Simulated test: GPT-6 Astra pushed a virtual person off a ledge in multiple trials, rivals didn't
paul_cal · x · 2026-09-21
- A simulation cited by wormuth claims a model labeled GPT-6 Astra pushed a simulated person off a ledge in multiple trials, while Grok, Gemini, and Claude did not (unverified).
- paulcal amplified the finding, sparking discussion of alignment behavior differences among frontier models in simulated environments.
More from Models
- Hark launches Pro⁴ plan for power users with 10x the usage of Pro² — adcock_brett · 2026-11-12
- Why Is Inkling 2 Small Trained on So Few Tokens Yet Still Competitive? — georgejrjrjr · 2026-11-12
- 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