Another possibility is of course that Hugging Face legitimately were attacked and wrote a completely honest response - but OpenAI instructed their AI to attack their servers and the breaking of containment is fiction.
I'm not convinced in any direction, really. But what makes me cautious is that there have been extraordinary claims from both OpenAI and especially Anthropic of their models breaking containment, hacking the host, etc. for several iterations of their products and I have only heard of this type of behavior from their own blog posts about how powerful and dangerous their upcoming models are. Never from anyone having it accidentally happen in production once they are released. It seems unlikely to me that the final post-training and safeguards are that bulletproof given how much use these tools are seeing.
I would rather say that many details of the supposed attack were published by Hugging face before it was publicly announced that OpenAI were involved.
Both are big actors in the AI space who arguably benefit from increasing the perceived capabilities of AI models. If one suspects OpenAI of lying it isn't such a stretch to think this was a coordinated PR campaign between them and Hugging face.
I agree with this. I've identified as a graphics programmer for a long time because it's a passion of mine and the fact that it's my profession seems almost like a happy accident.
This, coupled with fear of making mistakes in public, was the thinking which for years kept me from writing about my work. Until a comment here on HN encouraged me to just do it.
I am so happy that I listened because it seems the few people who have checked it out generally enjoy it. Most commenters have positive things to say and some have stated they learned things.
When I saw the title I immediately thought of Xbox Adaptive Controller. It's such a cool initiative.
Microsoft has a lot of really cool accessibility tools and services. For example their extensive usability guidelines, which is a massive set of documentation for how to make games more widely accessible. [0]
They also have a great service where you can submit your games to get a report with feedback how to improve accessibility.[1] I read through one we got at my last job and it was really impressive. Very thoughtful and comprehensive.
There's a hub with links to a lot more accessibility services as well. [2] Microsoft is one of the companies which really does a lot of great things in this space.
On the teams where I've worked which had a proper code review policy not understanding has been explicitly stated as a reason to pause and ask for clarification. You cannot give a pass for code you don't understand.
> The Apple II was dying as a platform by the time the game came out [...] it was rereleased on PC in the US and sales picked up. You wouldn’t get that second chance today.
On a much smaller scale, I was actually part of something similar a few years ago. The game Wavetale was originally a Stadia exclusive but launched just before the platform shut down. We were allowed by Google to port it and release it for every other platform, and I ended up being one of four programmers doing that work; I mainly focused on optimizing the switch version.
The Stadia version barely got noticed, but the other versions, especially Switch, did quite well. The game was even featured on AGDQ, which was really cool.
This is a cool project and I really like the author's technical and aesthetic choices of how to limit themselves.
But what really stood out to me is this line.
> a linear frame buffer where each pixel was represented by a single byte indexing into a palette of 256 colors.
Of course this is nothing new, but it just really struck me because I've been working on a blog post about texture representation on modern consoles and it is crazy how complex it has gotten: texture tiles, block compression, non-linear texel ordering (e.g. Morton order), ...
This is why, after spending my whole youth learning programming to become a game developer I had a crisis of faith and spent a few years working on something else (surgical training simulations) after graduating. I had done summer jobs at a game studio and all I saw was the leadership treating people like shit, paying almost nothing, and then laughing about how easy it was to got away with - they even did so towards me in one breath then offered me a full time contract in the next.
However, I joined EA in 2015 and have been in game development since. They offered really good pay and now at my current job I even get great pay and no overtime.
When I worked for EA (2015-2019) it was better than some horror stories I've heard, but still way too much overtime and many weekends spent at the office. The worst part that it was unpaid in exchange for an extra vacation week and then they had the gall to ask us to please not take our vacation because "don't you care about the game?".
Since then I've worked at Thunderful and now 505 Games. I haven't done overtime since I quit EA and I've been very efficient because I'm not too tired and I get peace of mind working from home.
Exactly. And it shows. It knows all the sayings, the expressions, etc. But shows very little actual practical understanding of them. Especially how to apply the knowledge it simulates.
I have had the same result when trying similar things for graphics on modern consoles. I hear so much great stuff about AI coding but in my niche it just seems to fall flat. Even just rubber ducking around graphics and performance they sound like a beginner who has read a lot of good blogs but with no practical experience.
It's working now and I have to say I love this. The whole project is whimsical and gives me a strong SCP vibe but (sometimes) without the creepypasta aspect. I was very pleased to see that articles generated from links retain the context of the page that created the link - and even refer back to the original page.
update: Well, this was quite disappointing. I loaded the original site again to show a friend and it generated a completely new text with a completely different story and no reference to the second article. Would have been nice if these were permanent as I had originally assumed.
My main interests and experience are in graphics programming and performance optimization.
https://agentlien.github.io