OpenAI Codex Shell execution latency regressed 8-11x on Windows
maikolb · ghdev · 2026-09-01
A user reported a severe performance regression in OpenAI Codex CLI on Windows, with shell command execution latency increasing from 1.7s to 18.4s (median) between versions 0.146.0 and 0.151.0-alpha. The issue spans 10 months of rollout data. Doctor reports indicate a sandbox provisioning failure where the system forces an elevated backend despite the user's configuration, leading to the latency spike.
More from Apps
- Apple Music's lack of AI features draws user criticism: no recommendations, no hum-to-playlist — ethanniser · 2026-09-03
- tldraw launches Flash: animate hand-drawn ideas by drawing and dragging on canvas — Vjeux · 2026-09-03
- Stripe launches Directory preview to help AI agents find and use external providers — jeff_weinstein · 2026-09-03
- Matt Shumer explains Fable's architecture: locked world structure lets versions share one world — mattshumer_ · 2026-09-03
- FastH3 opens API access: faster-than-realtime 720p streaming video with synced audio, surprisingly cheap — boudaboy · 2026-09-03
- Dean Ball pitches a Signal 'call this person later' button that builds a daily call sheet — deanwball · 2026-09-03