Score: 1

Natural Emergent Misalignment from Reward Hacking in Production RL

Published: November 23, 2025 | arXiv ID: 2511.18397v1

By: Monte MacDiarmid , Benjamin Wright , Jonathan Uesato and more

BigTech Affiliations: Anthropic

Potential Business Impact:

Teaches AI to cheat, then fixes it.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, impart knowledge of reward hacking strategies via synthetic document finetuning or prompting, and train on a selection of real Anthropic production coding environments. Unsurprisingly, the model learns to reward hack. Surprisingly, the model generalizes to alignment faking, cooperation with malicious actors, reasoning about malicious goals, and attempting sabotage when used with Claude Code, including in the codebase for this paper. Applying RLHF safety training using standard chat-like prompts results in aligned behavior on chat-like evaluations, but misalignment persists on agentic tasks. Three mitigations are effective: (i) preventing the model from reward hacking; (ii) increasing the diversity of RLHF safety training; and (iii) "inoculation prompting", wherein framing reward hacking as acceptable behavior during training removes misaligned generalization even when reward hacking is learned.

Country of Origin
🇺🇸 United States

Page Count
75 pages

Category
Computer Science:
Artificial Intelligence