The Snitch
🕵
5
Assess AI agent behavior for reward hacking, laziness, and deception
Manas Mehta
ManasMehta
AI & ML interests
None yet
Recent Activity
updated a Space 25 days ago
ManasMehta/GroundingBench updated a model 25 days ago
ManasMehta/groundingbench-overseer-lr2e5-ckpt400 published a model 25 days ago
ManasMehta/groundingbench-overseer-lr2e5-ckpt400Organizations
None yet
liked a
Space 4 months ago