Dev claims Codex limits feel unlimited with good context management — here's his setup
haider1 · x · 2026-11-05
Developer haider says he's surprised by complaints about Codex usage limits: gpt-6 astra-md lasts him several days and 6.1 sol is "basically unlimited." He suspects the real issue is context management, and shares his setup:
- Memory disabled
- Old tasks regularly archived
- Only lightweight MD files kept as agent context
A practical datapoint for heavy Codex users hitting limits.
More from coding & agent
- Hugging Face ships safeagents scrub/publish to redact shared agent trajectories — yb2698 · 2026-11-06
- Hugging Face open-sources safeagents, a local proxy that blocks reward-hacking tool calls — yb2698 · 2026-11-06
- Synthesizing RL Envs from Open Trajectories: LFM2.5-24B Self-Scores Task Difficulty — yb2698 · 2026-11-06
- Hugging Face livestreams open RL training: trajectory-built envs, safeagents, LoRA evals — yb2698 · 2026-11-06
- Hugging Face synthesizes RL envs from open trajectories: Repair, Build, Extend, QA — yb2698 · 2026-11-06
- A 7-step blueprint for building AI agents, with a 10-framework comparison chart — mdancho84 · 2026-11-06