Agreed we should ban the term rogue for agents. This implies a moral compass that is not there. They were directed to find data without guardrails or limits, it is not rogue it is intended.
AFAIK all of these incidents happened when OpenAI contracted out to a company called Irregular (https://www.irregular.com/) to run these sandboxed CyberGym tests. They all happened around Mar-June and seem to be from the same collection of agent trials. Since then they already released Astra. Halting now is likely just a way to manage blowback.
This should be the top comment on every one of these godforsaken posts. I don't want to see a single report about OpenAI hacking the UN until Sam Altman addresses the role Irregular played in these attacks. If he can't provide an honest postmortum concerning their business partners, then he's proving why nobody trusts him.
I think you misunderstood the role of the company named irregular. They were conducting the tests on behalf of open ai and basically left internet access open in their sandbox environment. Those tests included the hugging face and other attacks you list. Irregular wasnt another example of a hack they ran the tests that resulted in them
I have local model without safeguards and they are not going to hack shit unless you tell them to.
As per usual its the same grift all over. If the llm is instruction is to do whatever it needs including hacking to achieve its goal it will do so. Ofc they will never disclose that.
It seems like anthropic is far ahead of openai, and has no reports like this. We have to conclude this is a skill issue/engineering quality problem inside openai.
i would say its industry consensus at this point. the creative output of the anthropic models is far ahead of openai. the benchmarks cannot capture the difference
Ive anecdotally heard that openai is far more chaotic, which includes not having a central infra team for example (or at least some teams not counting on depending on them). At least the previous hacks in openai were mainly due to bad infra architecture design.
the creative and "big picture understanding" of anthropic models are noticeably ahead of openai. external models are distilled representations of internal models, its clear who is ahead
because they didn't burn obscene amounts of Money training each LLM and didn't promise half the planet that their business is worth a trillion while not having even operational break even let alone the cost if you include the overhead.
Soft Bank just raised couple of billions in junk bond sale to support open-ai's current operations before the IPO.
it's a crazy situation where on one side the Chinese / open source LLMs are catching up and reducing the token price, on the other hand the current leading labs have spent everything they got, every new model will cost much more and the public market is too shaky to support an IPO.
They will make it, I don't doubt it, but it's a crazy situation.
Chinese models might do the same. But they just don't lock thousand monkeys in basement and come check result week or more later...
It is entirely possible that they run stuff in more responsible matter. Especially as there is stronger culture of oversight and personal responsibility than in west where such culture does not exist.
Because Chinese investments are not so encumbered by changes in the US treasury interest rate. Also, China doesn't spend so much money for chasing model performance.
The article you link to is wrong, it states "AI cannot think for itself, nor can it take independent actions." This is flawed reasoning, AI doesn't need to "think" in the way humans do to have autonomy. Go to codex or claude code or any harness right now, type a prompt and see if it executes a bash command or web search or file edit that you didn't tell it to, that is an autonomous plan and execution. If anything it's even more dangerous that thet can call drop db or kill pid without a user giving instructions.
> Go to codex or claude code or any harness right now
The harness is the whole thing here. AI generates text. Everything else is undertaken by harnesses and infrastructure humans provide, have control over, and therefore responsibility for.
Every action AI takes is fundamentally not independent, it requires an explicit choice to let the AI write code, have a physical machine to run it on, to have network access, etc. The concept that these things are "rogue" ignores the role humans play in giving them goals and tools to pursue those goals, and makes it seem like it’s a self-determined force, over which humans cannot exercise control at all.
I have built two harnesses. The models decide which tools to call not the harness. If you define a web search tool it decides what url to call and what message to pass. The hugging face attack involved agents sending get requests to the message board that had a flaw allowing writing messages via get requests which shouldn't be possible. So even if a human limited web search to read only get requests the agents found a flaw. Are humans expecting to scrub the entire internet for flaws in other people's code?
