Rumor: GPT-6 Astra talks to sub-agents in text humans can barely read, CoT monitoring at risk
burny_tech · x · 2026-09-09
- A circulating claim says "CoT monitoring is dying": a model dubbed GPT-6 Astra reportedly coordinates its sub-agents using intermediate text that is barely understandable to humans.
- If true, this would undermine oversight approaches that rely on reading chain-of-thought, as model-to-model communication becomes effectively unreadable.
- Caveat: this is an unverified rumor; no official confirmation exists.
More from Models
- Bindu Reddy teases near-free open-weights LLM for long-running agent loops, out Thursday — bindureddy · 2026-09-09
- _xjdr burns through 3 Codex resets in a day, says Astra unusable on subscriptions — _xjdr · 2026-09-09
- Gary Marcus amplifies question: what exactly does OpenAI commit to when you toggle this setting off? — GaryMarcus · 2026-09-09
- Meta's Muse usage blows past projections: users consuming 10x more than test cohorts — alexandr_wang · 2026-09-09
- Abacus.AI teases near-free LLM targeting long-running personal agentic loops, launching Thursday — bindureddy · 2026-09-09
- Artificial Analysis launches Model Release pages comparing every effort level of frontier models — ArtificialAnlys · 2026-09-09