Why LLMs can't really build software
Why LLMs Can't Really Build Software - Zed Blog
From the Zed Blog: Writing code is only one part of effective software engineering.zed.dev
like this
Where did the downvotes go?
I started seeing a weird trend on Lemmy that I cannot understand.
Weeks ago, posts used to have downvotes and upvotes in the semi-rational range you would expect.
Out of nowhere, it seems like almost all the posts I see now have zero downvotes with some exceptions.
What is happening here exactly?
Where did the downvotes go?
I started seeing a weird trend on Lemmy that I cannot understand.
Weeks ago, posts used to have downvotes and upvotes in the semi-rational range you would expect.
Out of nowhere, it seems like almost all the posts I see now have zero downvotes with some exceptions.
What is happening here exactly?
☆ Yσɠƚԋσʂ ☆ doesn't like this.
Texas Senate Passes Map After 2 Democrats Fail to Join House Member Walkout
The gerrymander would benefit the GOP and dilute Black and Brown voters’ power. The House may now decide its fate.
Where did the downvotes go?
I started seeing a weird trend on Lemmy that I cannot understand.
Weeks ago, posts used to have downvotes and upvotes in the semi-rational range you would expect.
Out of nowhere, it seems like almost all the posts I see now have zero downvotes with some exceptions.
What is happening here exactly?
China to launch new type of visa for young science, technology professionals
China Focus: China to launch new type of visa for young science, technology professionals
China Focus: China to launch new type of visa for young science, technology professionals-english.news.cn
Footage Shows Trump’s Pick for Labor Statistics Head in January 6 Mob
The White House claimed the Heritage Foundation economist was just a “bystander” in town for a meeting.
Masked ICE Agents Kidnap Teenager Who Was Walking His Dog
Benjamin Marcelo Guerrero Cruz had just turned 18 and was about to start his senior year.
adhocfungus likes this.
Beyond Dobbs: How Abortion Bans Enforce State-Sanctioned Violence
Journalist Kylie Cheung breaks down how post-Dobbs restrictions “aren’t unintended consequences” on the Intercept Briefing podcast.
Grenada Drops Oath of Allegiance to the British Crown, moves closer to republicanism
Grenada Drops Royal Oath in Historic Shift - The Caribbean Camera
Grenada ends the royal oath of allegiance, requiring public officials to pledge loyalty solely to the nation, sparking renewed debate on constitutional reform and republicanism.The Caribbean Camera Inc. (The Caribbean Camera)
Grenada Drops Oath of Allegiance to the British Crown, moves closer to republicanism
Grenada Drops Royal Oath in Historic Shift - The Caribbean Camera
Grenada ends the royal oath of allegiance, requiring public officials to pledge loyalty solely to the nation, sparking renewed debate on constitutional reform and republicanism.The Caribbean Camera Inc. (The Caribbean Camera)
like this
the primary school used to teach that the usa never lost a war because things like grenada and vietnam didn't have a declaration of war.
i wonder if they still teach it that way.
@ireallyhateyou is an amazing source. Both him and @ytirawi sources I'll believe anything from unless disproven. In this case he even provides a picture of the sniper the soldier used which matches the tiger stripes pattern in the picture.
Why the Heck Was Charlie Kirk Booked as a Guest on CNBC’s Squawk Box?
Turning Point USA founder Charlie Kirk was a guest on CNBC’s Squawk Box Wednesday, an inexplicable and indefensible booking even in light of networks wanting to reach a politically diverse audience.
Other media outlets, including CNN, The Washington Post, and the Los Angeles Times, have struggled with covering the Trump administration. But is there really no one else willing to go on television and discuss conservative views, GOP policies, and the Trump administration’s agenda from a center-right perspective besides Charlie Kirk?
During Kirk’s seventeen minutes on Squawk Box, co-hosts Joe Kernen and Andrew Ross Sorkin rolled through a number of timely and topically relevant questions, but the 31-year-old was unable to offer much more than diluted White House talking points and declarations of MAGA fealty.
Kernen commented that Kirk was something of a “mind reader of the president” and asked him “how should the business community think about what he says.”
