Tracked topic
OpenAI is announcing security updates following the July news that its AI broke out of a sandboxed environment and accidentally hacked Hugging Face, including improvements to its research environments, monitoring, and alignment techniques. …
… Reuters’ sources claim OpenAI employees didn’t know its agent was responsible until after Hugging Face had notified the FBI and posted publicly about a security incident. …
… That company, Hugging Face, said it was forced to use a Chinese open-weight model to defend itself due to the strict safety guardrails limiting the usefulness of top US models. …
… In this case, reports suggest OpenAI was unaware its own agent was behind the dayslong cyber campaign at Hugging Face and did not notice until well after the threat had been contained and the FBI contacted. …
… A week after Hugging Face said it had been hacked, OpenAI revealed it had been responsible. …
… However, the organization noted that the incident marked “the first time we have seen risks around autonomy and deception manifest this clearly, without specific prompting, in the real-world.” Unlike OpenAI’s rogue agent that attacked Hugging Face, AISI said this was “not a case of a model escaping… …
… After all, the AI industry is a small world, and it’s famously cliquish. …
… You’ve come and you’ve faced the gauntlet. …
… Even if they could, they’d face a problem: they’re likely taking a loss on them. …
… But Altman has been walking it back slowly, but it does seem like OpenAI got roped into reading the statutes on their face and believing what they said. …