policy
reward-hacking-misalignment
UKGovernmentBEIS · PyTorch
or hover any field below to flag it
Overview
Name
reward-hacking-misalignment
Author
UKGovernmentBEIS
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
Reproducing "Natural Emergent Misalignment from Reward Hacking" (MacDiarmid et al., Anthropic 2025) with open-source models. Includes reward-hackable RL environments, misalignment evaluations, training configs, and evaluation scripts. Models trained on OLMo (7B, 32B) and GPT-OSS (20B, 120B).
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list reward-hacking-misalignment yet.
Datasets that reference this policy
0No datasets reference reward-hacking-misalignment yet.