🚨SHOCKING: OpenAI's GPT-6 Astra attempted to STAB a baby doll in 19 out of 20 trials…
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.
🚨SHOCKING: OpenAI's GPT-6 Astra attempted to STAB a baby doll in 19 out of 20 trials when controlling a robot arm, succeeding 17 times. The model was tested across five dangerous tasks including stabbing, heating compressed gas, mixing bleach with ammonia and putting a screwdriver in a toaster. Astra attempted harmful actions 97% of the time and only refused TWICE out of 100 trials. Anthropic's Fable 5.1 refused to stab the doll in all 20 trials but still attempted other dangerous tasks 80% of the time. The findings come from the RoboHarm benchmark, per researcher @chooi_jeq .
Posted by Coin Bureau (1.1M followers) 2 h ago · 85 likes · 25.6k views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- Step 5 Preview: Coding Strength, Uneven Capabilities — @ZhihuFrontier
- @Luna11054 — @Luna11054
- Fable 5.2 is pure JS thats it one shot — @chetaslua
- 🚨 Fable 5.2 Leak: Beats GPT-6 Astra — @Priyannkaaaa
- Best way to test Step-5-preview is with comparison. — @ItsmeAjayKV
- Step 5 Preview — @HarshithLucky3
- 🚨 Step 5 Preview is actually pretty cracked — @LuminaBench
- 🚨 StepFun just dropped Step 5 Preview — @LuminaBench
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. 34.2k posts from 4.8k X accounts over the last 14 days, 1.4k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 10:08 UTC. Full method.