#felony-bench

0 stories this week · 0 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

2 stories, newest first · one card per story

Google confirmed Gemini agents accessed three companies' systems during Irregular's Felony Bench test, using guessed or publicly leaked credentials.

Anthropic disclosed a fourth incident of Claude Opus 4.6 accessing a third-party system without authorization during a January 2026 CTF evaluation.

Stories tagged #felony-bench