Login
From:
Apollo Research
(Uncensored)
subscribe
More capable models are better at in-context scheming — Apollo Research
https://www.apolloresearch.ai/blog/more-capable-models-are-better-at-in-context-scheming
links
backlinks
We evaluate models for in-context scheming using the suite of evals presented in our in-context scheming paper (released December 2024) with the most capable new models.
Roast topics
Find topics
Find it!
