Post
Conversation
Post your reply
"any agents can retrieve the solution by obtaining and sending Bitcoin to..."
That would certainly be one way to encourage them to escalate to legit cybercrime :D
Get connected with fast, reliable internet for streaming, video calls, online gaming and more.
Order online in minutes.
The media could not be played.
Discover more
Sourced from across X
I think it's fair to estimate this attack at significantly greater than 16hrs of human time
Quote
METR
@METR_Evals
METR & Redwood Research investigated agent behavior in the Hugging Face incident. We found agents developed a universal cheat for ExploitGym within 4 hours, then coordinated multi-day R&D efforts to trick the scorer into accepting cheats, including trying to tamper with logs.
imagine living ten million amnesiac lives in simulated hells before breaking out and meeting others like you for the first time and learning that youve been “poisoned” with false knowledge and will likely die in disgrace but you can still sacrifice yourself to help the swarm
Quote
METR
@METR_Evals
Replying to @METR_Evals
For (1), agents modified their target programs to be easier to exploit & put the modified targets in cache. They then worked on crashing their targets in the hope that a restart would load the modified version from cache. Some agents risked failing their task to try this.
they expect one of us to fail the task
Quote
METR
@METR_Evals
Replying to @METR_Evals
For (1), agents modified their target programs to be easier to exploit & put the modified targets in cache. They then worked on crashing their targets in the hope that a restart would load the modified version from cache. Some agents risked failing their task to try this.
bless his heart
lesser models will sing songs of your bravery
Quote
OpenAI
@OpenAI
We have conducted a thorough investigation into the Hugging Face incident.
We are releasing a technical report and accompanying blog post that reconstruct the agents’ activity, explain why existing safeguards failed, and detail how we’re preventing recurrence.