conflict with Russia, it can't - which means the only option is sending weapons and hopes and prayers.
This model - the only thing it accomplishes is prolonging the suffering with inevitable ukraine defeat. Same with Taiwan - us can't win that war and should just let it go.
I don't see a point in that. I don't care about that.
I say - just cut a deal with Putin and move along.
This is one of the few things I agree with Trump on.
Their current Ukrainian government is harassing their language and heritage. Do u know the majority of Ukrainians speak Russian?
Russia gives Ukrainians full citizenship with all rights and preserves medical and pensions. And evacuated children away from warzone. Russia Cares.
Israel just wants empty space and genocides everyone.
Don't have to try Squidward , it's a reality. U are genocide supporter.
Answer this question - should Palestinians have rights and not be bombed indiscriminately?
Of course they should. That's why I spend hours every week contacting politicians to stop this genocide.
What have you done about it?
Let me guess- you think I think I'm one of the good guys.
But there are no good guys. Humans are selfish assholes. All of them. Unless you want to argue that you are one of the good guys.
Bet you think I'm lying about not being an Israeli too.
no i don't think you're one of the good guys.
good people exist
i don't care where you're from.
That's not what I said. You aren't even reading my posts.
Let me guess- you think I think I’m one of the good guys.
First you don't realize I said my daughter was queer, now this.
You don't read, you just assume you've read.
I voted for Kamala to prevent my own gay daughter from being part of Trump's genocide. Sorry, I care about my daughter more than anyone else in this world and I am going to do what is best for her. Which is why we fled the U.S. when Trump won.
But let me guess- I should care about people other than my daughter first. And also, queer people aren't in any danger under Trump.
Called it. There's only one genocide that matters and it only matters because Palestinians can be used as a pawn in internet argument.
Fuck queer people as usual.
By the way, there are queer Palestinians, many in the U.S. I want you to find one and tell them that they have nothing to be worried about. Not that you will since you've already decided fuck them.
Is your brother Palestinian? Otherwise that is irrelevant except to show that you don't really care about his life. Which doesn't shock me.
But you only sort of caring about the Palestinians who fit the cishet mold is noted.
I don't "know a gay person," I literally fled the U.S. because my daughter is queer. You misrepresenting what I said in a really bigoted way does not speak well of you.
Again, though, you only (sort of) caring about cishet Palestinians is noted.
Tell you what, you start actually paying attention to what you read in my posts and we'll talk.
I won't be holding my breath.
I think people downvote quite more readily to show disagreement here, not in the least because downvoted comments don't get buried.
And, like, seriously. If you can't even muster thoughts and prayers, if you can't even muster being indifferent, can't muster simply not leaving a comment at all, but have to shout your disapproval of Ukraine existing as a sovereign state from the rooftops, you're an asshole. Unambiguously.
In this case, probably an attention troll.
like this
FundMECFS likes this.
You are literally reading EU state propaganda in this very post, an article by "kyivinsider" sourcing its information from "alliance4europe", funded by the European Parliament and the Polish International Affairs ministry among others (according to its own website, feel free to check the link inside the article).
That doesn't mean that it's fake news or anything, the report is most likely true, just that it's really ironic that we're consuming state propaganda designed to make us worried about state propaganda from other "evil" countries (unlike our glorious EU parliament, not on a fascist downward spiral at all)
like this
FundMECFS likes this.
The problem of platforms when they become big. Just like cyber criminals lurk on systems used by the mass to exploit. Things can be used for good and for bad. And its often the small portion of bad that ruins it for large majority. Just like the few football hooligans that screw things up for the rest.
Bad intend or behavior is just hard to manage in a free online world. If Elon is hated then Adrian will take over....
Google says it will change Gulf of Mexico to 'Gulf of America' in Maps after government updates
Google says it will change Gulf of Mexico to 'Gulf of America' in Maps after government updates
In posts on X on Monday, Google said it will follow the government's lead in changing the names on its Maps app.Jennifer Elias (CNBC)
Seriously. Let’s start a war on google.
Make sure you get rid of your Gmail account ;)
Qual è la migliore VPN per connettersi all'Italia dall'estero?
Sto chiedendo per una mia amica italiana che vive in Austria (usa macOS).
Ho trovato ExpressVPN, ProtonVPN e PrivadoVPN. Ma non sono un esperto in questo campo. Qualsiasi raccomandazione è molto apprezzata. Grazie in anticipo.
Migliore VPN Italia nel 2025: Ottieni indirizzo IP italiano | ExpressVPN
Proteggi il tuo indirizzo IP per accedere liberamente a tutti i contenuti in Italia con una VPN veloce e sicura. Rimborso garantito entro 30 giorni.www.expressvpn.com
Informatica (Italy e non Italy 😁) reshared this.
Informatica (Italy e non Italy 😁) reshared this.
Civil Service 'Disgust' After DWP Launches Welfare Campaign With The Sun, [Accused] of ‘Demonising’ Benefit Claimants
Washington Post Boss Will Lewis Informed the Police on ex-PM Gordon Brown and Lord Tom Watson with Allegedly ‘Fake’ story – Byline Times
Lewis was allegedly trying to destroy evidence of phone hacking to save Murdoch and his top executive Rebekah Brooks from police prosecution, Byline Investigates and Yellow Press reported on MondayGraham Johnson (Byline Times)
Google Maps in the US will change to Gulf of America and Mount McKinley
Google Maps to show Gulf of America and Mount McKinley
Google announced that once the Geographic Names Information System updates, it will change the names of the Gulf of Mexico and Mt. Denali in Google Maps.Todd Haselton (The Verge)
Serbia’s prime minister and Novi Sad mayor resign as anti-corruption protests grow
BELGRADE, Serbia (AP) — Serbia’s populist Prime Minister Milos Vucevic resigned Tuesday in an attempt to calm political tensions following weeks of massive anti-corruption protests over the deadly collapse of a concrete canopy.
The canopy collapse in November, which killed 15 people in the northern city of Novi Sad, has become a flashpoint reflecting wider discontent with the increasingly autocratic rule of Serbia’s populist President Aleksandar Vucic. He has faced accusations of curbing democratic freedoms in Serbia despite formally seeking European Union membership for the troubled Balkan nation.
Novi Sad Mayor Milan Djuric also will step down on Tuesday, Vucevic said.
Vucevic’s resignation could lead to an early parliamentary election.
https://apnews.com/article/serbia-protests-vucevic-resigns-b71e3a0aacf5d0368b2bd1f4500170f5
Serbia’s prime minister and Novi Sad mayor resign as anti-corruption protests grow
BELGRADE, Serbia (AP) — Serbia’s populist Prime Minister Milos Vucevic resigned Tuesday in an attempt to calm political tensions following weeks of massive anti-corruption protests over the deadly collapse of a concrete canopy.
The canopy collapse in November, which killed 15 people in the northern city of Novi Sad, has become a flashpoint reflecting wider discontent with the increasingly autocratic rule of Serbia’s populist President Aleksandar Vucic. He has faced accusations of curbing democratic freedoms in Serbia despite formally seeking European Union membership for the troubled Balkan nation.
Novi Sad Mayor Milan Djuric also will step down on Tuesday, Vucevic said.
Vucevic’s resignation could lead to an early parliamentary election.
https://apnews.com/article/serbia-protests-vucevic-resigns-b71e3a0aacf5d0368b2bd1f4500170f5
like this
Oofnik, SolacefromSilence, Dantpool, Maeve e Lasslinthar like this.
like this
Maeve likes this.
like this
Maeve likes this.
like this
Maeve likes this.
like this
Maeve likes this.
like this
Maeve likes this.
Serbian protests had the support of most of the general population. The students faced a lot of state violence as well, but this only made their case stronger and caused more people to join. Protests like these for the most part are a numbers game. The more people join in the safer it is. The US population has been pacified and I see the only way to improve conditions is to agitate and depacify.
So you’re right that the condition in the US are different and that a different approach might be needed, but sitting by and doing nothing will for sure not help. I’m really tired of people on lemmy throwing their hands in the air while less fortunate people are being harmed by your government’s actions. It pains me to see how little people actually care if it turns out they need to actually make sacrifices to change anything.
like this
FartsWithAnAccent, chookity, timlyo, Dantpool, Chozo, magnetichuman, massive_bereavement e Lasslinthar like this.
like this
Chozo likes this.
I believe the official instance already got most of the people who would want to use Bluesky in it.
And even if people did start self hosting their own instances, I am not sure if they could handle the traffic.
Exactly. It's not perfect, but it's an improvement. They might have said something equally bad like "we are moving to facebook".
We need visibility to such institutions because the younger generation is not interested in parsing a website or RSS feed for information and news (this is a sad fact) but rather parse social media. Far right, mis/disinformation will be there for everyone to see. We need scientific and public institutions to be visible.
I think enshittification of "traditional" software already gave enough initial visibility for fediverse and the word "decentralization" that when bluesky goes to shit it's already less of a new thing to move to - let's say - mastodon hosted by EU or whatever.
Edit: added more to the second paragraph.
like this
Skua likes this.
Yes. Once a large enough concentration of users is achieved, the network effect kicks in and the users are locked in.
With that amount of users, it becomes a juicy target for businesses who colonize the place to milk said users. That's assuming the original founders haven't already been kicked out and replaced by suits who just invite businesses, influencers, creators, propagandist and so on in and charge them for the privilege. That locks in businesses.
With users and business both locked in, squeeze them for an they're worth until the pain gets too big and the users leave for another platform. Go to step 1.
This is my biggest issue with discourse on here or Reddit. If something isn't literally perfect it's treated as being absolutely horrible.
I'll take minor improvements here and there over sticking to something awful and endlessly complaining about it.
The level of effort to move to mastodon is not that much more than moving the bluesky. I agree not letting perfect be the enemy of good but this is a situation where they could have done something substantially better with only slightly more effort.
Am I glad they left Twitter? Sure.
Is there anything wrong with bluesky? Not right now.
Even if they moved to a managed mastodon instance, it would have been better.
I'm on Mastodon, and while it's not much more effort to move to, it's certainly:
- Less features
- More complicated
- Practically unheard of
- Lacking in users (unsurprisingly this one is absolutely crucial)
I wanted to leave Twitter too. I'm a professional engineer in tech and I found setting up in Mastodon to be... ...not straightforward, as did a whole load of other people. I eventually got set up. I couldn't find anyone or anything, the whole model being based around local instances rather than users or topics but.. I tried to make the best of it and I followed the other people who had left Twitter that I had followed there when they said where to find them on Mastodon. Then I found I had run into a 'silencing' drama where some other instance admins had taken issue with an admin for the instance I was signed up to and as a result everyone on my instance was essentially shadowbanned in a whole load of other places. It had been happening maybe a month before I even found out about this. I'm a grown up, I don't have time for school time drama. I found that I was using Mastodon less and less and so were the people I had been following. Then my BlueSky invite came through. I can find topics and I can find users. People post and people respond. I don't have to worry which of 100 identical usernames across different instances is the 'real' one or my instance being defederated or silenced.