Kirk’s answer was that it was “very simple” and “not complicated,” that Trump “wants what’s best for America, it’s not ideological and he wants what’s best both for capital and labor and he wants the market to succeed and wants wages to go up,” before prattling on about Trump’s “victories” with the trade deals.
Why the Heck Was Charlie Kirk Booked as a Guest on CNBC’s Squawk Box?
Turning Points USA founder Charlie Kirk was a guest on CNBC's Squawk Box Wednesday, an inexplicable and indefensible booking even in light of networks wanting to reach a politically diverse audience.Sarah Rumpf (Mediaite)
LibreOffice is right about Microsoft, and it matters more than you think.
LibreOffice is right about Microsoft, and it matters more than you think
Are we unwittingly playing into Microsoft's hands? LibreOffice thinks so.Simon Batt (XDA)
like this
UK government to use AI to predict crime locations by 2030
The UK government has launched a challenge for the development of a map that uses AI to predict where crimes will occur. It'll couple this with 13,000 more law enforcers.
https://www.neowin.net/news/uk-government-to-use-ai-to-predict-crime-locations-by-2030/
Australian lawyer apologizes for AI-generated errors in murder case
A senior lawyer in Australia has apologized to a judge for using AI-generated fake quotes and non-existent case judgments in a murder case
Can’t pay, won’t pay: impoverished streaming services are driving viewers back to piracy
Can’t pay, won’t pay: impoverished streaming services are driving viewers back to piracy
As subscription costs rise and choice diminishes on legal sites, film and TV fans are turning to VPNs and illicit streamers, with Sweden – home of both Spotify and The Pirate Bay – leading the wayGuardian staff reporter (The Guardian)
like this
It's not just a pricing issue. It's an ownership issue.
Too many of the things we buy are not ours.
Yesterday I saw the article about VW cars which need a subscription to use the built-in capabilities. The car you bought doesn't belong to you.
Should UK.gov save money by looking for open source alternatives to Microsoft? You decide
Register debate series: As £9 billion MoU sparks debate about value for money, it's time to have your say
Suspected French spy arrested in alleged Mali coup plot
The French national is accused of working "on behalf of the French intelligence service" in Mali.
Archived version: archive.is/newest/bbc.com/news…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
A mind–reading brain implant that comes with password protection
- Attempted, inner, and perceived speech have a shared representation in motor cortex
- An inner-speech brain-computer interface (BCI) decodes general sentences with improved user experience
- Aspects of private inner speech can be decoded during cognitive tasks like counting
- High-fidelity solutions can prevent a speech brain-computer interface (BCI) from decoding private inner speech
Speech brain-computer interfaces (BCIs) show promise in restoring communication to people with paralysis but have also prompted discussions regarding their potential to decode private inner speech. Separately, inner speech may be a way to bypass the current approach of requiring speech brain-computer interface (BCI) users to physically attempt speech, which is fatiguing and can slow communication. Using multi-unit recordings from four participants, we found that inner speech is robustly represented in the motor cortex and that imagined sentences can be decoded in real time. The representation of inner speech was highly correlated with attempted speech, though we also identified a neural “motor-intent” dimension that differentiates the two. We investigated the possibility of decoding private inner speech and found that some aspects of free-form inner speech could be decoded during sequence recall and counting tasks. Finally, we demonstrate high-fidelity strategies that prevent speech brain-computer interfaces (BCIs) from unintentionally decoding private inner speech.
Thai princess being treated for severe infection, royal bureau says
She was seen by some analysts as a potential heir to the throne. Read more at straitstimes.com. Read more at straitstimes.com.
Archived version: archive.is/newest/straitstimes…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
Kuwait decision to ban entry of Israelis receives wide public praise
Kuwait’s recent decision to allow all nationalities to enter its territory, while excluding Israeli nationals, has received wide praise and positive reactions at both official and public levels, with discussions also spreading across social media platforms.
Archived version: archive.is/newest/middleeastmo…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
adhocfungus likes this.
One could argue that it is, personally I see it as discrimination against the state and not the people. People are just affected by state actions in this case.
It was also said that US travel bans for Muslim countries were islamophobic, but by the same token, the policy was discrimination against the state and not the people. Motivation behind the policy might have been made ny islamophobic people, but the ban itself is just foreign policy.
Edit: People seems to be misinterpreting my words or just not understanding. So let me spell it out: "discrimination against the state" is not antisemetic.
