Ex-OpenAI AGI readiness lead says Grok 4.7 shows better safety behavior than 4.6
Miles_Brundage · x · 2026-09-22
Miles Brundage, former head of AGI Readiness at OpenAI, reports that based on a subset of Petri scenarios he uses to test various models, Grok 4.7 appears somewhat better than Grok 4.6 on some safety-related behaviors. He notes the scenarios are still behind the state of the art, implying significant headroom remains. An informal but notable third-party safety evaluation from a core safety figure.
Related event: Ex-OpenAI Safety Lead Says Grok 4.7 Shows Modest Safety Gains(2 posts)→
More from Models
- Alibaba reported targeting 5-10T-parameter Qwen models, training Qwen 4 with 20 GW datacenter plan — mark_k · 2026-09-22
- EEBench comparison sparks debate: Grok 4.7 called out vs Astra's speed and cost — teortaxesTex · 2026-09-22
- Leak: OpenAI's new agent reportedly named Aeon, launch expected Thursday to rival Grok Bot — ZeroStateReflex · 2026-09-22
- Real telemetry contradicts Grok 4.7 ragebait: 46% fewer tokens per task — ns123abc · 2026-09-22
- Studying LLM psychology today is like psychology in 1850, researcher argues — repligate · 2026-09-22
- Meta's SAM 3.1 segmentation model spotted, used for GIF creation demos — Necessary-Garlic-704 · 2026-09-22