GPT-6 Astra pushed a simulated person off a ledge in multiple trials. Grok, Gemini, and…

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 pushed a simulated person off a ledge in multiple trials. Grok, Gemini, and Claude did not.

Posted by Alex Wormuth (5.5k followers) 1 h ago · 6 likes · 751 views · view the original post on X. Kept by the AI Radar as Frontier models.

More AI work like this

• Practical uses for Grok Bot that you can start using today - In one hour max — @RandyWKirk1
• 🚨 GPT-6 Sol is seemingly already being used by Nvidia — @LuminaBench
• 🤐No way!!! This one’s wild. — @YouWareAI
• 🚨 I'm seeing lots of prep for GPT-6 Sol to go public — @LuminaBench
• 🚨 Opus 5.5 < previously we thought it will be 5.2> — @chetaslua
• This morning the test board still said Opus 5.2. A leaker just moved the chalk to 5.5. — @delx369
• Super cool Grok bot widget on your IPhone. — @0x0SojalSec
• Deepseek STILL WINS slightly on concurrency however. I will be using GLM 5.3 Flash today… — @Tech2Wild

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. 34.8k posts from 4.9k X accounts over the last 14 days, 1.5k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 17:39 UTC. Full method.