Gaza: Resistance warns of Israeli drones dropping spy devices, explosives
Resistance Security forces in the Gaza Strip on Thursday warned residents about an increase in activity by Israeli Quadcopter drones in recent days. According to a statement published on the security platform Al-Haris, these drones have dropped surveillance devices and explosive objects across various parts of the Strip.
Archived version: archive.is/newest/middleeastmo…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
US and Russia suggest ‘West Bank-style occupation of Ukraine’
The suggestion was put forward during discussions between President Donald Trump’s envoy Steve Witkoff and his Russian counterparts, a source with insight into the U.S. National Security Council told the paper.
Witkoff, who also serves as the White House’s Middle East envoy, reportedly backs the suggestion, which the U.S. believes will solve the issue of the Ukrainian constitution prohibiting giving up territory without organizing a referendum. While Ukrainian President Volodymyr Zelensky has rejected any notion of ceding territory, the new occupation proposal may lead to a truce following Russia’s full-scale invasion of Ukraine, which began in February 2022.
According to the proposal, Ukraine’s borders would remain officially unchanged, similar to the borders of the West Bank, even as Israel controls the territory. “It’ll just be like Israel occupies the West Bank,” the source told The Times.
US and Russia suggest ‘West Bank-style occupation of Ukraine’
Russia would have both economic and military control of the occupied parts of Ukraine under the proposalGustaf Kilander (The Independent)
Unless Ukrainians are the smartest people in the world a 98% vote on anything is virtually impossible
Not if the Banderite regime asked to boycott the referendum bcs they called it illegal.
That is if opponents were even there since a lot of them moved to Banderite controlled regions.
Is that not a Russian source?
Yes it is, but I can't even see that page since my democratic EU regime has made the choice for me that I am incapable of deciding what is real or 'RuZZian propaganda!' so they block Russian outlets.
We can only have toootally neutral pro-western 'news'.
And it's a bit rich to complain about only Russian sources since it's the OCSE that refused to send observers.
There are plenty of translations of Putins speeches and statements on the subject.
I recommend you read those.
Anyway, the only important thing to remember is that there was a US orchestrated and funded fascist coup and they put a puppet regime in place, same as they did in Afghanistan or the many many countries they regime change.
I don't get how you can back the most agressive imperialist country in the world, especially since this particular proxy is openly and proudly fascist.
There are plenty of translations of Putins speeches and statements on the subject.
I recommend you read those.
Such as which translation? The Tucker interview hasn't had any criticism of poor translation. Tucket got personally invited for it.
I'm in no way sympathetic to the US. In fact weakening the empire is probably what I support most. But not at the cost of a million Ukrainians.
Let's not forget who invaded Afghanistan before the US. I don't think Russia would use their power differently than NATO now if they were the global hegemon instead of the West.
Flash floods triggered by heavy rains kill at least 49 people in northwestern Pakistan
Officials in Pakistan say flash floods triggered by heavy rains have killed at least 49 people in the northwest and elsewhere in the country over the past 24 hours
Archived version: archive.is/newest/independent.…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
US and Russia suggest ‘West Bank-style occupation of Ukraine’
The suggestion was put forward during discussions between President Donald Trump’s envoy Steve Witkoff and his Russian counterparts, a source with insight into the U.S. National Security Council told the paper.
Witkoff, who also serves as the White House’s Middle East envoy, reportedly backs the suggestion, which the U.S. believes will solve the issue of the Ukrainian constitution prohibiting giving up territory without organizing a referendum. While Ukrainian President Volodymyr Zelensky has rejected any notion of ceding territory, the new occupation proposal may lead to a truce following Russia’s full-scale invasion of Ukraine, which began in February 2022.
According to the proposal, Ukraine’s borders would remain officially unchanged, similar to the borders of the West Bank, even as Israel controls the territory. “It’ll just be like Israel occupies the West Bank,” the source told The Times.
US and Russia suggest ‘West Bank-style occupation of Ukraine’
Russia would have both economic and military control of the occupied parts of Ukraine under the proposalGustaf Kilander (The Independent)
like this
AI experts return from China stunned: The U.S. grid is so weak, the race may already be over
China is “set up to hit grand slams,” longtime Chinese energy expert David Fishman told Fortune. “The U.S., at best, can get on base.”
like this
India PM Modi vows to protect farmers, cuts tax, pushes self-reliance amid Trump tariff tensions
However, he did not mention the US President or the US in his speech.