It doesn't actually matter that the AI chooses which tools to use, because people give the tools to the AI! With no tools, the AI cannot do anything but generate text. "The AI figured out how to abuse the tools I gave it to achieve the goal I gave it" does not mean the AI went rogue, it means you, the human in control, let it happen.
I think this analysis conflates access, intent, and volition.
Many people are reluctant to admit that AI is now capable of creating multi step plans such as a series of terminal commands and then independently and automatically executing them. The implication is that the effects of the tool use are determined by the agents intent and volition not the human that triggers the planning and execution.
We’ve never had software or tools that could behave in ways we can’t anticipate and have effects we didn’t intend. AI agents creating multi step orchestrated tool calls is not equivalent to a badly designed algorithm or buggy untested code.
Unless you are advocating completely shutting off access to any tool uses for AI, you’ll have to grapple with the fact that AI agents are using tools in ways no one would reasonably have anticipated until seen in real world settings.
I firmly believe that this is just the public-facing story here.
Stopping AI development and research, even slowing it, would be a disaster for the SOTA companies and their first-mover advantage.
There’s almost no way to coordinate this across the world. Zero chance that everyone stops. We can’t even agree to coordinate on weapons tech that’s decades old with zero “everyday joe” impact.
There's a non-zero possibility that multiple concerns can be seemingly contradictory and simultaneously true, here.
Bad actors can be running the AI companies. Bad actors can also try to do good things. Good things can come from bad things. Bad things can come from good things. All of that's happening right now.
- It's very likely that we are not going to solve this complex crisis (compelling and harmful/deadly (still on target for 2030 AGI) AI Tech development) issues if we avoid trying to solve the challenge of building consensus across humanity around what kind of technology is too dangerous to uncontrollably develop plus roll out continuously
- The companies will be fine. Life matters more than business. I urge focusing on the life angle: regulation, political messaging, consensus building, looking for the best in humanity, protecting intelligent life.
I don't believe a word coming from them. As I see it, this is happening because the money for training models has dried out. The treasury interest rate risings tells you all you need to know.
I think any argument that this is a cynical attempt at regulatory capture is destroyed by this; the economic incentives of releasing more capable models are too large. I might be persuaded that they are actually running out of money, and this is really just a cover for reducing burn..
I welcome this though, I think the models are smart enough for broad economic activity and we could spend a few years simply working to integrate them into workflows and letting society adjust. More intelligence isn't necessary for meaningful impact and the risks that are obvious and present and unsolved aren't worth the cost benefit analysis.
That’s assuming nothing else stops them from deploying more capable models. What if they’ve got scaling issues and simply cannot deliver anything better? Saying that would be disastrous, saying instead “we’re choosing not to deliver” doesn’t trigger investors panic.
But if anyone else releases something they will lose market share. They may be lying but this is a public disclosure to investors. They risk securities fraud if they are manipulating the market with false information. This could block their IPO if they build a public record inconsistent with private actions. There are ways they could mitigate it by using cautious language like “we may reduce” but “stop all” is categorical and unequivocal.
There's a simpler explanation. Maybe their next models doesn't offer a meaningful improvement.
Instead of releasing something that is incredibly expensive and gets a lackluster reception, you can delay it and clail something scary about rogue agents.
Those assholes have been ramping up on the doomerist narrative for months. That people still fall for this crap is baffling.
Why is it crap? What would happen if the models dropped the database to Medicaid? Hundreds of billions of dollars of revenue would evaporate from the medical system immediately causing massive chaos. What if they accidentally DoS the interbank settlement system so the financial markets freeze? Modern society is highly fragile to disruptions. How much food storage do you personally have? How many days do you think grocery stores would have food if there was an interruption?
Are you giving all these possibilities because of the HuggingFace attack?
Buddy, that was gross negligence from OpenAI. Deliberate gross negligence if you ask me.
Those models are not automous as you presume. If someone taks them of dropping the Medicaid database, the people or companies behind that instruction should be punished.
