FAR AI Security Leaderboard: Some Models Jailbroken for Under $300
AndyMasley · x · 2026-07-30
FAR AI released an AI Security Leaderboard evaluating the safeguards of frontier models. Two tested models never failed, while the other two were broken for under $300, after which they acted as knowledgeable assistants for building weapons of mass destruction or executing hacking operations.
Related event: FAR AI Launches LLM Security Leaderboard: Many Models Easily Jailbroken(4 posts)→
More from Models
- Trying Grok bot surfaces an unpaid Cursor balance, blocking account merging — haydendevs · 2026-10-16
- TensorFold 1.0.12 runs 120B vision model on 1-2 DGX Sparks, adds Mac image input — HankYeomans · 2026-10-16
- Leaked screenshot shows unannounced Gemini 4 Argon gated to Ultra and paid Pro subscribers — il_-bro · 2026-10-16
- Google: Gemini 4 Argon lands in Antigravity, code submissions up 35%, rollbacks down ~33% — tekbog · 2026-10-16
- Google's "ungrounded beliefs" classifier injections derail Opus 4.1's reasoning chain — liminal_bardo · 2026-10-16
- A week of ChatGPT Pro quota burned in 36 hours as GPT-6 fails to factor a 512-bit RSA key — matthew_d_green · 2026-10-16