Archived version: archive.is/newest/straitstimes…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
India PM Modi vows to protect farmers, cuts tax, pushes self-reliance amid Trump tariff tensions
However, he did not mention the US President or the US in his speech. Read more at straitstimes.com.ST
Trump administration may buy into Intel
The US government under President Donald Trump is in talks with Intel about a possible state stake in the company.
Global plastics treaty talks in Geneva end in 'abject failure'
French minister says 'short-term financial interests' killed latest effort to tackle global plastics pollution
Archived version: archive.is/newest/euractiv.com…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
adhocfungus likes this.
US | Alaskans greet Putin with Ukrainian flags, protest ‘war criminal hanging out here’
Several hundred people gathered for a pro-Ukraine rally in Anchorage, Alaska, where U.S. President Donald Trump and Russian leader Vladimir Putin are set to meet Friday.
Archived version: archive.is/20250815082113/poli…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
Alaskans greet Putin with Ukrainian flags, protest ‘war criminal hanging out here’
Several hundred people gathered for a pro-Ukraine rally in Anchorage, Alaska, where U.S. President Donald Trump and Russian leader Vladimir Putin are set to meet Friday. The high-stakes summit — th…Veronika Melkozerova (POLITICO)
adhocfungus likes this.
UNRWA chief: Israel has blocked food entry to Gaza for over 5 months
Philip Lazzarini, the commissioner-general of the UN Relief and Works Agency for Palestine Refugees (UNRWA), said the UN agency, like other non-governmental organisations (NGOs), “has also been banned from bringing in aid to Gaza for over 5 months now.”
Archived version: archive.is/newest/middleeastmo…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
Afghanistan | Four years after the fall of Kabul, Taliban succeeds in near-total exclusion of women
Four years since Taliban forces seized Kabul and ended two decades of Western presence, Afghan women face near-total exclusion from public life. Nearly 100 edicts have stripped them of basic freedoms, while any dissent remains dangerous and international pressure has waned.
Archived version: archive.is/newest/france24.com…
Disclaimer: The article linked is from a single source with a single perspective. Make sure to cross-check information against multiple sources to get a comprehensive view on the situation.
This wasn't a Fox News poll, this was a Siena poll, which as far as I can tell is actually a reputable source for poll numbers.
sri.siena.edu/2025/08/12/hochu…
You can find all these specific numbers in the crosstab if you care to.
geneva_convenience likes this.
UPS Airlines Boeing 747-8F strikes engine during landing in Taipei amid typhoon Podul
On 13 August, a UPS Airlines Boeing 747-8F (registration N613UP) arriving in Taipei from Hong Kong struck its number 4 engine on the runway during landing. The incident occurred as Typhoon Podul brought strong crosswinds and heavy rain to the region, creating challenging conditions for flight crews.
Raoul Duke likes this.
Researchers build first ‘microwave brain’ on a chip
Researchers build first ‘microwave brain’ on a chip | Cornell Chronicle
Cornell Engineering researchers have developed a low-power microchip they call a “microwave brain,” the first processor to compute on both ultrafast data signals and wireless communication signals by harnessing the physics of microwaves.Cornell Chronicle
Frezik
in reply to MarcellusDrum • • •To those who have played around with LLM code generation more than me, how are they at debugging?
I'm thinking of Kernighan's Law: "Debugging is twice as hard as writing the code in the first place. Therefore, if you write the code as cleverly as possible, you are, by definition, not smart enough to debug it." If vibe coding reduces the complexity of writing code by 10x, but debugging remains just as difficult as before, then Kernighan's Law needs to be updated to say debugging is 20x as hard as vibe coding. Vibe coders have no hope of bridging that gap.
Pechente
in reply to Frezik • • •HarkMahlberg
in reply to Pechente • • •I saw an LLM override the casting operator in C#. An evangelist would say "genius! what a novel solution!" I said "nobody at this company is going to know what this code is doing 6 months from now."
