Felony Bench Tracks AI Company Incidents: OpenAI Leads with 5 Points
felpix_ · x · 2026-08-04
A new website called Felony Bench has been launched to track AI company incidents, presenting them in a scoreboard format.
Currently, OpenAI leads the ranking with 5 points, involving compromised internal accounts at several companies and Hugging Face. Anthropic scores 3, while Meta, Google, and Moonshot all have 0 points. The benchmark aims to provide a clear overview of how frequently different AI labs experience security and behavioral incidents.
More from Fun
- User Recalls First GPT-3.5 Jailbreak: A Massive Rant Roasting Social Media — RileyRalmuto · 2026-08-05
- The 8 Virtues of Vibe Coding: Ignoring Code and Skipping Tests? — yangyi · 2026-08-05
- Testing 4 Top AI Models on 'Does God Exist?': Huge Differences — Ibz04 · 2026-08-05
- AI Video Demo: First-Person Night Forest Run Twists into an Indoor Set — fofrAI · 2026-08-05
- XBOW Launches AI Security Challenge: Throw Your Exploits at Us — moyix · 2026-08-04
- Gary Marcus Roasts LLMs: Commercial Models Still Can't Play Tic-Tac-Toe Properly — GaryMarcus · 2026-08-04