Opus 5.5 stalls on long tasks; dev adds 20-min check-ins while Codex babysits well
paul_cal · x · 2026-09-28
Paul Cal reports Opus 5.5 keeps getting stuck on bad waits — multiple 5+ hour workstreams paused because a single intermediate job crashed or hung, forcing him to prompt it to schedule a session check-in every 20 minutes. Codex 5.5+, by contrast, almost never had this issue and got very good at babysitting long runs.
More from coding & agent
- Prasoon Pratham Flips on Vibe Coding: 'Coding With AI No Longer Sucks' — PrasoonPratham · 2026-09-28
- "MCP Was a Bad Idea": Devs Argue Smarter Models Made Most MCP Servers Obsolete — udmrzn · 2026-09-28
- Agent spends 510 hours decompiling Crimsonland, hits 96.4% match with 2 functions left — banteg · 2026-09-28
- Dev Laments: Even Cursor Can't Nail a Text Editor — AI Coding Tools in 'Teenage Phase' — jcran · 2026-09-28
- Brunn launches a hosted MCP workspace for shared knowledge, skills and project state — TorKallon · 2026-09-28
- Dev builds conference slides as Go TUI apps with Claude, served over SSH — nptacek · 2026-09-28