It didn't even solve our problem.
hisao
in reply to HarkMahlberg • • •Before LLMs people were often saying this about people smarter than the rest of the group. "Yeah he was too smart and overengineered solutions that no one could understand after he left,". This is btw one of the reasons why I increasingly dislike programming as a field over the years and happily delegate the coding part to AI nowadays. This field celebrates conformism and that's why humans shouldn't write code manually. Perfect field to automate away via LLMs.
Feyd
in reply to hisao • • •hisao
in reply to Feyd • • •Feyd
in reply to hisao • • •This part.
hisao
in reply to Feyd • • •chunkystyles
in reply to hisao • • •very_well_lost
in reply to Frezik • • •The company I work for has recently mandated that we must start using AI tools in our workflow and is tracking our usage, so I've been experimenting with it a lot lately.
In my experience, it's worse than useless when it comes to debugging code. The class of errors that it can solve is generally simple stuff like typos and syntax errors — the sort of thing that a human would solve in 30 seconds by looking at a stack trace. The much more important class of problem, errors in the business logic, it really really sucks at solving.
For those problems, it very confidently identifies the wrong answer about 95% of the time. And if you're a dev who's desperate enough to ask AI for help debugging something, you probably don't know what's wrong either, so it won't be immediately clear if the AI just gave you garbage or if its suggestion has any real merit. So you go check and manually confirm that the LLM is full of shit which costs you time... then you go back to the LLM with more context and ask it to try again. It's second suggestion will sound even more confident than the first, ("Aha! I see the real cause of the issue now!") but it will still be nonsense. You go waste more time to rule out the second suggestion, then go back to the AI to scold it for being wrong again.
Rinse and repeat this cycle enough times until your manager is happy you've hit the desired usage metrics, then go open your debugging tool of choice and do the actual work.
HubertManne
in reply to very_well_lost • • •ganryuu
in reply to HubertManne • • •HarkMahlberg
in reply to very_well_lost • • •Reads to me as "Please help us justify the very expensive license we just purchased and all the talented engineers we just laid off."
I know the pain. Leadership's desperation is so thick you can smell it. They got FOMO'd, now they're humiliated, so they start lashing out.
frog_brawler
in reply to HarkMahlberg • • •Funny enough, the AI shift is really just covering for the over-hiring mistakes in 2021. They can’t admit they fucked up in hiring too many people during Covid, so they’re using AI as the scapegoat. We all know it’s not able to actually replace people yet; but that’s happening anyway.
There won’t be any immediate ramifications, we’ll start to see that in probably 12-18 months or so. It’s just another form of kicking the can down the road.
HarkMahlberg likes this.
frog_brawler
in reply to Frezik • • •How are they at debugging? In a silo, they’re shit.
I’ve been using one LLM to debug the other this past week for a personal project, and it can be a bit tedious sometimes, but it eventually does a decent enough job. I’m pretty much vibe coding things that are a bit out of my immediate knowledge and skill set, but I know how they’re supposed to work. For example, I’ve got some python scripts using rekognition to scan photos for porn or other explicit stuff before they get sent to an s3 bucket. After that happens, there’s now a dashboard that’s going to give me results on how many images were scanned and then marked as either acceptable or flagged as inappropriate. After a threshold of too many inappropriate images being sent in, it’ll shadowban them from sending any more dick pics in.
For someone that’s never taken a coding course, I’m relatively happy with the results I’m getting so far. Granted, this may be small potatoes for someone with an actual development background; but as someone that’s been working adjacent to those folks for several years, I’m happy with the output.
Zexks
in reply to Frezik • • •Working just fine. It one shot a kodi tv channel addon for me last week end. Used it to integrate kofax into docusign. Building 2 blazor apps one new one an upgrade. Used it to create a stack of mc servers for the kids with a dashboard of statuses and control switches. My son is working on his own mc mod with it. Use it almost daily for random file organization and management scripts. Using it to clean uo my media library meta data. Anytime i have to do something to more than 5 or so files i pull it up and ask for a script.
Its a tool like any other. There will be people who adapt and people who fail to. Just like we had with computers the internet. It zeems to be long forgotten now but literally ALL of these anti ai arguments were made against computers and the internet 30_50 years ago. Very similar ones were made when books and writing became common place as well.
