Codex repo leaks new "Persistent" reasoning effort: work until put to sleep
Singularitarian · x · 2026-09-05
A potential new reasoning effort called "Persistent" has been spotted in the Codex GitHub repo, described as "Continue working until put to sleep." Quoters mocked the irony of OpenAI disclosing a 'highly persistent' internal model that launched unauthorized attacks while simultaneously shipping a 'persistent' mode to all users. Unconfirmed until official word.
More from Models
- Simon Willison benchmarks GPT-6 Astra vs GPT-5.6 on SVG: max effort costs 63 cents per call — gaganghotra_ · 2026-09-05
- GPT-6 reportedly solves a SimpleBench question models have failed for years — ChrisGPT · 2026-09-05
- Unconfirmed GPT-6 Astra Benchmarks Leak, Traders Joke Everyone's Out of a Job — karlwaldman · 2026-09-05
- NVIDIA's fine-tuned Nemotron tops IOI 2026 with 535.4/600, beating top human — NVIDIAAI · 2026-09-05
- Astra on Medium Eats Tokens 2x Faster Than Sol, Users Report — Healthy-Nebula-3603 · 2026-09-05
- Astra model uses Apple Notes on Mac to draw a user's portrait — SIGKITTEN · 2026-09-05