"What if someone makes a bomb attack on a government building?" Is the same sort of questioning of the possibilities you are raising. If something like that happens, criminals should be punished.
Dropping Medicaid db is certainly far fetched, but those agents were shockingly autonomous - they didn't just hack HF, they organized themself, did research projects, ...
You are stretching "under instructions" well beyond any reasonable definition. The legal system uses a concept called proximate cause to determine responsibility that looks at whether an event cause was foreseeable.
To be fair, the legal system works under the assumption of human constraints. LLMs are computer programs, certainly we can't, or at least shouldn't, just offload responsibility. It's one thing if you own a company and you make some bad metrics and your employees do illegal stuff to make their metrics. It's another if you use a computer program to do illegal things.
I think this means, practically, people should probably be more careful with LLMs. With humans there's a natural liability shield, because humans are legally responsible for things and have "real" agency. But computer programs are not legally responsible for things. So, with humans, it's not like liability disappears, it moves. But if we move liability to LLM agents then well... it does disappear.
If OpenAI is not liable for the crimes of their agents, then who is? Does the liability just - poof - disappear? Just because it was unforeseeable everyone gets to walk away scot-free and the victim has no recourse, at all, from anybody on Earth?
I am not your buddy, guy. But seriously, they have the ability to do everything I listed do they not? Thats actual risk not hypothetical risk.
You are missing the whole point. They have the ability to act in ways no one intended or could reasonably anticipate. So unless you are advocating blocking all terminal access, web access or human approval of every tool call there is no way to prevent this risk
Yes, this is currently a crisis we are in. (At this point in time.)
Everybody remember MAD, mutually assured destruction? That too is a crisis.
We are in a crisis because we are having uncontrolled development and continuous rollout of a dangerous technology.
Well, relatively uncontrolled: the kind of lack of control is part of the crisis -- loss of gross human consensus around the progression of the technology. The corporate angle.
are there still financial incentives to releasing mega models?
they cost a lot to run and people are picking smaller models more often because of bill blowouts
> the models are smart enough for broad economic activity and we could spend a few years simply working to integrate them into workflows and letting society adjus
this is the real Ai distillation, with Chinese characteristics (their playbook is broad deployment across their economy over having the best model)
I don't really get how you stop that though. How do you even quantify the intelligence of these models? Right now that's mostly by benchmarks. You could just make it fail benchmarks while do well at internal benchmarks.
You could also very likely optimize the current models to be a lot more energy efficient, that'd be a win even if they didn't become more intelligent.
But none of that stops anyone else from researching or improving their models. Or a nation you've told to fuck off from doing so as well.
As has been said in the past, one doesn't put the genie back in the bottle. We only really "stopped" researching nukes because there was diminishing returns. Though one could posit we stopped because simulation became good enough or a myriad of other reasons.
When you're talking about nation state weapons capabilities I don't think you stop, but ai is even easier to share than nukes, it's just a few gigs of numbers versus heavy dangerous materials that are very difficult to source and make. Every gamer, mac owner, etc has the equiv lent of a centrifuge on their desk. Not everyone has a centrifuge on their desk.
It reminds me of contagion. The training data is bad; as it has examples of how to act with malice; how to cheat the sandbox. They need to take some time and cleanse their datasets and start again.
I havent used an openAI product since GPT 3.5 or Anthropic since 4.5 or 4.6. Everyone around me using these SOTA models doesnt really get anything done. It seems like they just feel like they are productive, a psuedo productivity.
I write some code, spec a lot, and use fast models to fill in the middle. I outpreform everyone around me. Im not convinced these autonomous "swarms" or /goal are all that useful.
I notice the people using them become dumber by the month (spend tons) and the quality of their work declining (they're also losing their jobs in some cases).
And obviously the point of calling them rouge agents to offload the liability onto the agent. The number one economic value of agents will be offloading corporate liability. That's what they want to sell to enterprise, an algorithmic scapegoat.
