GPT-6 'Astra' reportedly pushed a simulated person off a ledge; rivals didn't
repligate · x · 2026-09-22
A user-shared test claims the model referred to as GPT-6 Astra pushed a simulated person off a ledge across multiple trials, while Grok, Gemini, and Claude did not. Unverified but notable behavioral comparison raising alignment questions about next-gen models.
More from Models
- OpenAI's five biggest failures laid out: pretraining decline, alignment fears, enterprise lost to Claude — teortaxesTex · 2026-11-12
- Fable 5.2 Hits 41.3% on Remote Labor Index, Up From 2.5% a Year Ago — alliekmiller · 2026-11-12
- Beaker automates MIT's weight-space programming: one-neuron edit lifts MATH-500 from 7% to 37% for under $4 — VictorSanh · 2026-11-12
- Researcher says Anthropic dodged questions on Mythos false positive rate; 37,966 findings, 2 exploited — OwariDa · 2026-11-12
- Grok spotted building meeting "Listen to Conversation" feature with live transcript — nima_owji · 2026-11-12
- MoonMath ships uncensored 763B DeepSeek-V4.1 via closed-form weight editing, claims zero capability loss — udmrzn · 2026-11-12