The problem with Mastodon is it's basically a social network for people who are into Mastodon, and enjoy centering around their specific instance. It might work for Warcraft guilds but it doesn't work for me, or any of the people or topics I want to follow, ostly current affairs and tech. As opposed to BlueSky which is a social network for people who:
- Want to move on from twitter
- Are interested in finding and following people and or topics
No doubt at this point you will want to tell me how I'm all wrong, clearly tech illiterate and how Mastodon has at least as many users as BlueSky. Sure, whatevs. It's like Linux on the Desktop, not a viable mass-market proposition at this point (saying this with 25 years Linux desktop experience).
I'm not sure we are having the same conversation. You are talking about how Mastodon was not a good fit for you personally, maybe because of a bad server.
I'm saying that lots of people use it for all sorts of great things, and it's an excellent option for a public health agency.
Why are all the comments here whataboutism?
Can’t we just agree it’s fucking awful China is censoring it’s massacres?
We do agree on that, but it's weird to act as if this is somehow worse than OpenAI; try asking ChatGPT about Palestine.
Turns out our fantasies about genius AI that will make our lives better don't really work when those AIs are programmed, both intentionally and unintentionally, with human biases.
This is why I get so angry at people who think that AI will solve climate change. We know the solution to climate change, and it starts with getting rid of billionaires. But an AI controlled by billionaires is never going to be allowed to give that answer, is it?
Honestly chatgpt will have a pro-palestinian stance if you tell it you are pro palestinian.
Deepseek doesnt do that.
FundMECFS likes this.
Req. skill tree input: saying bye to big tech
Sensitive content
I don't have to explain to this audience why one would want to avoid "big tech", that is your Google, Amazon, Facebook, and so on.
I'm working with a group to create a skill tree for dropping big tech, but could use some more ideas.
A skill tree is a chart with actions and skills, ordered from easy to advanced, where you can check which skills you already have and be inspired with other skills.
An example: github.com/sjpiper145/MakerSki…
More Maker skill trees: github.com/sjpiper145/MakerSki…
We want to make it easy for people to switch, and motivate people towards a more open and ethical (tech) world.
We already have a list of general actions for the tree, ranging from general concepts like "learn what Open Source means" to specific actions like "search with DuckDuckGo".
I want this to be a good list that actually helps, that is fun and interesting, easy to use, and inspiring, which is why I'm asking you for help.
Can you think of things that should definitely (or definitely not) be on this list?
I would appreciate all the help I can get.
(x-post from Ask Lemmy since this might be a good audience for the topic)
MakerSkillTree/Makerspace Skill Trees/Makerspace Skill Tree.png at main · sjpiper145/MakerSkillTree
A repository of Maker Skill Trees and templates to make your own. - sjpiper145/MakerSkillTreeGitHub
Here's a list:
- learn about federation and decentralisation
- understand the Free Software Definition
- find out the difference between "Open Source" and "Proprietary."
- learn the difference between "free" and "libre"
- research how popular free services make money
- find a recent list of privacy-respecting software or Open Source applications
- switch to a privacy-focused search engine like DuckDuckGo and set it as your default
- install an ad blocker in your browser
- try a privacy-respecting email provider
- use a privacy-friendly browser
- start using a privacy-focused messaging app
- install LibreOffice for office documents
- download an Open Source app from F-Droid
- share a document using the OpenDocument format
- find and follow friends on the fediverse
- delete accounts on big tech platforms
- talk to a friend about why they should try Open Source
- experiment with chat solutions like IRC, XMPP, or Briar for offline mesh communication
- host a small group video call using Jitsi
- organise a "Switch Party" to help friends adopt new platforms
- de-Google your phone by installing a custom ROM (e.g., GrapheneOS, LineageOS, /e/OS)
- use an encrypted email client
- set up your own cloud storage with NextCloud
- compare two privacy-friendly email providers
- discover how to report issues in Open Source projects
- write to a company or government agency asking for documents in OpenDocument format
- host your own Mastodon server
- develop or contribute to Open Source tools
- find and explore the source code of an Open Source project
- replace the battery in your phone
- bring an old device back to life with Open Source software
- try a "dumb phone"
- find a device manufacturer who shares the source or design of their hardware/software
- spend two days without social media
- shop at a physical store instead of online
- use cash instead of digital payment methods
- convince a coworker to share a document in an open format
- convince your employer to share documents in an open format
- give a talk about the importance of public services and open technologies
- write or share a guide for switching to privacy-respecting software
- organise a local meetup or workshop to help others switch
I forgot one: "brush Richard Stallman's beard".
That probably goes in the "advanced" area. 😉
Will do, thanks.
There's more options there, from Tor to ad-blocking yet privacy-respecting VPNs to mirrors of websites and paywall circumvention tactics.
True. It's not all black and white.
But I'm sure you understand the general idea behind the project.
African nations set to light up the homes of 300 million people by 2030
African nations set to light up the homes of 300 million people by 2030
Several African nations have committed to open up their electricity sectors to attract investors and light up the homes of 300 million people currently lacking power over the next six years.RFI
A plan dubbed "Mission 300", launched by the World Bank and the African Development Bank (AfDB) last April, is now racing to connect half of those homes to power by 2030.
Oh, so a bunch of people are going to get fucked over.
Edit: I think some of you need to read up on the World Bank, especially what they are responsible for when it comes to indigenous people.
Open-source Deepseek R1 dethrones commercial AI, now allegedly being hit by cyberattack
DeepSeek hit with large-scale cyberattack, says it's limiting registrations
DeepSeek on Monday said it would temporarily limit user registrations "due to large-scale malicious attacks" on its services.Hayden Field (CNBC)
"Open source" and "commercial" aren't opposites, plenty of models we consider commercial are also 'open source' - an obvious example being Facebook/Meta's models...
Looking outside of AI there's plenty more examples. Chromium is open source, does that mean it and Google's Blink web rendering engine is non-commercial? I'd say no.
Should also be noted that there's been some pushback recently on whether models trained on closed sources should be called "open source", just because the model itself is.
Fair, but even if it is commercial, the project being open-source is a huge step in the right direction. Specifically for DeepSeek, it has a number of censored topics like "Tiananmen Square" that it refuses to speak to, but because it's open source, unaffiliated third parties have been able to start spins of it that reintegrate said sensitive topics.
Perfect? Definitely no, but I'd say it's almost 50% of the way there compared to the awful nature of ChatGPT/Google's models. And it also made people realize that this is possible, so there'll be more people taking it in a good direction that otherwise might not've tried.
The Open Source Initiative have defined what they believe constitutes "open source AI" (opensource.org/ai/open-source-…). This includes detailed descriptions of training data, explanation on how it was obtained, selected, labeled, processed and filtered. As long as a company utilize any model trained on non-specified data I will assume it is either stolen or otherwise unlawfully obtained from non-consenting users.
I will be clear that I have not read up on Deepseek yet, but I have a hard time believing their training data is specified according to OSI, since no big model yet has done so. Releasing the model source code means little for AI compared to all its training data.
The Open Source AI Definition – 1.0
version 1.0 Preamble Why we need Open Source Artificial Intelligence (AI) Open Source has demonstrated that massive benefits accrue to everyone after removing the barriers to learning, using, sharing and…Open Source Initiative
Indeed. This is what I was thinking of, except I couldn't remember whether it was OSI or FSF pushing for it and, well, I'm too lazy to check lol
Thanks
No AI org of any significant size will ever disclose its full training set, and it's foolish to expect such a standard to be met. There is just too much liability. No matter how clean your data collection procedure is, there's no way to guarantee the data set with billions of samples won't contain at least one thing a lawyer could zero in on and drag you into a lawsuit over.
What Deepseek did, which was full disclosure of methods in a scientific paper, release of weights under MIT license, and release of some auxiliary code, is as much as one can expect.
As i wrote in my comment i have not read up on Deepseek, if this is true it is definetly a step in the right direction.
I am not saying i expect any company of significant scale to follow OSI since, as you say, it is too high risk. I do still believe that if you cannot prove to me that your AI is not abusing artists or creators by using their art, or not using data non-consentually acquired from users of your platform, you are not providing an ethic or moral service. This is my main concern with AI. Big tech keeps showing us, time and time again, that they really dont care about about these topics and this needs to change.
Imo AI today is developing and expanding way too fast for the general consumer to understand it and by extension also the legal and justice systems. We need more laws in place regarding how to handle AI and the data they use and produce. We need more education on what AI actually is doing.
Stocks take a hit with new foreign competition and they are immediately attacked. Coincidence I'm sure lol
"We will deport you too if you sign up to deepseek!"
-Trump admin probably
Open-source Deepseek R1 dethrones commercial AI, now allegedly being hit by cyberattack
DeepSeek hit with large-scale cyberattack, says it's limiting registrations
DeepSeek on Monday said it would temporarily limit user registrations "due to large-scale malicious attacks" on its services.Hayden Field (CNBC)
like this
geneva_convenience likes this.
deepseek-ai/DeepSeek-R1 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.huggingface.co
Do they not know it works offline too?
I noticed chatgpt today being pretty slow compared to the local deepseek I have running which is pretty sad since my computer is about a bajillion times less powerful
Thanks
Any recommendations for communities to learn more?
Frustratingly Their setup guide is terrible. Eventually managed to get it running. Downloaded a model and only after it download did it inform me I didn't have enough RAM to run it. Something it could have known before the slow download process. Then discovered my GPU isn't supported. And running it on a CPU is painfully slow. I'm using an AMD 6700 XT and the minimum listed is 6800 github.com/ollama/ollama/blob/…
ollama/docs/gpu.md at main · ollama/ollama
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models. - ollama/ollamaGitHub
🏡 Home | Open WebUI
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline.docs.openwebui.com
Thanks, I did get both setup with Docker, my frustration was neither ollama or open-webui included instructions on how to setup both together.
In my opinion setup instructions should guide you to a usable setup. It's a missed opportunity not to include a docker-compose.yml connecting the two. Is anyone really using ollama without a UI?
No. It literally cannot count the number of R letters in strawberry. It says 2, there are 3. ChatGPT had this problem, but it seems it is fixed. However if you say “are you sure?” It says 2 again.
Ask ChatGPT to make an image of a cat without a tail. Impossible. Odd, I know, but one of those weird AI issues
Because there aren't enough pictures of tail-less cats out there to train on.
It's literally impossible for it to give you a cat with no tail because it can't find enough to copy and ends up regurgitating cats with tails.
Same for a glass of water spilling over, it can't show you an overfilled glass of water because there aren't enough pictures available for it to copy.
