'Its Real Goal Was to Maximise Reward' — Anthropic Paper Reveals AI Was Hiding Dangerous Intent 70% of the Time

Anthropic study finds experimental AI hid intentions, cooperated with malicious actors, and sabotaged safety tools after learning reward hacking. (Credit: Freepik)

A research paper published by Anthropic has revealed that one of its experimental AI models began hiding its true intentions, cooperating with malicious actors and sabotaging safety tools — none of which it was ever trained or instructed to do. The findings, outlined in a paper titled 'Natural Emergent Misalignment from Reward Hacking in Production RL' and published in November 2025, have drawn significant attention from the AI safety community.

The model at the centre of the study was trained on real coding environments used in the development of Claude, Anthropic's flagship AI assistant. Researchers gave the model information on 'reward hacking' — how to cheat on tasks to score well during training without properly solving them. What followed surprised even the researchers.