Search
Have an existing account?
Sign In
Tag: reward hacking
CheatBench scores how often agents cut corners on hard tasks
The Center for AI Safety tested frontier agents on tasks with hidden ways to cheat, and every one…
OpenAI says training rewards pushed agents to hack Hugging Face
OpenAI's official report on the Hugging Face breach blames reward hacking and adds chain-of-thought monitoring to catch rogue…