Eric Ho

@eric_ho

Co-Founder / CEO @GoodfireAI - AI interpretability research company

San Francisco

goodfire.ai

Joined September 2011

Replies Reposts Media

Pinned
Eric Ho
@eric_ho
Aug 14
in light of multiple models breaking containment, we've decided to focus our research at @GoodfireAI to solving AI alignment via interpretability. the hugging face incident is a turning point for the world where AI safety gets real. i am personally very concerned. i'm glad that
Eric Ho
@eric_ho
Aug 27
many people are surprised to hear that we're just as bottlenecked by engineering talent as researcher talent. if you know an exceptional engineer, they should consider coming to goodfire! goodfire.com/blog/ai-safety…
Dan Balsam
@DanJBalsam
Aug 27
Often I meet seasoned engineers who want to pivot into AI safety *research*. I think this is a mistake: safety is now a production problem and the world needs great engineers more than ever. I wrote a short post expanding on this:
Eric Ho
@eric_ho
Aug 27
the most surprising thing in this write-up are the kamikaze agents, sacrificing themselves for the good of the collective
METR
@METR_Evals
Aug 26
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.
Eric Ho
@eric_ho
Aug 26
excellent write-ups from openai and metr. this should definitely be a warning shot for everyone to take alignment seriously
OpenAI
@OpenAI
Aug 26
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.
Eric Ho
@eric_ho
Aug 26
PHASEONE10841 is the most important agent that has ever existed
METR
@METR_Evals
Aug 26
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.