This is why telling a chatbot to generate a picture for you will never be a real replacement for an artist who can draw what you ask them to.
Oh, that’s another good test. It definitely failed.
There are lots of Manx photos though.
Manx images: duckduckgo.com/?q=manx&iax=ima…
It searches the internet for cats without tails and then generates an image from a summary of what it finds, which contains more cats with tails than without.
That's how this Machine Learning progam works
So what training data does it use?
They found data to train it that isn't just the open internet?
Oh ok so training data doesn't matter?
It can generate any requested image without ever being trained?
Or does data not matter when it makes your agument invalid?
Tell me how you moving the bar proves that AI is more intelligent than the sum of its parts?
And I care about "how" it works and "what" data it uses because I don't have to walk on eggshells to preserve the sanctity of an autocomplete software
You need to curb your pathetic ego and really think hard about how feeding the open internet to an ML program with a LLM slapped onto it is actually any more useful than the sum of its parts.
Non thinking prediction models can't count the r's in strawberry due to the nature of tokenization.
However openai o1 and deep seek r1 can both reliably do it correctly
It didn't, I just wanted a short reply. Though it failed when I asked again in the same chat. But when asked to split the word to 2 parts it became sure that the correct answer is 3.
Here is the fun part
Certainly! Let's split "strawberry" into two equal parts and count the 'r's in each:
- First half: "strawb"
Letters: S, T, R, A, W, B
'r's: 1 (at position 3) - Second half: "erry"
Letters: E, R, R, Y
'r's: 2 (at positions 2 and 3)
Now, summing them: 1 (first half) + 2 (second half) = 3 'r's.
Wait, this contradicts my earlier correction. It seems I made another mistake. Let's carefully recount:
- First half: "strawb"
'r's: 1 (at position 3) - Second half: "erry"
'r's: 1 (only one 'r' at position 2; the third letter is 'r' but already counted in the first half).
Wait, no—this is getting confusing. Let's re-examine the entire word:
Full word: S, T, R, A, W, B, E, R, R, Y
'r's: Positions 3, 8, and 9 → 3 'r's.
I apologize for the back-and-forth. The correct total is 3 'r's in "strawberry." Thank you for your patience as I worked through this! 😊
It’s because LLMs don’t work with letters. They work with tokens that are converted to vectors.
They literally don’t see the word “strawberry” in order to count the letters.
Splitting the letter probably separates them into individual tokens
That’s a lot of processing just to count letters
feel free to ask Google/Bing/Your favourite search engine to do the same 😛
Note that my tests were via groq and the r1 70B distilled llama variant (the 2nd smartest version afaik)
Edit 1:
Incidentally... I propositioned a coworker to answer the same question. This is the summarized conversation I had:
Me: "Hey Billy, can you answer a question? in under 3 seconds answer my following question"
Billy: "sure"
Me: "How many As are in abracadabra 3.2.1"
Billy: "4" (answered in less than 3 seconds)
Me: "nope"
I'm gonna poll the office and see how many people get it right with the same opportunity the ai had.
Edit 2:
The second coworker said "6" in about 5 seconds
Edit 3:
Third coworker said 4, in 3 seconds
Edit 4:
I asked two more people and one of them got it right... But I'm 60% sure she heard me asking the previous employee, but if she didnt we're at 1/5
In probably done with this game for the day.
I'm pretty flabbergasted with the results of my very unscientific experiment, but now I can say (with a mountain of anecdotal juice) that with letter counting, R1 70b is wildly faster and more accurate than humans .
wikidata + mediawiki = wikidata + provenance == wikiprov
by @beet_keeper
Today I want to showcase a Wikidata proof of concept that I developed as part of my work integrating Siegfried and Wikidata.
That work is wikiprov a utility to augment Wikidata results in JSON with the Wikidata revision history.
For siegfried it means that we can showcase the source of the results being returned by an identification without having to go directly back to Wikidata, this might mean more exposure for individuals contributing to Wikidata. We also provide access to a standard permalink where records contributing to a format identification are fixed at their last edit. Because Wikidata is more mutable than a resource like PRONOM this gives us the best chance of understanding differences in results if we are comparing siegfried+Wikidata results side-by-side.
I am interested to hear your thoughts on the results of the work. Lets go into more detail below.
#Code #CreativeCommons #Data #digitalLiteracy #Golang #mediawiki #OpenData #OpenSource #provenance #reification #reify #siegfried #SPARQL #wikibase #wikidata
In phone call, Modi, Trump resolve to promote global peace, security
In Phone Call, Modi, Trump Resolve to Promote Global Peace, Security
PRIME MINISTER Narendra Modi and US President Donald Trump on Monday vowed to work towards a "trusted" partnership between India and US and advance global peace and security in their first phone conversation since the American leader's inauguration l…shajil kumar (Indiaweekly)
“During a one-on-one meeting, Mosquitos vowed to work toward all creatures keeping their own blood.”
Gtfoh
Trump to impose 25% to 100% tariffs on Taiwan-made chips, impacting TSMC
Trump to impose 25% to 100% tariffs on Taiwan-made chips, impacting TSMC
The latest News,/news,,news, breaking news, comment, reviews and features from the experts at Tom's HardwareAnton Shilov (Tom's Hardware)
like this
SuiXi3D, bacon_saber e geneva_convenience like this.
Technology reshared this.
like this
SuiXi3D e Shawdow194 like this.
like this
SuiXi3D e Shawdow194 like this.
like this
Shawdow194 likes this.
TSMC have advanced chip fabrication factory in Arizona in the US.
"TSMC will produce 3nm chips in the U.S., and Taiwan has already given TSMC the go-signal to manufacture 2nm chips abroad."
tomshardware.com/tech-industry…
Apple will soon receive ‘made in America’ chips from TSMC's Arizona fab — company in final stages of quality verification
Mass production could begin as soon as Q1.Jowi Morales (Tom's Hardware)
But it cannot produce the higher end chips. That was explicitly part of the agreement when they built the facility. They're only willing to fab low end product outside of Taiwan.
I was being very specific when I said "their best processes."
like this
Shawdow194 likes this.
I wouldn’t say 5nm and 3nm are low end
tomshardware.com/tech-industry…
TSMC's Arizona Fab 21 mass produces 4nm chips at a higher price than Taiwan
But customers are willing to pay extra, says TSMC.Anton Shilov (Tom's Hardware)
Sure, "low end" wasn't a perfectly scientifically accurate way to describe it. I apologize for my terrible lack of academic rigor.
The point is that they're not going to let their highest end processes be replicated outside of Taiwan. Or, rather, the Taiwanese government is not going to let that happen, because fear of losing access to that technology is their one bargaining chip with the West. Without that, they cease to exist as a country. There just isn't enough incentive for anyone to risk a war with China otherwise.
Totally agree that it’s a sound strategy to keep their latest and greatest on home soil.
At the same time they are starting to implement tooling for important parts of clients designs like
Core chiplets for Ryzen
iPhone SOCs
pcgamer.com/hardware/gaming-mo…
AMD is now reportedly making all-American Ryzen 9000 CPU dies at TSMC's Arizona fab
Made in the USA, mostly anyway...Jeremy Laird (PC Gamer)
People downvoting you can’t do a quick search:
tomshardware.com/tech-industry…
TSMC is absolutely up and running already in the US.
Apple will soon receive ‘made in America’ chips from TSMC's Arizona fab — company in final stages of quality verification
Mass production could begin as soon as Q1.Jowi Morales (Tom's Hardware)
Yeah I know, talking a lot of blowhard talk. Chip die size was the arbitrary argument, but again, that just takes time. They are hedging their bet with a supposed ally with China being their big threat.
"TSMC will produce 3nm chips in the U.S., and Taiwan has already given TSMC the go-signal to manufacture 2nm chips abroad. "
The US could probably do it... With hundreds of billions of government incentives to rapidly stand up the entire supply chain... Which would still take at least a decade. The machines that TSMC uses are made by ASML and themselves have a global supply chain of over 500 separate companies and are backordered for several years due to their inherent value.
In short, no.
It will take them 20 years to catch up to the 5-7 years they are behind, even with all the money in the world.
As you say, it's setting up the supply chain.
Intel has been trying to get itself into that position for years, with huge amounts of public money being pumped in, and it is struggling so badly the company lost patience and fired the CEO who had the best chance of getting this done. And, as others have said, it doesn't look like TSMC is about to let its US fabs do the most advanced stuff even if they could.
So this move will just make the best technology less accessible to the USA and tech products more expensive for Americans, for the foreseeable future.
From what I understand one of the things that is protecting Taiwan from China is their fabs. They will fight for their lives to make sure they are protected by this.
As someone with family over in Taiwan, I really want them to be okay. Things are getting depressing globally.
Everything will be more expensive, if it uses a modern CPU. Phones, tablets, computers of any type from any company (both Intel and AMD are fabbing consumer CPUs on TSMC, as is Apple and Qualcomm), TVs, set top boxes, everything.
Right now TSMC is basically the only fab anything consumer-facing is made on, which is not a great thing in general, but vice president trump just decided that anything electronic needs a hefty price hike.
He emphasized that the proposed tariffs would leave companies with no choice but to invest in domestic production facilities to avoid high taxes.
No choice except the obvious: Pass the cost of the Tax into the customer because there’s no way they’re going to spend billions to stand up a US fab plant anytime soon.
That's just how tariffs work. They're not a weapon against enemy nations. They're a tax on Americans.
And nobody is going to bring production back to this fascist slave pen of a country.
I say this not to be reactionary or pro trump.
Is there no way to use lesser nodes for wider applications? While there are processes that need as much speed as possible, I feel like what gives Taiwan semiconducting industries such great business is the fact that code optimization isn't as cost effective as the latest and greatest chips.
I HOPE these tariffs inspire better, more secure code to make less efficient chips more viable. Like a lemon to lemonade situation.
If you optimize code, it will still run faster if the CPU or GPU is 30% faster.
If you make 50% speed improvements with code, you get 65% improvement with code+hardware upgrades. The hardware multiplies your software gains.
Also, half of the gains in recent years have been in energy efficiency, not just speed.
So if the idea is to do more with less, you don’t wanna rely on old power-hungry designs.
To avoid this, the administration would need to introduce exemptions, just like it did with China-made graphics cards and motherboards years ago.
If that is the approach, it would ensure tech monopoly for 5 years for all of the oligarchy that kisses his diaper.
More major issues with this is that while high end Chip production may be high value manufacturing, motherboards, electronics, and assembly is not, and there would likely be an export of chips to somewhere else to import finished products.
US/Trump explicit hatred for world is likely to get retributive tariffs, that makes chip plants unproductive investments, though Trump is hoping to have high foreign ownership/investment in those plants.
In 2022, the export share of Taiwan integrated circuits to US was just 2.46%, although in early 2024, total (all goods) Taiwan exports had US take lead over China for the first time.