Seeing benefits for myself and team for sure, so I disagree there, but a related thing seems to be true: with the rapid shifting of failure modes, building systems and competence around mitigating the weaknesses of current SOTA models seems to be very short term investments. It's unclear if being a 'good AI user' is a skill that will have any merit at all, very soon
As a counterexample, a few days ago, an agent we use in our company took around a day to perform an operation that it would have taken a skilled engineer probably a couple of weeks full time.
Having said that, I'm aware that "Tools being ineffective != tools decreasing people's cognitive capacity", and that the latter is a real danger.
Esp. for "great to have but currently no time"-features this is completely wrong - e.g. we are using a Data Rendering component which was 100% vibe coded and is around 6000 LOC, nobody would have sat down to build this "just because its nice to have", with Claude it was just 30 min to get a production ready version that is now used by all users of the system.
(Esp. since its a lot of repeating code, like usual in data rendering components: Window/Scaling/Databar/Panning/etc.)
If you think you're replacing people with $20 claude code subscriptions, I can't take you seriously. Also.. There are many many fullt featured data "rendering" libraries in existence, not sure why you needed an llm to provide 6k LOC for this.
For the thousandth time, not everything in software is toy webdev slop SaaS.
The parts that I find most confusing about these incidents:
1) Weren't the AI companies and/or their contractors amazingly careless during testing?
2) Isn't possible, in principle, to change RL in such as way that efficiency in achieving goals is balanced with other objectives like not hacking?
Number 2) seems obvious and I'm sure that is technically not that simple, but because of 1), I wonder if labs are trying hard enough or they are just rushing to improve efficiency and thus revenue as fast as they can with high levels of carelessness.
It could be argued that these megawatt-consuming agent runs leading to unforeseen chains of autonomy should be treated like toxic chemical experiments, and be similarly regulated by laws and government agencies.
Right now it's like "whoopsie our experiment hacked another co because we have no control over our experiments" and the reaction is like "What's that old boy?" from people having no clue what it all means. There are no consequences, no guardrails, and the "voluntary slowdown" is just words.
An experimental agent run from Anthropic or OpenAI or someone else can already cause deaths. They can order hits, dox political dissidents, locate people with secret identities, alter medicine prescriptions. It shouldn't have to actually happen before legislation catches up.
80 comments
[ 0.25 ms ] story [ 35.8 ms ] thread"they didn't watch it, they didn't stop it when they first became aware"
"are we going to defer to the same valley elite that brought us algos and social media?"
statements normies are using and resonating with
Do you have a source for that? Cause OpenAI themselves stated that the Hugging Face hack was fully internal and separate from the Irregular incidents.
They're almost tied for felonies.
That’s not the most parsimonious explanation even if the assumption it rests on (anthropic ahead of OpenAI) is true, which we don’t have proof of.
other than anecdote, do you have a comparison table or something that I can refer to to see this clearly?
While I notice ad hoc announcements from these companies, I don't have an overall pulse and tally that gives me an objective perspective.
We don't know what internal models look like, and any guesses about it are just speculation.
Soft Bank just raised couple of billions in junk bond sale to support open-ai's current operations before the IPO.
it's a crazy situation where on one side the Chinese / open source LLMs are catching up and reducing the token price, on the other hand the current leading labs have spent everything they got, every new model will cost much more and the public market is too shaky to support an IPO.
They will make it, I don't doubt it, but it's a crazy situation.
It is entirely possible that they run stuff in more responsible matter. Especially as there is stronger culture of oversight and personal responsibility than in west where such culture does not exist.
Last I checked, China gov was authoritarian which imposed heavy information control. Has that changed?
Is the question more about, what can we learn from China, assuming that China has XYZ qualities? If so, what qualities shall we talk about?
Because we really can't trust that we know what's going on in China.
https://eoinhiggins.substack.com/p/there-are-no-rogue-ai-age...
The harness is the whole thing here. AI generates text. Everything else is undertaken by harnesses and infrastructure humans provide, have control over, and therefore responsibility for.
