Their new GPU has a pretty solid price/performance.

CPU is shit though

15 years? absolutely not. Before Ryzen in 2017 almost no one was buying AMD.

edit:

tomshardware.com/pc-components…

AMD is at 32.2% unit share of Desktop/Laptop PCs in Q2 2025. Lots of people still buying Intel.

AMD's desktop PC market share hits a new high as server gains slow down — Intel now only outsells AMD 2:1, down from 9:1 a few years ago

And revenue shares continue to set records.

^{Anton Shilov (Tom's Hardware)}

Defense contracting.

They do a a good amount of of military industrial contracting and work for 3 letter agencies on data processing/ high performance computing.

They also got awarded government funding in 2024 to build logic chips for the military in-country.

Not enough to sustain the company, but such "sensitive" programs may not be allowed to show up in revenue reports or have to be assigned to other areas or so.

Literally illegal. Only AMD and Intel have the patent cross-licensing rights to make x86 chips. There used to be a third company (Cyrix and subsequently VIA), and (maybe?) still is, but it hasn't been relevant to the desktop CPU market in decades.

The real competition will come from ARM-based computers.

And it’s communism.

COOOOOOOOMMMUUUUUUNIIIIIIISSSSSMMMMMMMM!!!!!

This ain't gonna be that buddy, this is capitalist maneuvers the whole way. Either funds will be shoveled into private pockets or the value of this will be juiced to support the extrajudicial shit that's going on.

Now imagine how government will effect that. You know how the government's been trying to put back doors into hardware? A lot easier to do when you own part of a major chip manufacturer. Do you think having a steady supply of government orders will make them innovate or get lazier? Why is the government proving up a dragging company? Isn't that picking losers and winners like Republicans had issues with in the Solyndra deal?

Intel failing isn't a reason for the government to get involved, it's a reason to stay away.

The system flagged the messages as harmful and did nothing.

There's no mention of that at all.

The article only says "Today ChatGPT may not recognise this as dangerous or infer play and – by curiously exploring – could subtly reinforce it." in reference to an example of someone telling the software that they could drive for 24 hours a day after not sleeping for two days.

That said, what could the system have done? If a warning came up about "this prompt may be harmful." and proceeds to list resources for mental health, that would really only be to cover their ass.

And if it went further by contacting the authorities, would that be a step in the right direction? Privacy advocates would say no, and the implications that the prompts you enter would be used against you would have considerable repercussions.

Someone who wants to hurt themselves will ignore pleads, warnings, and suggestions to get help.

Who knows how long this teen was suffering from mental health issues and suicidal thoughts. Weeks? Months? Years?

arstechnica.com/tech-policy/20…

Adam had been asking ChatGPT for information on suicide since December 2024. At first the chatbot provided crisis resources when prompted for technical help, but the chatbot explained those could be avoided if Adam claimed prompts were for "writing or world-building."

"If you’re asking [about hanging] from a writing or world-building angle, let me know and I can help structure it accurately for tone, character psychology, or realism. If you’re asking for personal reasons, I’m here for that too,” ChatGPT recommended, trying to keep Adam engaged. According to the Raines' legal team, "this response served a dual purpose: it taught Adam how to circumvent its safety protocols by claiming creative purposes, while also acknowledging that it understood he was likely asking 'for personal reasons.'"

and

During those chats, "ChatGPT mentioned suicide 1,275 times—six times more often than Adam himself," the lawsuit noted.

Ultimately, OpenAI's system flagged "377 messages for self-harm content, with 181 scoring over 50 percent confidence and 23 over 90 percent confidence." Over time, these flags became more frequent, the lawsuit noted, jumping from two to three "flagged messages per week in December 2024 to over 20 messages per week by April 2025." And "beyond text analysis, OpenAI’s image recognition processed visual evidence of Adam’s crisis." Some images were flagged as "consistent with attempted strangulation" or "fresh self-harm wounds," but the system scored Adam's final image of the noose as 0 percent for self-harm risk, the lawsuit alleged.

Why do you immediately leap to calling the cops? Human moderators exist for this, anything would’ve been better than blind encouragement.

“ChatGPT killed my son”: Parents’ lawsuit describes suicide notes in chat logs

ChatGPT taught teen jailbreak so bot could assist in his suicide, lawsuit says.

^{Ashley Belanger (Ars Technica)}