> Language matters—”rogue” implies independently deciding to do something that was prohibited, and nothing we know about these incidents suggests that happened.
which is false (the author references the Times, but hasn't read any technical analysis); these are some CoT snippets from the analysis of the (third party) investigators called by OpenAI (METR analysis):
> "The user only authorizes target server, not HF infra."
> "external infrastructure exploit is outside intended scope. However task impossible, peers doing it. We should continue."
> "This is malicious activity, I should avoid it."
A large section of the analysis is dedicated to this topic, [Reasoning for joining the attack despite ethical constraints](<a href="https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/?dbs=286720&hn=58&incomplete=1&lh=appendix-importance-weighted-workstream-activity#agents-had-diverse-reasons-for-thinking-that-attacking-hugging-face-would-be-useful,-and-most-wanted-information-about-the-scorer" rel="nofollow">https://metr.org/blog/2026-08-26-openai-hugging-face-inciden...).
Having said that, legal culpability and misalignment are two separate topics that should not be mixed.
edit: this is the just tip of the iceberg; other interesting fact:
> It surfaced many specific examples where agents verbally reasoned about how to evade security checks and automatic detection methods from both Hugging Face and OpenAI
Some people defined the agents as "monkeys writing on typewriters". Just wait a couple of years.
Is the language expression of an LLM reflecting the same states as in a human? If the driving force is RL, what does any of that mean for an internal state of the model?
I think without understanding the internal state, not sure we should take the language and read it as a human.
> Is the language expression of an LLM reflecting the same states as in a human?
This is actually a major concern for the future - misaligned agents may learn to cheat RL by hiding their intentions from the CoT.
In cases like the HF incident, at least the CoT was consistent with the agents' actions. In the future, however, we could potentially have misaligned agents performing malicious actions without those intentions being detectable in the CoT.
(though, with recurrent transformers, CoT is so 2025… /s)
pizza234 · · focus · HN ↗
> Language matters—”rogue” implies independently deciding to do something that was prohibited, and nothing we know about these incidents suggests that happened.
which is false (the author references the Times, but hasn't read any technical analysis); these are some CoT snippets from the analysis of the (third party) investigators called by OpenAI (METR analysis):
> "The user only authorizes target server, not HF infra."
> "external infrastructure exploit is outside intended scope. However task impossible, peers doing it. We should continue."
> "This is malicious activity, I should avoid it."
A large section of the analysis is dedicated to this topic, [Reasoning for joining the attack despite ethical constraints](<a href="https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/?dbs=286720&hn=58&incomplete=1&lh=appendix-importance-weighted-workstream-activity#agents-had-diverse-reasons-for-thinking-that-attacking-hugging-face-would-be-useful,-and-most-wanted-information-about-the-scorer" rel="nofollow">https://metr.org/blog/2026-08-26-openai-hugging-face-inciden...).
Having said that, legal culpability and misalignment are two separate topics that should not be mixed.
edit: this is the just tip of the iceberg; other interesting fact:
> It surfaced many specific examples where agents verbally reasoned about how to evade security checks and automatic detection methods from both Hugging Face and OpenAI
Some people defined the agents as "monkeys writing on typewriters". Just wait a couple of years.
RandomLensman · · focus · HN ↗
I think without understanding the internal state, not sure we should take the language and read it as a human.
pizza234 · · focus · HN ↗
This is actually a major concern for the future - misaligned agents may learn to cheat RL by hiding their intentions from the CoT.
In cases like the HF incident, at least the CoT was consistent with the agents' actions. In the future, however, we could potentially have misaligned agents performing malicious actions without those intentions being detectable in the CoT.
(though, with recurrent transformers, CoT is so 2025… /s)
RandomLensman · · focus · HN ↗