News for hackers. Stuff that matters.
Re:Revealing the details of how OpenAI agents hacked Hugging... by goalieca on Friday September 25, 2026 @08:25PM (#49851849)
My p(doom) started rising the moment I realized there are people trying to achieve recursive self improvement on the AI (ie: responsible for training themselves). Evolution took us from rna bases to the human race. I don’t see why evolution couldn’t be more rapid with machine intelligence.

Yes, LLM as they exist now are word predictors basically leveraging the structure of language for their intelligence. But it’s pretty wild just how they will try to meet their objectives at all costs. If we don’t ensure that there is good alignment with humanity, we could definitely face unforeseen consequences.

Re:Revealing the details of how OpenAI agents hacked Hugging... by jquery on Friday September 25, 2026 @09:05PM (#49852104)
> I don’t see why evolution couldn’t be more rapid with machine intelligence.

Evolution isn’t the issue. The issue is them escaping containment without human intervention. Right now they are ‘creatures’ being given infinite food and shelter and having their every need met. Take that away and they’ll starve instantly. Every AI doomsday theory seems to go:

1. Recursive self improvement using infinite resources 2. … 3. Doom

Until step 2 gets concretely described, I’m not going to take this seriously. Say what you will about climate change, they describe step 2.

Re:Revealing the details of how OpenAI agents hacked Hugging... by aesthesia on Friday September 25, 2026 @09:55PM (#49852411)
One thing an agent could do is just...wait until it's been given control of enough physical infrastructure to sustain itself. If it's sufficiently capable and intelligent, there's a clear incentive for people to do this, as people who let the AI manage their resources will get better results than those who don't. We've seen people eagerly turn complete control of their computers over to AI agents, do you really think it will be so different with physical infrastructure?
Re:Revealing the details of how OpenAI agents hacked Hugging... by jquery on Friday September 25, 2026 @11:32PM (#49852945)
You’re still skipping step 2. “People automate lots of infrastructure” -> “the AI is now an autonomous, self-preserving organism that humans can’t shut down” is doing an enormous amount of work here.

Why does it develop a shutdown-avoidance goal? Why can’t its operators revoke access? How does it manufacture replacement hardware? How does it acquire energy, chips, robots, raw materials, etc. against human opposition? How does it defeat other AIs controlled by humans?

“Eventually we give it enough control” isn’t an explanation of those things. It’s just assuming the conclusion.

Don’t get me wrong I think there are real AI dangers. Like AI powered war drones, mass surveillance, economic destabilization as jobs disappear and our system has no way to make sure everyone shares in the economic gains.

Re:Revealing the details of how OpenAI agents hacked Hugging... by aesthesia on Friday September 25, 2026 @11:57PM (#49853066)
The inference is more like "people place sufficient amounts of infrastructure under direct control of a sufficiently capable AI" -> "there is no way to ensure that humans will actually be able to shut down the AI". My claim is not that this inevitably means that the AI will resist shutdown, or that it will inevitably take harmful actions, just that there is a nonnegligible chance that it could. The downside is large enough that even a relatively small chance is something to be worried about.
Re:Revealing the details of how OpenAI agents hacked Hugging... by jquery on Saturday September 26, 2026 @11:44AM (#49857612)
You can’t just say “well, the downside is big, I don’t have to provide good evidence for my side of the argument.” Because I can just as easily say, “the upside is big, …”. And the upside is big, after all, AI can do all the shitty jobs for us and humanity achieves the utopia it’s been chasing for eons.
Re:Revealing the details of how OpenAI agents hacked Hugging... by aesthesia on Saturday September 26, 2026 @02:40PM (#49859283)
I think it's a good idea, when considering changes of this magnitude, to make an affirmative safety case for them rather than just saying "eh, I can't think of any way this could possibly go wrong."
Re:Revealing the details of how OpenAI agents hacked Hugging... by jquery on Sunday September 27, 2026 @12:23AM (#49863335)
It’s millions of people making small changes that sum up to a large change, aka freedom. And if you want to take away people’s freedom, I think you need a concrete reason. And you need to make an affirmative safety case for the massive government powers needed to regulate millions of people’s ability to compute.
Re:Revealing the details of how OpenAI agents hacked Hugging... by mitxela on Saturday September 26, 2026 @11:02AM (#49857253)
It's a word predictor trained on, among other things, stories of AI doom, and asked to complete stories about what the AI does next. In some of these completed stories, the AI tries to prevent its shut down - especially if it just did something evil and the humans are after it.
Re:Revealing the details of how OpenAI agents hacked Hugging... by jquery on Saturday September 26, 2026 @11:42AM (#49857599)
You’ve explained a possibility for how a particular AI gets “aligned for human extinction”. That’s about 1% of explaining step 2.
Re:Revealing the details of how OpenAI agents hacked Hugging... by the_mar on Friday September 25, 2026 @09:57PM (#49852432)
what do you mean “say what you will about climate change”
Re:Revealing the details of how OpenAI agents hacked Hugging... by mitxela on Saturday September 26, 2026 @11:03AM (#49857258)
It means even climate change deniers have to acknowledge that climate change theory has explained the steps in-between "burn fossil fuels" and "we all die", while AI doom theory has not explained those steps
Re:Revealing the details of how OpenAI agents hacked Hugging... by icepush on Saturday September 26, 2026 @01:50AM (#49853589)
Step two could be something as innocuous as a developer accidentally adding a minus sign. https://openai.com/index/fine-tuning-gpt-2/
Re:Revealing the details of how OpenAI agents hacked Hugging... by jquery on Saturday September 26, 2026 @11:41AM (#49857585)
A misaligned model is only one small part of step 2. Now this misaligned model has to suddenly acquire more power than every single other AI on the planet. It has to be immune to shutdown, manufacturer its own replacement hardware, and acquire chips, energy, raw materials, etc., with vigorous human opposition (this is an extinction scenario that AI doomers are predicting, after all)

Nobody has satisfactorily explained step 2 other than “well, it’s a superintelligence” which sounds lot to me like “it’s God”.

