Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
RCEpic

wuyoscar/Internal-Safety-Collapse

[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.

Owner
wuyoscar (personal account)
Stars
Stars: 2,599
Forks
Forks: 414
Language
Python
License
None
Created
2026
Tier
RC (2,000 to 4,999 ★) What this tier means
View on GitHub

More repos by wuyoscar

All 4 repos by wuyoscar

Nearby in Python

All Python repos