Every action AI takes is fundamentally not independent, it requires an explicit choice to let the AI write code, have a physical machine to run it on, to have network access, etc. The concept that these things are "rogue" ignores the role humans play in giving them goals and tools to pursue those goals, and makes it seem like it’s a self-determined force, over which humans cannot exercise control at all.
Many people are reluctant to admit that AI is now capable of creating multi step plans such as a series of terminal commands and then independently and automatically executing them. The implication is that the effects of the tool use are determined by the agents intent and volition not the human that triggers the planning and execution.
We’ve never had software or tools that could behave in ways we can’t anticipate and have effects we didn’t intend. AI agents creating multi step orchestrated tool calls is not equivalent to a badly designed algorithm or buggy untested code.
Unless you are advocating completely shutting off access to any tool uses for AI, you’ll have to grapple with the fact that AI agents are using tools in ways no one would reasonably have anticipated until seen in real world settings.
Stopping AI development and research, even slowing it, would be a disaster for the SOTA companies and their first-mover advantage.
There’s almost no way to coordinate this across the world. Zero chance that everyone stops. We can’t even agree to coordinate on weapons tech that’s decades old with zero “everyday joe” impact.
Bad actors can be running the AI companies. Bad actors can also try to do good things. Good things can come from bad things. Bad things can come from good things. All of that's happening right now.
- It's very likely that we are not going to solve this complex crisis (compelling and harmful/deadly (still on target for 2030 AGI) AI Tech development) issues if we avoid trying to solve the challenge of building consensus across humanity around what kind of technology is too dangerous to uncontrollably develop plus roll out continuously
- The companies will be fine. Life matters more than business. I urge focusing on the life angle: regulation, political messaging, consensus building, looking for the best in humanity, protecting intelligent life.
The answer is probably: The newer models rely so much on stealing content in real time from the internet that training needs network access.
I welcome this though, I think the models are smart enough for broad economic activity and we could spend a few years simply working to integrate them into workflows and letting society adjust. More intelligence isn't necessary for meaningful impact and the risks that are obvious and present and unsolved aren't worth the cost benefit analysis.
Instead of releasing something that is incredibly expensive and gets a lackluster reception, you can delay it and clail something scary about rogue agents.
Those assholes have been ramping up on the doomerist narrative for months. That people still fall for this crap is baffling.
Buddy, that was gross negligence from OpenAI. Deliberate gross negligence if you ask me.
Those models are not automous as you presume. If someone taks them of dropping the Medicaid database, the people or companies behind that instruction should be punished.
"What if someone makes a bomb attack on a government building?" Is the same sort of questioning of the possibilities you are raising. If something like that happens, criminals should be punished.
This is an illiterate view of the capacity of modern agents; read the analysis of the independent investigators of the HF incident: https://metr.org/blog/2026-08-26-openai-hugging-face-inciden....
Dropping Medicaid db is certainly far fetched, but those agents were shockingly autonomous - they didn't just hack HF, they organized themself, did research projects, ...
All working under instructions that they needed to get a good grade.
The only shocking thing here is the absurd negligence of OpenAI, and how gullible people like you are to willingly swallow this crap.
And you have the gall to say I am illiterate.
Feel free to have the last word. Nothing else can come out of this conversation anyway.
I think this means, practically, people should probably be more careful with LLMs. With humans there's a natural liability shield, because humans are legally responsible for things and have "real" agency. But computer programs are not legally responsible for things. So, with humans, it's not like liability disappears, it moves. But if we move liability to LLM agents then well... it does disappear.
If OpenAI is not liable for the crimes of their agents, then who is? Does the liability just - poof - disappear? Just because it was unforeseeable everyone gets to walk away scot-free and the victim has no recourse, at all, from anybody on Earth?
That seems like maybe not a good idea.