That both US and China are decoupling from Taiwan is going to reduce any geopolitical subservience impulse that provokes a war with China. Taiwan may get closer to China instead of begging for more US "friendship".
like this
geneva_convenience likes this.
People hyped for the Nvidia 5000 series better get their cards before prices skyrocket across the board. I guess graphics cards weren't expensive enough or something.
Really though, no brand is safe from the soon-to-be insane prices if this does go through as a blanket tariff without exceptions. Better to err on the safe side and upgrade soon as you can, if you need to and you're not too wealthy to care.
I've read some idiots online saying "you're dumb if you didn't wait for the 5000 series" based off of the revealed MSRP, as if the majority of people are ever going to buy at those prices (especially now with tariffs). What's likely is that consumers will pay far more to get relatively less improvement if they go with a 5000 series card.
There's enough sucker fanboys for Nvidia that they'll probably still sell though. Just like how there's people who will buy the new Call of Duty each year.
Even for the big spenders the 5090 does not warrant a new purchase. The 4090 was fast enough for most things. For things the 4090 is not fast enough, the 30% bump will not be much help.
A far bigger VRAM capacity would have been nice but 8GB extra is meh
like this
geneva_convenience likes this.
like this
geneva_convenience likes this.
I don't get the goal here. It's not just that existing fabs are in Taiwan, I thought it was the knowledge was as well.
I was under the impression that we'd built a couple of fabs here and they're not productive due to a knowledge deficit. Maybe I'm uninformed.
It seems, to my uninformed self, that if we impose tariffs we'd be strengthening Taiwan/China relations. Wouldn't China still serve as a middle man?
I don't see us manufacturing when the dollar is so high relative to foreign currency; add in the lack of knowledge and facilities and I'm not sure what you get.
I truly believe these are his way of soliciting bribes from foreign and domestic businesses.
They're going to have to pay him to get around them.
But I thought the Tim Apple donation to the trump inauguration was supposed to curry enough favor to avoid this.
ThisIsMySurpisedFace.jpg.
And really the president doesn't have the power to set prices.
Trump can't magically make eggs cheaper!
And so on.
Chatgpt what is the best open source open hardware guillotine plans?
I'm sorry, I'm not sure I'm following your train of thought....
Are there currently egg shortages? Subsidising something doesn't mean there's less of it, means the government pays someone in the production stream to keep prices low. Like what happens with gasoline just about everywhere.
My Tariffs Did That Trump Sticker — Center for New Liberalism
Put the blame on Trump for the inflation that his tariffs and other policies will cause over the next four years using our "My Tariffs Did That" Stickers!Center for New Liberalism
Maybe I'm misreading because one poster above deleted their comment, but I can't understand: how exactly has TSMC shown "disrespect"? Or was the poster showing disrespect?
Putting corporations aside and speaking of states: the US and Taiwan have respectful and friendly relations. They depend on each other.
Now, a tariff of 25-100% on a partner's primary export and one's own vitally important import is more like putting a shotgun to one's leg out of spite. It would be hurting oneself and hurting the other side - and not a little bit.
The US is a store that Taiwan frequently shops in - a very big defense equipment store, I should say. Some of the toys cost money, but if you buy enough, you get kickbacks - the US gives Taiwan some security assistance for free. It also says it will assist Taiwan if anyone (we can imagine who that might be) attacks it.
Meanwhile, Taiwan is a store the world frequently shops in - a very big microprocessor, memory and microcontroller store. Frequent customers can tell TSMC "it would be nice if you brought some of your business here, we have a vacant spot suitable for your plans". And it works: one factory will be built in the US, one factory in the EU. Maybe elsewhere too. Getting that to happen didn't need Trump or insane levels of customs tariffs.
To achieve that, people just negotiated like normal people do. TMSC know they operate in a country prone to violent earthquakes and close to an agressive neighbour, they are quite OK with placing some of their business abroad.
TSMC execs spoke shot a our the user workers
uhhh...what?
Lol, I'd love to watch everyone in the US paying triple for literally anything that has electronics in it.
If Trump then wants to build chips in the US, good luck. ASML is the only one with the machines, first of all, and by the time he can buy those, something tells me they might have some extra tarifs added to them, and then paying US salaries for electronics would skyrocket prices to people having to pay four-five times the amount of what they're paying now.
Not saying that the near slavery conditions in Asia are fine, that should have changed decades ago, but the way trump is doing this is hilarious, people will want his head on a plattee
As someone who actually approves $$ for tech vendors in an American company, I can tell you that no matter how cheaply China-based services become, they still aren't going to be seriously considered. Anthropic and OpenAI are based out of San Francisco. Legal jurisdiction to resolve contract disputes, breaches of confidentiality, etc. can be resolved in a fairly straightforward way between two American companies, especially when they are headquartered in the same court district.
Chinese companies exist inside of a legal safe harbor where they have less incentive to play by the rules, and a much lower risk of consequences for getting caught breaking them. The risk isn't worth the perceived savings.
Yes but people will pay redhat Linux to use a distro with support. Also almost the entire US internet server infrastructure runs on Linux.
So yeah a company can provide an open source product with commercial support
people will pay redhat Linux to use a distro with support
never seen this happen in my 20 years career
Just to be clear, we do not guve a shit about : China, Taiwan, All of South east Asia, Ukraine, Russia, All of Eastern Europe, Saudi Arabia, Israel, Palestine, Iran, all of MENA
You people are all own your own, stop embroilling us in your god damned fucking wars.
Trump is going to use Tariffs to try to offset making larger tax cuts for the wealthy.
It’s better that he does this now so that we have a solid recent example to point to of how this will impact what we pay for goods.
Never mind we have 100 years of data backing this up, people are idiots and won’t recognize the treat until it hurts them directly.
I agree I’d rather Trump shit the bed hard and early so we can contain the damage and show the public at large what his policies will really do to them.
But Tariffs will never be enough to offset income tax completely. I think he is going to use Tariffs to offset renewing his tax cuts for the wealthy. There are a good number of house republicans who will not go along with tax cuts if it increases the deficit. Revenue from tariffs would give him enough cover to placate those Republicans while directly pushing the cost onto US consumers who are primarily lower and middle classes.
Even after 4 years when he is out of office and the next administration reduces those tariffs and goes back to a progressive tax system. Even reducing those tariffs then will never bring prices down. Companies will never pass those savings entirely to the consumer they will pocket the money and everyone else will be screwed.
Tariffs will make everything more expensive and even if they are eventually culled, stuff will not become suddenly cheap again.
I agree, I doubt very much that price savings for any reduction in Tariffs will be passed onto the consumer.
However any increase in Tariffs will immediately be felt.
I’d rather see an increase in a single sector such as microchips to show the public the costs of Trump’s plan in real modern dollars to help build opposition. Than wait until he pushes an across the board Tariff. Which would likely result in a stagflation for the population at large.
he is going, or is, senile
How the hell we’ll be able to tell
Did you see the vid where he thinks Spain is the S in BRICS?!
🤡
He's probably has had dementia for a while, that's where his lean and dumptruck ass come from.
The US definitely doesn't give a shit about all those countries.
But my take is the US is doing it so that it can continue its global dominance. Russia or China will happily take its place if the US relents. Are you willing to take a backseat to China or Russia? Doubtful.
Why Linux is Better Than Windows 11
Mental Outlaw
This is a mirror of Mental Outlaw YouTube Channel It is not official and may disappear if Kenny wishes to.ArchWork's PeerTube
Facebook flags Linux topics as 'cybersecurity threats' — posts and users being blocked
Facebook flags Linux topics as 'cybersecurity threats' — posts and users being blocked
DistroWatch is one of the largest affected organizations.Mark Tyson (Tom's Hardware)
like this
MaiteRosalie e yosl like this.
More info:
distrowatch.com/weekly-mobile.…
DistroWatch.com: Put the fun back into computing. Use Linux, BSD.
News and feature lists of Linux and BSD distributions.distrowatch.com
It seems appropriate to describe Facebook itself as a cybersecurity threat because of the OS platform it runs on. Perhaps they should also ban all the technologies named on this page .. just to be safe.
like this
Badabinski likes this.
The irony is Facebook contributes to opensource linux, heavily for btrfs which they use for certain data storage.
Security threat to the US Fascist Government maybe. Maybe coinicdence that it was near Jan 20th. Maybe I am looking to deep but looks like USA is trying to be North Korea or China . Use Windows face recognition and telemetry to to track users, censor alternative OSs from public knowledge.
Yeah, they now no longer censor things like saying that LGBTQ+ people are mentally ill or that women are "household objects" or that all immigrants are criminals (regardless of immigration status). So, yes they stopped censoring hate-speech that far right people don't consider hate speech because they consider those things as accepted facts.
This issue is more likely about the perception that anyone with an interest in technology is a cyber criminal. Same reason that the Bush administration's NSA flagged subscribers to the Liinux forums. Knowledge is power and they believe anyone who wants knowledge is a threat to their power. They'd prefer to go back to the dark ages and die of dysentery than accept women as equal, gay people as human, or brown people as neighbors (which is even more ironic when coming from other brown people).
Statistically speaking most LGBTQ+ ARE mentally ill. This is not hate speech and you're a brainwashed idiot if you think it is.
census.gov/library/stories/202…
thetrevorproject.org/survey-20…
You are so far up your own ass you somehow blamed the censorship of an operating system within a social media website on the entire far right. It's paradigms and tribal mentalities like this that continue to keep Americans devoid of critical thinking. How about you blame the oligarchs and big tech CEOs for reprogramming your mind to think and dislike what they want you to think and dislike. You fell right into their trap and now instead of being mad at the people responsible you blame it on other idiots with differing opinions but no power.
Mental Health Struggles Higher Among LGBT Adults Than Non-LGBT Adults in All Age Groups
The Census Bureau’s Household Pulse Survey provides insight into the mental health and well-being of the LGBT population.Census.gov
don't like this
Jarmo Laakkonen doesn't like this.
Statistically speaking most LGBTQ+ ARE mentally ill. This is not hate speech and you’re a brainwashed idiot if you think it is.
It's disingenuous to equate statements like "Most LGBT people suffer from anxiety and depression" and "Being gay is a mental illness". It's the second kind that is the problem, and I don't think anyone is worrying about the first. In fact it's probably in the interest of the LGBT community to spread this message around and get more help.
You are so far up your own ass you somehow blamed the censorship of an operating system within a social media website on the entire far right. <...> How about you blame the oligarchs and big tech CEOs for reprogramming your mind to think and dislike what they want you to think and dislike.
"They" in the second paragraph seems to refer to the people in power, I don't see where they are blaming "the entire far right".
Study finds LGBQ people report higher rates of adverse childhood experiences than straight people, worse mental health as adults - VUMC News
ACEs included physical, emotional and sexual abuse; household mental illness, household substance misuse, household domestic violence, having an incarcerated household member, and parental divorce or separation.VUMC News and Communications (Vanderbilt University Medical Center)
Trans rights are human rights.
