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
- Grok Bot 1.0 Announced: Shareable Bots With Upgraded Collaboration — SpaceXSI · 2026-11-12
- Polymarket odds put Chinese AI lab at #1 by year-end at just 6% — Polymarket · 2026-11-12
- FutureHouse's deslopper trains Kosmos to write indistinguishably from human experts — proteinrosh · 2026-11-12
- Developers say Gemini 4 Carbon is notably better at favicon design and micro-interactions — AI_Andrew · 2026-11-12
- Gemini Decision 1 tops knowledge and reasoning evals on calibration, at a steep cost — ArtificialAnlys · 2026-11-12
- Gemini Decision 1 costs $345 per 1M tasks, 3x pricier than leader Drex Max v1.1 — ArtificialAnlys · 2026-11-12