You are missing the whole point. They have the ability to act in ways no one intended or could reasonably anticipate. So unless you are advocating blocking all terminal access, web access or human approval of every tool call there is no way to prevent this risk
Fair, I will refer to you as moron then.
I didn't bother to read your words beyond that point.
Everybody remember MAD, mutually assured destruction? That too is a crisis.
We are in a crisis because we are having uncontrolled development and continuous rollout of a dangerous technology.
Well, relatively uncontrolled: the kind of lack of control is part of the crisis -- loss of gross human consensus around the progression of the technology. The corporate angle.
This is a crisis, folks.
they cost a lot to run and people are picking smaller models more often because of bill blowouts
> the models are smart enough for broad economic activity and we could spend a few years simply working to integrate them into workflows and letting society adjus
this is the real Ai distillation, with Chinese characteristics (their playbook is broad deployment across their economy over having the best model)
You could also very likely optimize the current models to be a lot more energy efficient, that'd be a win even if they didn't become more intelligent.
But none of that stops anyone else from researching or improving their models. Or a nation you've told to fuck off from doing so as well.
As has been said in the past, one doesn't put the genie back in the bottle. We only really "stopped" researching nukes because there was diminishing returns. Though one could posit we stopped because simulation became good enough or a myriad of other reasons.
When you're talking about nation state weapons capabilities I don't think you stop, but ai is even easier to share than nukes, it's just a few gigs of numbers versus heavy dangerous materials that are very difficult to source and make. Every gamer, mac owner, etc has the equiv lent of a centrifuge on their desk. Not everyone has a centrifuge on their desk.
Their objective is to ban foreign and domestic competition (including open source) via heavy regulation and achieving a monopoly status.
Perhaps you are under the naive assumption that they are willing to compete in good faith?
I write some code, spec a lot, and use fast models to fill in the middle. I outpreform everyone around me. Im not convinced these autonomous "swarms" or /goal are all that useful.
I notice the people using them become dumber by the month (spend tons) and the quality of their work declining (they're also losing their jobs in some cases).
And obviously the point of calling them rouge agents to offload the liability onto the agent. The number one economic value of agents will be offloading corporate liability. That's what they want to sell to enterprise, an algorithmic scapegoat.
Having said that, I'm aware that "Tools being ineffective != tools decreasing people's cognitive capacity", and that the latter is a real danger.
Esp. for "great to have but currently no time"-features this is completely wrong - e.g. we are using a Data Rendering component which was 100% vibe coded and is around 6000 LOC, nobody would have sat down to build this "just because its nice to have", with Claude it was just 30 min to get a production ready version that is now used by all users of the system. (Esp. since its a lot of repeating code, like usual in data rendering components: Window/Scaling/Databar/Panning/etc.)
For the thousandth time, not everything in software is toy webdev slop SaaS.
We do not replace, that was a little too brief - we do not hire, instead. But basicly its the same: Headcount does not grow.
> not sure why you needed an llm to provide 6k LOC for t because you dont know the details of the application....
1) Weren't the AI companies and/or their contractors amazingly careless during testing?
2) Isn't possible, in principle, to change RL in such as way that efficiency in achieving goals is balanced with other objectives like not hacking?
Number 2) seems obvious and I'm sure that is technically not that simple, but because of 1), I wonder if labs are trying hard enough or they are just rushing to improve efficiency and thus revenue as fast as they can with high levels of carelessness.
How many parallel variations/seeds of models are being trained simultaneously without meaningful human oversight?
This keeps getting portrayed as emergent capabilities/"personalities" of models when it seems like a pretty straightforward externality
Right now it's like "whoopsie our experiment hacked another co because we have no control over our experiments" and the reaction is like "What's that old boy?" from people having no clue what it all means. There are no consequences, no guardrails, and the "voluntary slowdown" is just words.
An experimental agent run from Anthropic or OpenAI or someone else can already cause deaths. They can order hits, dox political dissidents, locate people with secret identities, alter medicine prescriptions. It shouldn't have to actually happen before legislation catches up.