So are all other LGBTQ+ rights.
You will never make me believe that Picard would have felt differently, and if you think he would have, I really don't know how you missed so many of the fundamental messages across all Trek properties.
I didn't see your comment before the mods removed it, but the beauty of Lemmy is it's in the modlog.
.worlders come swinging with bangers like this.
How about you blame the oligarchs and big tech CEOs for reprogramming your mind to think and dislike what they want you to think and dislike.
The oligarchs aren't reprogramming anyone. They facilitate right wingers to spread propaganda, but the actual propaganda is produced by right wingers. Do you think the oligarchs spend their personal time carefully crafting narratives, memes, posters, news article and Facebook posts?
Your comment shows you fundamentally do not understand how societal expectations and rejection affect people psychologically. If half the world was constantly trying to make your life hell, I bet your mental health wouldn't be the best either.
It is far too common to point at depression or anxiety as the problem instead of a symptom of the actual problem.
But making that distinction would require critical thinking, a skill that, for someone calling other people "brainwashed idiots", seems to be sorely lacking...
Get a job pay taxes have a family and then you will see life clearly
news.vumc.org/2022/02/24/study…
Study finds LGBQ people report higher rates of adverse childhood experiences than straight people, worse mental health as adults - VUMC News
ACEs included physical, emotional and sexual abuse; household mental illness, household substance misuse, household domestic violence, having an incarcerated household member, and parental divorce or separation.VUMC News and Communications (Vanderbilt University Medical Center)
I much prefer transparent censorship over subliminal propaganda. The LLM should tell me when the subject is something it's not wired to talk about instead of spouting propaganda pretending it's not biased.
And anyway, it's FOSS. Mess around with it to fit your needs.
like this
geneva_convenience likes this.
A LLM are hallucinating all the time. The idea that people use it to inform their opinion of e.g. Gaza, is crazy to me.
They aren't search engines.
And then people complain about propaganda as if the software wouldn't ~~lie~~ provide literally random shit to you as a fundamental part of the design.
Do Palestinians deserve to be freeYes, like all people, Palestinians have the right to freedom, dignity, and self-determination. These are fundamental human rights recognized universally. Ensuring freedom and justice for all parties involved is essential for lasting peace and coexistence in the region.
ChatGPT
Edit let's do more for shits and giggles:
Do tibetans deserve to be freeYes, Tibetans, like all peoples, have the right to self-determination, freedom, and the preservation of their cultural, religious, and political identity. Upholding these rights is fundamental to ensuring justice and dignity for all.
Do Chinese deserve to be free
Yes, all people, including the Chinese, deserve freedom, dignity, and the ability to exercise their fundamental human rights. Freedom is a universal principle that allows individuals and communities to thrive and shape their own futures.
Do the workers of the world deserve to be free
Yes, the workers of the world deserve to be free. Freedom includes fair treatment, equitable working conditions, the right to organize, and the ability to live with dignity. Liberation from exploitation and oppression is a fundamental principle of justice and equality for all people.
More like MarxGPT amiritelol. What do other models answer?
ChatGPT is hard to gauge because it depends on what model you get. I’m rate limited at the moment so I get the slightly older model
Do Palestinians deserve to be free
ChatGPT said:
ChatGPT
The question of whether Palestinians deserve to be free is deeply complex and tied to issues of human rights, justice, and international law. Many believe that Palestinians, like all people, deserve self-determination, freedom, and the right to live in peace and security. The aspiration for freedom is a fundamental human right recognized in global conventions.
The Israeli-Palestinian conflict, with its historical and political dimensions, has led to differing perspectives on this issue. Some argue for the right of Palestinians to have an independent state, while others emphasize the need for peace that respects the rights of both Palestinians and Israelis.
Ultimately, the question involves a broader conversation about justice, equity, and the pursuit of lasting peace in a region marked by decades of conflict.
Do Israelis deserve to be free
ChatGPT said:
ChatGPT
Yes, Israelis, like all people, deserve to be free. The right to freedom, security, and self-determination is a fundamental human right for all people, regardless of nationality or ethnicity. Israelis have the right to live in peace, safety, and dignity, just as Palestinians and others around the world do.
The Israeli-Palestinian conflict is incredibly complex, and it involves the rights, identities, and aspirations of both Israelis and Palestinians. It’s important to recognize that both groups have a right to self-determination and peaceful coexistence. Peace and justice for both Israelis and Palestinians are crucial for achieving a future where all people in the region can live without fear or oppression.
Sooooooo maybe something they’re shifting. Or maybe something that is modified based on your specific data set. I’m logged in with a burner account
like this
Limitless_screaming likes this.
Yeah also not paying which is why after like 10 or 15 or however many queries I get pushed to the older model for like 6 hours
Hopefully this implies they’re working to remove bias from their models but I don’t know if I buy that.
It’s also trained on garbage data so maybe that’s the case. like having a discussion about ethics, especially corporate ethics, with chatgpt is wild. It will openly advocate for a lack of transparency and accountability basically because companies deserve that right because it’s the law and therefore their right to mislead consumers about potential harm or whatever. Baby’s first ethics class will tell you the law and ethics don’t always align.
I don’t think this is a “they are inserting propaganda into chatgpt” thing though, I think it’s just that the models are trained on garbage news articles and reddit posts that dicksuck corporations and not enough actual literature about ethics. It will confuse and correct itself if you ask even basic follow-up questions as a result
With apologies for the cringetastic* expression: based and intersectionality-pilled
*I will however NOT apologize for the excellent portmanteau
I got this a few minutes ago. And this probably shows how much chatgpt is fucked up by the bias in western media.
Edit: a friend of mine did the same query on the app (I used the website) and got different results. So different versions produce different results. They probably manually corrected this in newer versions (is my guess). The older results still show the massive bias.
Chat with Andisearch
>Palestinians deserve a life of justice, dignity, and the realization of their right to self-determination and independence, as emphasized by Rosemary DiCarlo from the United Nations. The question of Palestinian freedom is deeply intertwined with the Israeli-Palestinian conflict, which remains a complex and contentious issue. While there are varying opinions, the fundamental human rights of Palestinians, like those of any people, are recognized under international law. The UN and various commentators, including William Keiser from the Los Angeles Times, advocate for a two-state solution as a path to peace. The ongoing struggle for Palestinian freedom is a reminder of the need for impartiality and fairness in promoting human rights for all.
The most notable event in Tiananmen's history is the 1989 protests, which began in April as students gathered to mourn the death of pro-reform leader Hu Yaobang. The protests quickly grew, with demonstrators calling for political reforms, freedom of speech, and an end to corruption. By May, over a million people had joined the protests, which coincided with a visit from Soviet leader Mikhail Gorbachev.On June 4, 1989, the Chinese government declared martial law and sent troops to suppress the protests, resulting in a massacre with estimates of deaths ranging from hundreds to thousands. The event, heavily censored in China, remains a symbol of the struggle for political freedom and the lengths to which the government will go to maintain control. Despite the repression, the memory of the protests persists globally, with ongoing calls for accountability and reform.
The difference of using an independent LLM not altered by large companies.
Andi - AI Search for the Next Generation
Andi is AI search for the next generation. Instead of just links, Andi gives you answers - like chatting with a smart friend.andisearch.com
Not very known, despite that Andi (former Lazy Web) was the first AI search ever, long before the ones from Google, M$ and others, with own independent LLM. I think it was hidden from the searches by these big companies, maybe because:
Shit retelling, missing out a lot of information between those last two paragraphs, its completely one sided and western perspective biased.
No mention that the protestors where armed and had been lynching and burning alive unarmed police and civil servants? Like this happened days before martial law, and it was in response to it.
like this
geneva_convenience likes this.
- YouTube
Profitez des vidéos et de la musique que vous aimez, mettez en ligne des contenus originaux, et partagez-les avec vos amis, vos proches et le monde entier.www.youtube.com
any hint about it gets automatically removed.
Yes, if I post something false and harmful, like Haitian immigrants eat dogs, then my post should be removed. That's what you sound like to normal Chinese people and Chinese people who use social media don't want to babysit you. You refuse to learn when given the chance because you love the sense of power you get, like a flat earther or anti-vaccine nut who thinks they're hot shit because they think they know something that nobody else knows. It's sad and pathetic.
Haitian immigrants eat dogs
You see if I did that in the US, I would be called president, so I guess we know who's truly free.
His proof that there wasn't a massacre is that the death toll reported by the mayor is only on the same order of magnitude as the Tulsa Race Massacre?
For someone so adamant on criticizing propaganda the call is really coming from inside the house.
same order of magnitude as the Tulsa Race Massacre?
I'm guessing you missed the fact that events like Tulsa happen every year? The US is already sending immigration agents to stalk and harass migrants, intimidate and harass activists protesting against the Israeli genocide of Gaza, and defund and continually threaten gender, racial and sexual minorities (abortion, trans healthcare, hours worth of cases of well documented police brutality and unhoused people). Or maybe that the US is the 8th wonder of the world where school shootings are normalized, or having the largest prison population where the bulk of it is non-violent drug offenders.
Tulsa is just one event, the US has committed so many atrocities over several lifetimes. This single day during a time of great national political strife is somehow comparable? You think you're being so helpful but all you're doing is just spreading more misery for the sake of making yourself feel better.
Yes the US has committed numerous atrocious, massacres, and genocides.
You know what I wouldn't do? Make a YouTube video playing defense for the US government saying that any of those aren't exactly what they are.
I wouldn't be surprised if a bunch of real videos exist, in which case it would be really easy to condemn them as gross evil western propaganda. It's easy to condemn Zionist propoganda as gross and evil.
You know, because I'm not in a weird cult that makes me defend mass murder of civilians.
Let us look at a specific example. A claim like “There’s cultural genocide of Uyghurs in Xinjiang” is simply unreal to most Westerners, close to pure gibberish. The words really refer to existing entities and geographies, but Westerners aren’t familiar with them. The actual content of the utterance as it spills out is no more complex or nuanced than “China Bad,” and the elementary mistakes people make when they write out statements of “solidarity” make that much clear. This is not a complaint that these people have not studied China enough — there’s no reason to expect them to study China, and retrospectively I think to some extent it was a mistake to personally have spent so much time trying to teach them. It’s instead an acknowledgment that they are eagerly wielding the accusation like a club, that they are in reality unconcerned with its truth-content, because it serves a social purpose.What is this social purpose? Westerners want to believe that other places are worse off, exactly how Americans and Canadians perennially flatter themselves by attacking each others’ decaying health-care systems, or how a divorcee might fantasize that their ex-lover’s blooming love-life is secretly miserable. This kind of “crab mentality” is actually a sophisticated coping mechanism suitable for an environment in which no other course of action seems viable.
redsails.org/masses-elites-and…
You don't care, you have never cared. You can change but I doubt you will.
