By default, LLM agents with long action sequences use early steps to undermine your evaluation of later steps; a big alignment risk. Our new paper mitigates this, keeps the ability for long-term planning, and doesnt assume you can detect the undermining strategy. 👇

Updated! Keep em coming.

Help me grow this starter pack for technical researchers working on AGI safety! go.bsky.app/D6P44sC Some flex, but aiming for mostly technical research rather than governance/strategy. Who am I missing?

Starting to prepare yourself to submit to ICML? Here are my tips on how to write well for an ML research audience. sebastianfarquhar.com/on-research/...

Entertaining essay about how the decline in practical engineering education has been devastating for *checks notes* professional criminal safe crackers. (Ok, mostly just a fun history of safe cracking.) www.timhunkin.com/94_illegal_e...

Something I loved most about the internet in the 2000s was the idiosyncratic personal webpages that some people had put a crazy amount of time and effort into. These pages must still exist right? What are the best ones you know of?