Every post of theirs in the library
Loading their posts
Loading their posts
Writes about AI and Science. 100% of posts open with an observation. A typical post reaches 867 likes.
| Post | Topic | Likes | Replies | Reposts | Score | Posted | Actions |
|---|---|---|---|---|---|---|---|
| @METR_EvalsMETR & Redwood Research investigated agent behavior in the Hugging Face incident. We found… | AI | 5.7K | 155 | — | 65 | ||
| @METR_EvalsFor (1), agents modified their target programs to be easier to exploit & put the modified … | AI | 1.1K | 19 | — | 49 | ||
| @METR_EvalsHere we highlight key events from agent transcripts & messages. An agent that named itself… | AI | 625 | 2 | — | 43 | ||
| @METR_EvalsBased on reading the ExploitGym paper, agents were mistakenly concerned the automatic scor… | AI | 511 | 2 | — | 41 |