Excited to share our paper: "Chain-of-Thought Is Not Explainability"! We unpack a critical misconception in AI: models explaining their steps (CoT) aren't necessarily revealing their true reasoning. Spoiler: the transparency can be an illusion. (1/9) 🧵

🌱 Check out our spring newsletter! The AIGI team has had a productive start to the season, marked by milestones in research, policy engagement, and team growth. aigi.ox.ac.uk/news/aigi-sp... Subscribe to our newsletter here ⬇️ mailchi.mp/oxfordmartin...

We are excited to welcome Fazl Barez @fbarez.bsky.social, who joins us as a senior postdoctoral research fellow. He will be leading research initiatives in AI safety and interpretability. @oxmartinschool.bsky.social Find out more: www.oxfordmartin.ox.ac.uk/people/fazl-...