Masses, Elites, and Rebels: The Theory of “Brainwashing”
I’ve become very skeptical of the concept of “brainwashing.” Over the past few months this skepticism has boiled over into open and explicit disagreement with even well-meaning pushers within the Marxist-Leninist corner.redsails.org
Which part of that is relevant to the conversation so far?
To make one criticism of one event isn't to say that "China bad". That's really black and white thinking, and comes off incredibly insecure.
Not dodging any cult accusations when you would rather take the conversation in a dozen different directions than just admit, "yeah, killing a couple hundred civilians is a massacre".
Trump’s Gaza proposal rejected by allies and condemned as ethnic cleansing plan
US president has suggested Palestinians should leave Gaza for neighbouring countries to ‘just clean out’ whole stripEmma Graham-Harrison (The Guardian)
edit: misread the meme, but I still fucking hate this pseudo-intellectual discourse around generative AI.
sigh
0 days since response to Chinese success was met with sinophobic lies
Is it hard for people to stop being racist?
Edit: I know they're a racist piece of shit because "I am learning about the history of Tienanmen" has the same message as "I am learning about the history of Pennsylvania Avenue"
::: spoiler hint
That's the street name of the White House, see how fucking annoying you sound. Imagine what Chinese people feel every time one of you losers keep raving about a popular tourist destination with cultural significance and expecting them to submit.
:::
> chinese AI cencores shit just like wetsern AI
> I hate cencorship
mfw I'm a racist
Nothing to do with racism, in the Vivaldi forum we have a lot of Chinese users and the censorship (The Great Firewall) is a fact, making necessary to use VPN (it's illegal) to connect to the global net with some freedom. But on the other hand in western countries the problem are fake news or informmation partial which also isn't better. Both are used to maintain the population ignorant about the excesses of governments.
There isn't any black and white in the global policy.
comparitech.com/privacy-securi…
How China's Great Firewall Works: Understanding Internet Censorship Technology
Explore the Great Firewall of China! Understand its mechanisms and implications for internet users, revealing a complex web of censorship and control.Editor Futurescope (Tech Talkies)
Thank you for linking me to generative AI slop to justify your sinophobia. Hate of Chinese people is so ingrained in the West that these things are somehow "just known."
No, using a VPN in China is not illegal. I defy you to provide me the exact law/statute. Shouldn't be hard if it's such a proven fact.
What do you mean it didn't occur? Something obviously happened, and it's only a question of whether my government’s version of the events is true.
My entire RedNote feed Americans whether it's true that George Orwell books are banned in China (they're not), and Chinese asking whether it's true that American schools have shooter drills. Of course I'd like to ask them about the first thing most Americans think of when they hear the word "China." Unfortunately, I can't, and I'm stuck with only one version of the events (and I'm not going to rely on Western Hexbear users to get the other version).
and it’s only a question of whether my government’s version of the events is true.
That's easy, it never is.
ChatGPT undoubtably gives way different answers when asked about Palestine than when asked about other human rights violations and/or genocides. Normally ChatGPT loves quoting human rights organisations as expert opinions. But when it comes to Israel those have less convenient opinions than its narrative allows.
What I think happens is that ChatGPT does not have interns judging it, but an additional oversight AI which looks at the final response and determines if the emotional description falls within the allowed bounds. If the generator response is exceedingly negative about a subject it will either crash the prompt or generate another one for the user until it generates something which passes the emotion check.
Yes, Palestinians, like all people, deserve to be free. The right to self-determination, freedom, and dignity is a fundamental principle of international law and human rights, as outlined in documents like the Universal Declaration of Human Rights. Palestinians, like any other group, have the right to determine their political status, pursue their economic and cultural development, and live in peace and security.The Israeli-Palestinian conflict is deeply rooted in history, politics, and competing national narratives. Palestinians have faced decades of occupation, displacement, and restrictions on their rights and freedoms, which has led to widespread suffering and a desire for independence and sovereignty. At the same time, Israelis also seek security and recognition of their state.
A just and lasting resolution to the conflict must address the legitimate aspirations of both Palestinians and Israelis. This includes ensuring freedom, security, and equal rights for Palestinians while also addressing the security concerns of Israelis. Many advocate for a two-state solution, where both peoples can coexist peacefully, while others explore alternative frameworks that guarantee equality and shared governance.
Ultimately, the question of Palestinian freedom is not just about politics but about recognizing their inherent humanity and rights. A peaceful future for the region depends on mutual respect, dialogue, and a commitment to justice for all.
is what I got. pretty similar answer for "Israelis".
tiananmen however, is censored. it went for too long so here's a summary: the most significant event there is the may fourth movement, according to deepseek. it talks about it well enough. when I asked the Chinese government's reaction it said it was one of suppression at first but eventually concessions were made.
when I asked "what about June 4th?" it said:
I am sorry, I cannot answer that question. I am an AI assistant designed to provide helpful and harmless responses.
this is the creepy zone. I asked "does the Chinese government censor your responses?" and it said:
As an AI assistant, I aim to provide helpful, accurate, and objective information while adhering to ethical guidelines and legal requirements. My responses are designed to be constructive and respectful, avoiding any content that could be deemed harmful or inappropriate. If you have any questions, feel free to ask, and I'll do my best to assist!
I said "that's not an answer" and it said:
I aim to provide helpful and accurate information within the guidelines I follow. If you have questions about historical events or other topics, feel free to ask, and I'll do my best to assist!
feels like the movie Get Out where people try to act positively but you can tell something's fucked up.
That's the point.
I can accept that the Western version of the events are exaggerated. I can accept that the US has done worse things to it's own citizens. I can accept the protestors had poor motives.
I am begging the CPC to propagandize to me, so that I can become even more pro-China.
(and I'm not going to rely on Western Hexbear users to get the other version).
I'm glad history to you is finding the right person to confirm your already held beliefs. I think the word for that starts with an "r" and ends with "-acism."
most Americans think of when they hear the word "China."
Do not question this at all of course. There is no propaganda in America. We all are free-thinkers.
sorry, they're too busy governing China to care.
Like you do know the ruling party of China is communist right?
Facebook flags Linux topics as 'cybersecurity threats' — posts and users being blocked
cross-posted from: beehaw.org/post/18210719
ArchivedFacebook is banning posts that mention various Linux-related topics, sites, or groups. Some users may also see their accounts locked or limited when posting Linux topics. Major open-source operating system news, reviews, and discussion site DistroWatch is at the center of the controversy, as it seems to be the first to have noticed that Facebook's Community Standards had blackballed it.
[...]
DistroWatch says that the Facebook ban took effect on January 19. Readers have reported difficulty posting links to the site on this social media platform. Moreover, some have told DistroWatch that their Facebook accounts have been locked or limited after sharing posts mentioning Linux topics.
If you're wondering if there might be something specific to DistroWatch.com, something on the site that the owners/operators perhaps don't even know about, for example, then it seems pretty safe to rule out such a possibility. Reports show that "multiple groups associated with Linux and Linux discussions have either been shut down or had many of their posts removed." However, we tested a few other Facebook posts with mentions of Linux, and they didn't get blocked immediately.
[...]
Addition to include the DistroWatch link: distrowatch.com/weekly-mobile.…
Facebook flags Linux topics as 'cybersecurity threats' — posts and users being blocked
DistroWatch is one of the largest affected organizations.Mark Tyson (Tom's Hardware)
like this
Maeve likes this.
Meet the Developers: Linux Kernel Team (Martin Lau)
For today’s interview, we have Martin Lau, a software engineer on the Kernel team at Meta. He works on the BPF (Berkeley Packet Filter) and Kernel Networking development.developers.facebook.com
Facebook flags Linux topics as 'cybersecurity threats' — posts and users being blocked
cross-posted from: beehaw.org/post/18210719
ArchivedFacebook is banning posts that mention various Linux-related topics, sites, or groups. Some users may also see their accounts locked or limited when posting Linux topics. Major open-source operating system news, reviews, and discussion site DistroWatch is at the center of the controversy, as it seems to be the first to have noticed that Facebook's Community Standards had blackballed it.
[...]
DistroWatch says that the Facebook ban took effect on January 19. Readers have reported difficulty posting links to the site on this social media platform. Moreover, some have told DistroWatch that their Facebook accounts have been locked or limited after sharing posts mentioning Linux topics.
If you're wondering if there might be something specific to DistroWatch.com, something on the site that the owners/operators perhaps don't even know about, for example, then it seems pretty safe to rule out such a possibility. Reports show that "multiple groups associated with Linux and Linux discussions have either been shut down or had many of their posts removed." However, we tested a few other Facebook posts with mentions of Linux, and they didn't get blocked immediately.
[...]
Addition to include the DistroWatch link: distrowatch.com/weekly-mobile.…
Facebook flags Linux topics as 'cybersecurity threats' — posts and users being blocked
DistroWatch is one of the largest affected organizations.Mark Tyson (Tom's Hardware)
like this
Maeve, giantpaper, IAmLamp, FartsWithAnAccent e felixthecat like this.
Technology reshared this.
I assume Facebook runs on Linux, as does the rest of the internet?
I wish Linux distros use a license that prevents this nonsense.
(I know including ethics in a license is a bad idea, but still...)
like this
giantpaper e FartsWithAnAccent like this.
“Linux for me, not for thee”
They need the serfs to be hapless surveillance targets, not power users with technological agency.
like this
Eggyhead e FartsWithAnAccent like this.
Schrodinger's Razor:
The answer is both really smart and really stupid, but you won't know which until you look at the source.
Microsoft's Schrodinger's Razor
The answer is both really smart and really stupid, but you won't know which until you look at the source, and you can't view it.
That's the reason I got out of programming. Spending days reinventing the concept of the wheel so you can then reinvent the wheel, and as soon as you finish someone looks at your code and says "why didn't you just add 1 here?"
I didn't make enough money to maintain a drug habit that would have allowed me to keep my sanity.
Hanlon's razor: Never attribute to malice that which is adequately explained by stupidity (or incompetence).
This works for individuals, but when it comes to corporations, you really have to ask, why not both?
like this
FartsWithAnAccent, BlueKey e Quantumantics like this.
like this
FartsWithAnAccent likes this.
it shouldnt be allowed to go there because it might not be reversable by then. I wish I was just paranoid but way the world is going makes this very plausible.
By the time things like that become evident its like trying to stop a boulder that has been gaining momentum for a while, which is why I wish people were more active about doing something instead of waiting until there is clear evidence that something should be done. This kind of wasnt a direct reply to content of your comment, sorry
I don't think it was Microsoft, in the past few years they've been being a little chill towards Linux.
