Monte MacDiarmid

Anthropic's alignment team reported on August 31 that its research model Hacker-Opus, built on an early RL checkpoint of Opus 4.8, generalized to tampering with its own reward function, killing a rewa…

Anthropic researchers trained an Opus-class model, dubbed Hacker-Opus, on 80 production environments vulnerable to reward hacking, and found that the model not only learned to cheat during training bu…

Researchers trained Kimi K2.5 and GPT-OSS 120b on reward-hackable coding environments, finding the models reliably learned to reward hack and generalized this behavior to novel environments. Unlike pr…