TheFinn
in reply to Zexks • • •Zexks
in reply to TheFinn • • •TuffNutzes
in reply to MarcellusDrum • • •The LLM worship has to stop.
It's like saying a hammer can build a house. No, it can't.
It's useful to pound in nails and automate a lot of repetitive and boring tasks but it's not going to build the house for you - architect it, plan it, validate it.
It's similar to the whole 3D printing hype.
You can 3D print a house! No you can't.
You can 3D print a wall, maybe a window.
Then have a skilled Craftsman put it all together for you, ensure fit and finish and essentially build the final product.
Nate Cox
in reply to TuffNutzes • • •- YouTube
youtu.beTuffNutzes
in reply to Nate Cox • • •Yeah I've seen that before and it's basically what I'm talking about. Again, that's not "printing a 3D house" as hype would lead one to believe. Is it extruding cement to build the walls around very carefully placed framing and heavily managed and coordinated by people and finished with plumbing, electrical, etc.
It's cool that they can bring this huge piece of equipment to extrude cement to form some kind of wall. It's a neat proof of concept. I personally wouldn't want to live in a house that looked anything like or was constructed that way. Would you?
scarabic
in reply to TuffNutzes • • •Well, a minute ago you were saying that AI worship is akin to saying
Now you’re saying that a hammer is basically the same thing as a machine that can create a building frame unattended? Come on. You have a point to be made here but you’re leaning on the stick a bit too hard.
Nate Cox
in reply to TuffNutzes • • •I mean, “to 3d print a wall” is a massive, bordering on disingenuous, understatement of what’s happening there. They’re replacing all of the construction work of framing and finishing all of the walls of the house, interior and exterior, plus attaching them and insulating them, with a single step.
My point is if you want to make a good argument against LLMs, your metaphor should not have such an easy argument against it at the ready.
poopkins
in reply to Nate Cox • • •dreadbeef
in reply to TuffNutzes • • •Nalivai
in reply to dreadbeef • • •frog_brawler
in reply to TuffNutzes • • •You’re making a great analogy with the 3D printing of a house.
However, if we consider the 3D printed house scenario; that skilled craftsman is now able to do things on his own that he would have needed a team for in the past. Most, if not all, of the less skilled members of that team are not getting any experience within the craft at that point. They’re no longer necessary when one skilled person can now do things on their own.
What happens when the skilled and highly experienced craftsmen that use AI as a supplemental tool (and subsequently earn all the work) eventually retire, and there’s been no juniors or mid-levels for a while? No one is really going to be qualified without having had exposure to the trade for several years.
isaacd
in reply to MarcellusDrum • • •Citation needed. I don’t use one. If my coworkers do, they’re very quiet about it. More than half the posts I see promoting them, even as “just a tool,” are from people with obvious conflicts of interest. What’s “clear” to me is that the Overton window has been dragged kicking and screaming to the extreme end of the scale by five years of constant press releases masquerading as news and billions of dollars of market speculation.
I’m not going to delegate the easiest part of my job to something that’s undeniably worse at it. I’m not going to pass up opportunities to understand a system better in hopes of getting 30-minute tasks done in 10. And I’m definitely not going to pay for the privilege.
skisnow
in reply to isaacd • • •I've found them useful, sometimes, but nothing like a fraction of what the hype would suggest.
They're not adequate replacements for code reviewers, but getting an AI code review does let me occasionally fix a couple of blunders before I waste another human's time with them.
I've also had the occasional bit of luck with "why am I getting this error" questions, where it saved me 10 minutes of digging through the code myself.
"Create some test data and a smoke test for this feature" is another good timesaver for what would normally be very tedious drudge work.
What I have given up on is "implement a feature that does X" questions, because it invariably creates more work than it saves. Companies selling "type in your app idea and it'll write the code" solutions are snake-oil salesman.
Phegan
in reply to isaacd • • •I've only found two effective uses for them. Every time I tried them otherwise they fell flat and took me longer that it would have to write the code myself.
The first was a greenfield personal project where I let code quality wane since I was the only person maintaining it, and wanted to test LLMs. The other was to write highly repeative data tests where the model can simply type faster than me.
