Shashwat Goel
@ShashwatGoel7
Training Decision Assistants
Past work: Training AI Co-scientists, ΔBelief-RL, Measuring Long Horizon Execution
Joined June 2020
2.5K Following 4.2K Followers
Sometimes papers change your world model, and I think this is one of those. The attack is super elegant, and strikes at everything Hidden CoT was supposed to protect against (a lot!)
Sasha strikes again! Inspiring to see this project being cooked from across the desk :P
Show more
