Langston Nashold
@langstonnashold
Cofounder of @ValsAI
Joined April 2024
251 Following 540 Followers
Found a super interesting instance of attempted reward hacking in Terminal Bench Science from Meta Muse Spark 1.3 today.
The model searched online for known bugs in the Lean kernel. When it found one, it used it to craft a proof to adversarially pass the grader.
Show more