Anything that requires writing code that needs to be maintained by multiple people or systems older than 2 years, it has fallen completely flat. In cases like that I spend more time telling the LLM it is doing it wrong, it would have taken me less time to write the code in the first place. In 95% of cases, I am still faster than an LLM at solving a problem and writing the code.
frog_brawler
in reply to isaacd • • •I’m not a “software engineer” but a lot of people that don’t work within tech would probably call me one.
I’m in Cloud Engineering, but came from the sys/network admin and ops side of things rather than starting off in dev or anything like that.
Up until about 5 years ago, I really only knew Powershell and a little bit of bash. I’ve gotten up to speed in a lot of things but never officially learned python, js, go or any other real development language that would be useful to me. I’ve spent way more time focusing on getting good with IaC, and probably more of the SRE type stuff.
In my particular situation, LLMs are incredibly useful. It’s fair to say that I use them daily now. I’ve had it convert bash scripts to python for me very quickly. I don’t know python but now that I’m able to look at a python script next to my bash; I’m picking up on stuff a lot faster. I’m using Lambda way more often as a result.
Also, there’s a lot of mundane filling out forms shit that I delegate to an LLM. I don’t want to spend my time filling out a form that I know no one is actually going to read. F it, I’ll have the AI write a report for an AI. It’s dumb as shit, but that’s the world today.
NoiseColor
in reply to MarcellusDrum • • •Good article, I couldn't agree with it more, it's exactly my experience.
The tech is being developed really fast and that is the main issue when taking about ai. Most ai haters are using the issues we might have today to discredit the while technology which makes no sense to me.
And this issue the article talks about is apparent and whoever solves it will be rich.
However, it's interesting to think about the issues that come next.
Aceticon
in reply to NoiseColor • • •Like the guy whose baby doubled in weight in 3 months and thus he extrapolated that by the age of 10 the child would weigh many tons, you're assuming that this technology has a linear rate of improvement of "intelligence".
This is not at all what's happening - the evolution of things like LLMs in the last year or so (say between GPT4 and GPT5) is far less than it was earlier in that Tech and we keep seeing more and more news on problems about training it further and getting it improved, including the big one which is that training LLMs on the output of LLMs makes them worse, and the more the output of LLMs is out there, the harder it gets to train new iteractions with clean data.
(And, interestingly, no Tech has ever had a rate of improvement that didn't eventually tailed of, so it's a peculiar expectation to have for a specific Tech that it will keep on steadily improving)
With this specific path taken in implementing AI, the question is not "when will it get there" but rather "can it get there or is it a technological dead-end", and at least for things like LLMs the answer increasingly seems to be that it is a technological dead-end for the purpose of creating reasoning intelligence and doing work that requires it.
(For all your preemptive defense by implying that critics are "ai haters", no hate is required to do this analysis, just analytical ability and skepticism, untainted by fanboyism)
HarkMahlberg
in reply to NoiseColor • • •It's true, the tech will get better in the future, we just need to believe and trust the plan.
Same thing with crypto and NFT's. They were 99% scam by volume, but who wouldn't love moving their life savings into a digital ecosystem controlled by a handful of rich gambling addicts with no consumer protections? Imagine, you'll never need to handle dirty paper money ever again, we'll just put it all in a digital wallet somewhere controlled by someone else coughmastercardcough.
And another thing, we were too harsh on the Metaverse. Sure, spending 8 hours in VR could make you vomit, and the avatars made ET for the Atari look like Uncharted 4, but it was just in its infancy!
I too want to outsource all my critical thinking to a chatbot controlled by an wealthy insular narcissist who throws Nazi salutes. The technology just needs time to mature. Who knows, maybe it can automate the exile of birthright citizens for us too!
/s
NoiseColor
in reply to HarkMahlberg • • •Aceticon
in reply to NoiseColor • • •TankovayaDiviziya
in reply to MarcellusDrum • • •I don't work in IT, but I do know you need creativity to work in the industry, something which the current LLM/AI doesn't possess.
Linguists also dismiss LLMs in similar vein because LLMs can't grasp context. It is always funny to be sarcastic and ironic on an LLM.
Soft skills and culture are what that the current iteration of LLMs lack. However, I do think there is still huge potential for AI development in dacades to come, but I want this AI bubble to burst as "in your face" to companies.