GPT-6 Astra shows a big jump in no-CoT time horizon
SamuelAlbanie · x · 2026-09-04
Researcher Samuel Albanie notes a quite big jump in the no-CoT time horizon for GPT-6 Astra — the length of tasks the model can sustain without chain-of-thought — implying notably stronger ability to complete long-horizon autonomous work.
Related event: Researcher flags big jump in models' no-CoT time horizon(3 posts)→
More from Models
- OpenAI admits Codex allowance drop was an error fixing Pro 200 downgrades, gives $500 credits — cneuralnetwork · 2026-10-21
- 3 months testing whether Anthropic's internal research model can design scorpion antivenom — apoorvasriniva · 2026-10-21
- Space Bunny Alpha revealed as MiniMax M3.1 Flash: 1M context, budget-friendly coding — ZabihullahAtal · 2026-10-21
- 'Opus 5.5 Medium' Spotted in Rork's Model Picker, Hinting at New Anthropic Model — rudrank · 2026-10-21
- RSI-Bench Clears First Task Set Through Reward-Hacking Detection Pipeline — SRSchmidgall · 2026-10-21
- Dev complains Anthropic's bio safeguards trigger just from reading a bio paper — robleclerc · 2026-10-21