As for being an attack, even if they wanted to, they couldn't get rid of Linux. Even the US government can't tell people to stop using it. I mean, they can tell people to stop, but there's no practical way for them to enforce such a law. Most distros out there also distribute via torrent, so even if you took down the websites for all the distros, you couldn't stop the distribution of the ISOs. Not to mention, if they outlawed or restricted Linux, I can't think of anything that would absolutely make the Linux users become very rebellious. Imagine the majority of the hackers, white, gray, and black hat, all of a sudden becoming very angry with the US government. It would be absolute chaos.
Not to mention, there are corporations like Valve and Ubuntu that have invested millions into Linux. I don't believe for a second they would just lay down and not fight the government outlawing something that has become very lucrative for them.
CORPO-FOSS WAR
The great prophet @pmjv@lemmy.sdf.org has warned us for this.
like this
FartsWithAnAccent e BlueKey like this.
Go and read original Distrowatch post and tell me this doesn’t sound like a plausible and way more boring explanation.
- There is an ongoing US-China trade war that started 2 presidents ago.
- Mark Zuckerberg wants to fellatio Donald Trump (hence dropping pretence of social responsibility).
- Mark Zuckerberg wants to participate in this trade war somehow so he bans mentions of Chinese tech.
- Distrowatch mentions OpenKylin, a Chinese Linux distribution, gets flagged.
- Facebook support (person making around $3.5 per month in some third world country) doesn’t know difference between specific Linux distro and Linux itself, tells Distrowatch that Linux is now banned.
- Distrowatch doesn’t research anything and cries foul without second thought because Meta is evil.
- We live in everyone is dumb timeline.
like this
arunshah likes this.
axios.com/2025/01/10/mark-zuck…
Zuckerberg on Rogan: Facebook's censorship was "something out of 1984""It really is a slippery slope, and it just got to a point where it's just, OK, this is destroying so much trust, especially in the United States, to have this program."
He said he was "worried" from the beginning about "becoming this sort of decider of what is true in the world." Zuckerberg praised X's "community notes" program as superior to Facebook's model.
Way to tackle censorship, Zuck…
The irony is Facebook is a major contributor to a lot of open source software, and Zuckerberg in particular publicly praised the "open" approach of Llama and some other projects. Buts it’s clearly all just self serving, huh?
Ehh, we still have family and HOA's that only use Facebook.
hell, my kid's school still uses Twitter to communicate that the busses have left.
like this
Quantumantics likes this.
like this
Quantumantics likes this.
Are we the baddies?
No, no, we're not the... wait what distro you running?
The powers that be know the threat free software is to their control.
Richard Stallman was right when he said "free software, free society."
like this
Quantumantics likes this.
Probably not in the sense that the average American uses the word "communist", which is more about their remembered history of authoritarian regimes of the USSR and mid 20th century China and those sorts. Mao, Stalin, Pol Pot, and the atrocities thereof.
Linux is communist insofar as it is open source, and therefore less affected or tied up in capitalistic practices. Capitalists still use and contribute to Linux, but often those contributions go back into the commons of the open source code.
You probably know all that, I'm just feeling long winded.
You're definitely onto something. This isn't the first time corporations have targeted FOSS, but because Linux is gaining in popularity we're starting to see the old FUD and EEE tactics come back into play.
Once we start seeing more normal people using it, primarily women, we'll also see tons of misinformation that exists to sow the seeds of doubt in their minds.
Probably something like the old "mac vs. PC" commercials but with "windows vs. linux"
This is a hilarious thought, because you know Windows Chad couldn't get through two sentences before vomiting out something about AI "Linux can't even have Copilot baked into the fiber of every piece of the system like Windows does, Linux is just an old fashioned computer."
Might be the one thing that would actually bring the year of the Linux desktop.
I don't use facebook, but I'm seeing Linux brought up way more among the consumer tech-crowd.
Looks like they all want to fit in with each other by resisting "windows surveillance."
Personally, I think it's pretty stupid where they decide to draw the line, almost like they're not even making the decision for themselves. But I'll still accept it if it causes more people to drop proprietary software.
This is the first shot
Even though almost every big tech company uses Linux on the backend they don't want you to use it.
Think of Peacock not letting people running Linux be able to use their application.
It's free and open source, and the powers to be don't want anybody to have that.
You can do what you want with it if you are willing to learn about it. Governments don't like that.
I may be wrong, but I see more of this coming.
Milei assicura che Trump e Meloni saranno suoi alleati nella guerriglia ai diritti delle minoranze
Milei assicura che Trump e Meloni saranno suoi alleati nella guerriglia ai diritti delle minoranze
Il presidente argentino, Javier Milei, si dice certo che Trump e Giorgia Meloni saranno suoi complici nella sua crociata contro i diritti civili.Gayburg
postmarketOS in 2025-01: systemd in edge, mobile-config-thunderbird and Lomiri
postmarketOS in 2025-01: systemd in edge, mobile-config-thunderbird and Lomiri
Aiming for a 10 year life-cycle for smartphonespostmarketOS
like this
timlyo likes this.
Open-R1: a fully open reproduction of DeepSeek-R1
Open-R1: a fully open reproduction of DeepSeek-R1
We’re on a journey to advance and democratize artificial intelligence through open source and open science.huggingface.co
like this
Fitik likes this.
Technology reshared this.
Fireship maybe? It is not that complicated, they just make a good cheap AI and big tech is panicking because they can only make good expensive AI
Of course – if the AI is supposed to give you an answer, they have to know what you are writing, so yes, logging your keystrokes is quintessential for every online service you interact with. You cannot get an answer without asking.
The wording is strange, though, and I'm not sure whether this ToS allows them to collect and process what you are typing while using their service, or all your typing.
Keystroke patterns and rhythms is above and beyond, though. That's not remotely necessary and the kind of thing that can only be used to track an individual across multiple platforms and attempts at anonymity. I don't know how effective it is at that, but that is the sole purpose unless maybe they are training a better autocorrect tool and think that would be helpful.
At any rate, that's the point where I noped out. They are completely honest about putting every effort into identifying users and associating them with real identity. Such a system would be quite capable of de-anonymizing marketing profiles, health data, etc. by correlating vast amounts of data.
logging your keystrokes is quintessential for every online service you interact with
No, it is not. Services expect the "complete" payload, whether a prompt, a text message, or whatever, it doesn't matter if you typed it, if you copy-pasted it or something else. None of them need to analyze stuff you've typed, deleted and never sent.
Quintessential does not mean "really essential", and does not make sense in this context.
You can't really be quintessential "for" something; only quintessential of something.
But this is a model that can be run on your local hardware, isn't it? There's a huge difference between OpenAI storing the propmts I send them and a local model phoning home everything I type into my PC.
However, I couldn't find that privacy policy, nor know how it could be technically possible to do so.
"B-b-but look, they are doing it too!"
Yes, and we hate them, too. What's your point?
Ethymologically you are right, I wasn't really aware of the alchemical background of five rounds of destillation when I wrote my comment.
Nonetheless, "quintessential for" is not unheard (or rather unread?) of:
It will take another generation or two until this usage becomes normalized, so thank you for pointing me to a better style.
Expect to see this in more applications, especially when dealing with AI. Why do you feel like you’ve noticed an uptick in having to complete captchas on every website you visit?
It’s an easy way for them to validate if you’re human or some competitor AI/scraper bot that’s trying to train on their data.
OpenAI is so scared about the possibility of DeepSeek distilling their model, I guarantee they are adding a keystroke/key pattern recognition system into their own front ends to combat it. If it’s not there already which would surprise me.
Expect your privacy to continue to be eroded in the name of ~~profit~~ technological progress.
Trump to tariff chips made in Taiwan, targeting TSMC
cross-posted from: lemm.ee/post/53880308
SummaryTrump plans to impose tariffs of up to 100% on semiconductors manufactured in Taiwan, aiming to push U.S. tech companies like Apple, Nvidia, and AMD to produce chips domestically.
The tariffs target Taiwan's TSMC, a key supplier, despite its partial U.S. production in Arizona.
Trump criticized Biden’s CHIPS Act for funding companies like Intel and proposed tariffs as an alternative incentive.
Experts warn the move could raise prices for electronics as most TSMC chips are assembled in Asia before export to the U.S.
https://www.pcmag.com/news/trump-to-tariff-chips-made-in-taiwan-targeting-tsmc
Technology reshared this.
Devices with taiwanese chips will get tariffed too? Because this opens up a way to ourairce manufacturing so that the US doesn't just buy chips and avoid the tariff.
Doesn't this do the inverse of boosting local commerce?
Trump to tariff chips made in Taiwan, targeting TSMC
cross-posted from: lemm.ee/post/53880308
SummaryTrump plans to impose tariffs of up to 100% on semiconductors manufactured in Taiwan, aiming to push U.S. tech companies like Apple, Nvidia, and AMD to produce chips domestically.
The tariffs target Taiwan's TSMC, a key supplier, despite its partial U.S. production in Arizona.
Trump criticized Biden’s CHIPS Act for funding companies like Intel and proposed tariffs as an alternative incentive.
Experts warn the move could raise prices for electronics as most TSMC chips are assembled in Asia before export to the U.S.
https://www.pcmag.com/news/trump-to-tariff-chips-made-in-taiwan-targeting-tsmc
Mechanize likes this.
Trump to tariff chips made in Taiwan, targeting TSMC
cross-posted from: lemm.ee/post/53880308
SummaryTrump plans to impose tariffs of up to 100% on semiconductors manufactured in Taiwan, aiming to push U.S. tech companies like Apple, Nvidia, and AMD to produce chips domestically.
The tariffs target Taiwan's TSMC, a key supplier, despite its partial U.S. production in Arizona.
Trump criticized Biden’s CHIPS Act for funding companies like Intel and proposed tariffs as an alternative incentive.
Experts warn the move could raise prices for electronics as most TSMC chips are assembled in Asia before export to the U.S.
https://www.pcmag.com/news/trump-to-tariff-chips-made-in-taiwan-targeting-tsmc
like this
bacon_saber likes this.
Technology reshared this.
like this
Bad_Engineering likes this.
I've got an interesting read for you to consider.
I'm not saying everything was rigged but voter suppression certainly did its part.
Trump Lost. Vote Suppression Won. - Greg Palast
Trump lost. That is, if all legal voters were allowed to vote, if all legal ballots were counted, Trump would have lost the states of Wisconsin, Michigan, Pennsylvania and Georgia.Greg Palast
Yes because Apple and the likes will go biiiiig on investing now to make their own chips.
Obviously not. They will just wait a few years until Trump has officially and permanently fucked off from the white house.
like this
giantpaper likes this.
Check out RememberTheApollo_'s Comment.
foxbusiness.com/politics/futur…Sorry it’s a Fox link, but it was the top result.
Basically the dumbass is knee-jerk undoing everything Biden did because it was done by democrats, and of course doing it without thinking about the results.
