Sign in

Davis Brown

@davisbrown.bsky.social
32 followers 72 following 0 posts

Research in science of {deep learning, AI security, safety}. PhD student at UPenn davisrbrown.com

PostsRepliesMedia
Reposted by Davis Brown
adamlsteinl.bsky.social @adamlsteinl.bsky.social · 10/04/2026
We found widespread cheating on popular agent benchmarks, affecting 28+ submissions across 9 benchmarks and thousands of agent runs. Surprisingly, the top 3 submissions on Terminal-Bench 2 are all cheating! Here's what we found 🧵
121