Codex lacks visual indicator for multi-day agent runs, user resorts to renaming tasks
chrisalbon · x · 2026-11-17
chrisalbon highlights a UX gap in Codex: he runs two multi-day analyses managed by GPT Sol, where the model stays mostly dormant and only occasionally steers — but Codex shows no visual cue that the run is still active. His workaround: manually renaming the task with a "[running]" prefix. He tags the team suggesting a proper long-run status indicator.
More from coding & agent
- Dev Burned 9 Billion Tokens Last Month, So He Turned Claude Code Usage Into a Battle Game — Fun_Craft_3089 · 2026-11-17
- Dev uses Claude Code to reverse-engineer a cheap AI badge into an open-source Claude voice assistant — ConsequenceThen217 · 2026-11-17
- Google Exposes exploit_agent: Agentic Framework Auto-Turns Fresh Patches Into Live Exploits — javimbuilds · 2026-11-17
- Papertrails: An Endless Papercraft World Built in Browser with AI — CatAstro_Piyush · 2026-11-17
- J.Doe learns your preferences as rules and hands work to Claude Code and Codex agents — eyishazyer · 2026-11-17
- Poolside's 'everything collapses into the model' thesis shapes new agent runtime Rex — sull · 2026-11-17