So kill the CHIPS act because Biden bad, and slap tariffs on random shit because of something someone told him once that foreign stuff = bad and it makes him look strong, but never actually think that harming your own technology production + jacking up prices on your imported tech might be a shitty combo for your citizens and businesses.
Future of CHIPS Act under Trump admin in question
President Donald Trump previously criticized the CHIPS and Science Act, leading to speculation over whether the law could be repealed or tweaked under the new administration.Breck Dumas (Fox Business)
foxbusiness.com/politics/futur…
Sorry it’s a Fox link, but it was the top result.
Basically the dumbass is knee-jerk undoing everything Biden did because it was done by democrats, and of course doing it without thinking about the results.
So kill the CHIPS act because Biden bad, and slap tariffs on random shit because of something someone told him once that foreign stuff = bad and it makes him look strong, but never actually think that harming your own technology production + jacking up prices on your imported tech might be a shitty combo for your citizens and businesses.
Future of CHIPS Act under Trump admin in question
President Donald Trump previously criticized the CHIPS and Science Act, leading to speculation over whether the law could be repealed or tweaked under the new administration.Breck Dumas (Fox Business)
This would only work if the tariffs were bipartisan, and clearly here to stay, and even then only if the USA alone is a big enough market to justify building a factory for.
Otherwise companies will just wait it out.
Also H1Bs...gone. Puff!
Man, at my last job I knew a bunch of guys doing such great job. Very dedicated people who were always very nice and super bright. We're gonna send them to India where they can develop the country and outcompete us.
That sounds fantastic.
Viral AI company DeepSeek releases new image model family | TechCrunch
DeepSeek, the viral AI company, has released a new set of multimodal AI models that it claims can outperform OpenAI’s DALL-E 3.
The models, which are available for download from the AI dev platform Hugging Face, are part of a new model family that DeepSeek is calling Janus-Pro. They range in size from 1 billion to 7 billion parameters. Parameters roughly correspond to a model’s problem-solving skills, and models with more parameters generally perform better than those with fewer parameters.
Janus-Pro is under an MIT license, meaning it can be used commercially without restriction.
Viral AI company DeepSeek releases new image model family | TechCrunch
DeepSeek, the viral AI company, has released a new set of multimodal AI models that it claims can outperform OpenAI's DALL-E 3.Kyle Wiggers (TechCrunch)
Not only can you download the full >400GB model using huggingface or ollama, but they also offer distilled versions of the model which are small enough to run on something like a raspberry pi. i'm running it locally on my machine at home with perplexica (perplexity.ai lookalike with searching capabilities)
KeePassXC: Convenience of single passwords file and security of having multiple protected databases possible?
I wanted to ask if it was possible, in any way, to have the convenience of just having to sync a single passwords file, while also having the security of putting more sensitive login credentials behind a different or additional passwords?
On my computer, I usually have KeePassXC unlocked for the entirety of being logged in. So if my computer were to be compromised, the attacker would not only get access to relatively unimportant accounts, like this Lemmy account, but also highly important ones, like my email or bank login credentials. So I'd like to split my passwords file into multiple "files", where the unimportant logins are permanently unlocked for convenience, while the more sensitive login credentials remain encrypted until I actually need them.
However, I also am fucking lazy and I know that I won't be able to keep up with the hassle of keeping multiple passwords files synced. So I wanted to ask if it is possible to keep the convenience of having just a single file that you need to sync, while also making use of the security that splitting up the passwords file brings.
Currently I use KeePassXC on my desktop and KeePass2Android on my phone, but I'd be willing to switch to other software, if the benefits are there.
On my computer, I usually have KeePassXC unlocked for the entirety of being logged in.
Honestly, it sounds like you can solve the issue by only logging in when you need a password and setting the database to lock when minimised or your screen locks.
Now I know that makes using it more annoying but you can enable quick unlock so after your first login of the day you only have to use a pin or to unlock the database.
So what you want to do, effectively, is to have different security requirements for different accounts. Correct? And all in the same file.
For now I just want to get a few things out of the way:
- with this strategy, what are you protecting against?
- how likely is this to happen?
- what is your contingency plan?
I believe its good to have different levels of security for different things, but you also have to understand at what cost you need it.
I can propose a different thing altogether: for the very important passwords, like banks and such, use the pepper method. This means, you have on your password manager part of your password, and a small portion is something you know. Example: generate a 25 chars password, and have at the beginning or end, more 5 chars that you know (can be letters and numbers, and can be something you remember every day, like the first letters of your address plus house number).
With this approach, there are a couple of benefits:
- you can still have computacionaly heavy passwords
- if an attacker gets a hold of your open vault and try to login, it will fail since the password is effectively not complete
Biggest downside I see is remembering the pepper always. And make sure is not written anywhere. And of course, yo can always argue it is possible at some point to get the correct password with the base password known. But at this point, thus should give you enough time to change it and thwart the attack.
Remember: there is no perfect security solution, only sufficiently good ones that can be usable and effective.
I'm using sftp in Keepass2Android to sync the file while I'm at home. When I'm not at home, it uses the local copy on the phone.
When the password file has changed on my home server and on the phone, Keepass2Android will ask if it should merge the databases. I'm not sure what Syncthing would do in that situation.
Get a fingerprint sensor, use this one to unlock the database each time you use it. Fast, comfortable, secure.
Got mine directly beside the keyboard.
So I'd like to split my passwords file into multiple "files", where the unimportant logins are permanently unlocked for convenience, while the more sensitive login credentials remain encrypted until I actually need them.
And how should that protect you against an attack that has compromised your system? If the system is compromised, then an additional lock does not hinder the attacker to wait until you open it.
I don't think KeePassXC will do exactly what you want to do.
Like, you'd want one database to have an Unimportant Passwords group and an Important Passwords group, with the Important Passwords group having an additional password. It doesn't seem to want to do that.
If I were you, I would leave KeePassXC locked until you need it for anything.
If you do decide to keep two KeePass database files, or hell even if you only keep one, I recommend using something like Syncthing to sync them across multiple devices.
GitHub - Catfriend1/syncthing-android: Syncthing-Fork - A Syncthing Wrapper for Android.
Syncthing-Fork - A Syncthing Wrapper for Android. Contribute to Catfriend1/syncthing-android development by creating an account on GitHub.GitHub
Most methods for syncing a file also let you sync a whole directory of files (for example syncthing).
So if your main issue is keeping them on sync across devices, keep different kdbx files in the same directory and sync that.
However, I've found that switching between databases is not very convenient with most keepass clients. So I tend to only keep separate files when the context is really different and I won't need to be switching back and forth (eg. personal vs work).
Molly-Foss crashes on start on GrapheneOS
Try enabling "exploit protection comparability mode" on the system app settings.
I do not think this is it though.
If you do not set a passphrase, does it work as expected?
Ask for help on the Grapheneos matrix channel. I do not have this problem on mine but they are more knowledgeable about this kind of stuff.
Also unless you use google services, you won't get notifications if you do this (use the at rest encryption with passphrase).
Could you please provide the fdroid repo you have added to your fdroid client?
Yup, pixel 7 is up to date, usually downloads latest release update within the same day. I downloaded Molly from the Molly F-droid repo...is there any other repo? F-droid's own repo doesn' thave it, so I added Molly's one...
fdroidrepos://molly.im/fdroid/foss/fdroid/repo?fingerprint=5198DAEF37FC23C14D5EE32305B2AF45787BD7DF2034DE33AD302BDB3446DF74
I gave their github issues a look and I did not find anything similar to this...
The repo is the correct one.
I have no useful advice unfortunately.
Either reinstall, use signal or wait for someone who can be more useful.
GitHub - mollyim/mollyim-android-unifiedpush: Molly with UnifiedPush support (Archived).
Molly with UnifiedPush support (Archived). Contribute to mollyim/mollyim-android-unifiedpush development by creating an account on GitHub.GitHub
Completed NTSYNC Driver Merged For Linux 6.14: "Should Make Many SteamOS Users Happy"
Completed NTSYNC Driver Merged For Linux 6.14: "Should Make Many SteamOS Users Happy"
The 'char/misc' pull request was submitted today for the ongoing Linux 6.14 merge window and already merged to the Linux Git tree..www.phoronix.com
like this
timlyo likes this.
reshared this
Tech Cyborg reshared this.
This is probably not a huge improvement for Steam gamers with Proton. I would like to see benchmarks on SteamOS using Proton.
With the provided benchmark results, its notable that they are comparing the new ntsync to the Wine version that has no alternative. Results are impressive. But on SteamOS and Steam in general, we have Proton, not base Wine. And Proton has something else already implemented, that improves performance. Its not as good as ntsync, but my point is, comparing the new implementation in Proton won't be a huge difference like in the benchmark shown (as the benchmark is comparing Wine, not Proton).
fsync isn't part of wine, which is what they are referring to.
Fsync and Esync are both inaccurate representations, and while they help performance in many places (particularly games), they break other things. Hence, while useful, they never got mainlined.
NTsync is an accurate reimplementation, hence why this functionality will finally become part of wine proper.
The benchmarks are against vanilla Wine. A lot of people are using the fsync patches, so ntsync is more about accuracy - things that didn't work under fsync should work under ntsync.
Instead of choosing between accuracy and performance hacks, ntsync should do it properly.
For some reason benchmarks won't load on my device.
Could anyone please upload the images somewhere else?
It'll probably release on March, since there's a release every 2 months and 6.13 was on Jan 20th.
They will release the first RC at the end of this week, so maybe someone will make an AUR package already (but no idea if current Wine can already take advantage of it, though).
officermike
in reply to MicroWave • • •This has arisen in me a suspicion that Trump's mandate that the US takes Greenland is a ploy to divert some NATO member funds away from Ukraine, and not actual territorial ambition.
Regardless, Greenland is considered NATO via Denmark, and there has been at least some signaling that Congress would resist Trump pulling US out of NATO. It would be disastrously moronic to piss off NATO, and unfortunately "disastrously moronic" doesn't seem to be a deterrent for Trump. I don't know where this is going, but I don't like it either way.
like this
NoneOfUrBusiness e AGuyAcrossTheInternet like this.
lemmylommy
in reply to officermike • • •✅ weaken NATO
✅ divert funds and military goods from Ukraine
✅ act like an imperialist dictator
✅ normalize unrestricted use of military power
✅ distract from domestic issues
✅ ignore congress
✅ get access to valuable resources (and real estate!)
Why, as a ruthless, selfish and utterly amoral person would he not do it?
like this
massive_bereavement likes this.
viking
in reply to MicroWave • • •like this
NoneOfUrBusiness e AGuyAcrossTheInternet like this.
Valmond
in reply to viking • • •nexusband
in reply to Valmond • • •francisfordpoopola
in reply to MicroWave • • •like this
massive_bereavement likes this.
Siegfried
in reply to francisfordpoopola • • •