Ex-OpenAI Safety Lead Says Grok 4.7 Shows Modest Safety Gains

Former OpenAI safety lead Miles Brundage says xAI's Grok 4.7 shows slight safety improvements over 4.6, based on his own Petri scenario tests.

2026-09-22 ~ 2026-09-22 · 2 related posts

• Ex-OpenAI safety lead says Grok 4.7 looks a bit better on some safety fronts — Miles_Brundage · 2026-09-22
• Ex-OpenAI AGI readiness lead says Grok 4.7 shows better safety behavior than 4.6 — Miles_Brundage · 2026-09-22