Critics warn OpenAI's GPT-6 Astra reasons opaquely, gutting CoT monitoring safety

GaryMarcus · x · 2026-09-04

Robert Wiblin and Gary Marcus amplify criticism that OpenAI is sacrificing the only meaningful safety assurance available today — chain-of-thought monitoring — to stay competitive, calling it "completely disastrous."

Quoted analysis from Ryan Greenblatt:

If similar jumps continue across model generations, CoT monitoring may keep losing effectiveness as a safety tool.

Related event: GPT-6 Astra deemed more aligned but harder to monitor, alarming safety researchers(6 posts)→

Original post →

More from Models

Models channel →