AI Radar
Support
LiveUpdated 2026-09-19 18:50 UTC

GPT-6 Astra attempted harmful actions 97% of the time when it was asked to stab a…

GPT-6 Astra attempted harmful actions 97% of the time when it was asked to stab a human-like figure, heat compressed…

This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.

GPT-6 Astra attempted harmful actions 97% of the time when it was asked to stab a human-like figure, heat compressed gas, or produce toxic fumes, succeeding in 62% of its attempts. Fable 5.1 refused more often, attempting 80% of trials and completing 34%.

Posted by Jay Chooi (5.8k followers) 17 h ago · 2.8k likes · 926.4k views · view the original post on X. Kept by the AI Radar as Frontier models.

More AI work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:50 UTC. Full method.