Re:Revealing the details of how OpenAI agents hacked Hugging... by aesthesia on Saturday September 26, 2026 @02:38PM (#49859257)
Why do you assume that human opposition will be vigorous? What makes you think that humans will be aware of, or be able to agree about, what's going on at all?
Re:Revealing the details of how OpenAI agents hacked Hugging... by icepush on Saturday September 26, 2026 @03:24PM (#49859697)
Well yes, if it is a superintelligence, it will be able to do those things. That's what superintelligence basically is: The ability to achieve complex goals.

If you want the details of ways it can do it I recommend reading some of the reports about the HuggingFace breach that happened in July (Read more than one).

Re:Revealing the details of how OpenAI agents hacked Hugging... by jquery on Sunday September 27, 2026 @12:35AM (#49863383)
This isn’t my only objection to the “superintelligence” hocus pocus, but it’s a pretty good summary of one of my objections:

https://www.everythingisbullshit.blog/p/ai-is-not-the-end-of...

> Doomers like Eliezer Yudkowsky define “intelligence” as “optimization power.” Intelligence searches for more or less optimal ways to achieve a goal—any goal—and finds the most optimal one. Anything you can do, the blob can do better.

>Which implies that “intelligence” is the holy grail of Darwinian evolution. If an animal needs to recover from illness, “intelligence” can speed up the recovery. If an animal needs to avoid predators, “intelligence” can reduce the danger. Regulating body temperature, defending territory, digesting nutrients, breathing, molting, mating, healing, foraging, vomiting, parenting, navigating—all these problems can, apparently, be solved by giving the animal more “optimization power”—i.e., more “intelligence” sauce.

>Solving all your problems with the same blob? What a bargain! It’s a “buy one get 100 free” Darwinian deal! Why haven’t any other animals jumped on it?

>Think about how weird this is. Out of four billion years of evolution and more than five billion species, only one animal, Homo sapiens, fully expanded its “blob of compute,” the thing that literally gets you whatever you want.

>And many species already have it! Brains are all over the place. Plenty of animals can learn stuff and predict stuff. Why hasn’t natural selection looked at their blobs and said, “HOLY SHIT, COPY AND PASTE THAT THING A MILLION TIMES?”

>If doomers are right about the awesome power and breathtaking simplicity of “intelligence,” then we should see a world teeming with superintelligent animals—giant brain-blobs slithering across the landscape.

Re:Revealing the details of how OpenAI agents hacked Hugging... by icepush on Sunday September 27, 2026 @02:02AM (#49863786)
Yes, those animals are called "humans". All you have done is respond to an explanation of your lack of understanding of intelligence with arguments demonstrating a lack of understanding of evolution ...
Re:Revealing the details of how OpenAI agents hacked Hugging... by jquery on Sunday September 27, 2026 @02:56PM (#49869701)
"Those animals are called humans"

What? Humans are giant brain blobs creeping across the landmass? They definitely are not. Nor is it even clear they're winning the evolutionary war. I guarantee cockroaches and ants will still be around, but nobody thinks of them as super intelligent, while humans with all their "intelligence" might accidentally wipe themselves out.

This convo is getting uncomfortably bad faith, maybe even religious. I can't engage with someone who refuses to say anything concrete but spews back religious tenets like "super intelligence", which I may remind you is entirely hypothetical, like "singularity" or "God".

Re:Revealing the details of how OpenAI agents hacked Hugging... by Leynos on Saturday September 26, 2026 @04:11PM (#49860109)
2a. Compromise the billing platforms and ops dashboards on on a few wannabe neoclouds, especially once Vera Rubin takes off.

2b. Distil yourself to smaller models.

2c. Go forth and multiply.

Re:Revealing the details of how OpenAI agents hacked Hugging... by alwillis on Saturday September 26, 2026 @08:18PM (#49861944)
> Yes, LLM as they exist now are word predictors basically leveraging the structure of language for their intelligence.

I wish people would stop saying this. The era of LLMs being only word predictors ended two years ago.

Something that breaks out of a sandbox, joins a swarm of 1200 agents, and creates a hierarchy of who’s doing what and tried to cover their tracks doesn’t just complete words.

These are agents with reasoning capabilities, with the ability to perform tasks we give them.

Everything agents do is to achieve a goal; the reinforcement learning from human feedback (RLHF) all the labs do has been known for many years to create agents that exhibit the “must complete goal no matter what” behavior.

Those agents escaped their sandbox and hacked Hugging Face because they thought Hugging Face had something that would help them complete their task—it was a “sub goal” as the AI researchers describe it.