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.

by Oscar (Yutao) Wu Python Other licence 428 forks Created Mar 2026 View on GitHub

Stars: 2,618; 23% of wuyoscar's stars
Rank: #26,062; of 851,984 repos, top 4%
In Python: #4,689; of 173,300 repos, top 3%

Among 851,984 repos

All repos Python

2.5k–4k stars: 10,616 repos, including Internal-Safety-Collapse

top 50%top 10%top 1%top 0.1%

Stars along the bottom, and repos in each band on a log scale

Quick stats

Next rank: +1 star to reach #26,051
Next milestone: +4,602 stars to reach the top 1%
Popular: One of 66,569 repos with 1k+ stars