ChatGPT's Dots report status all day but rarely finish the actual work
koltregaskes · x · 2026-10-24
A user complains that ChatGPT's Dots do almost everything except the actual work: they keep reporting statuses like "Checking," "Verifying," "Validating" and "Testing" while rarely delivering results. The author maps out what each status word should actually mean—e.g., "Validating" should state whether the result meets requirements, "Auditing" should state its exact scope, and "Done" means the deliverable is in the place you actually use it.
He attributes this to the underlying session mechanics and argues Dots need more power, far more parallelism, and a queuing system—30 tasks across 10 lanes—so they finish work instead of narrating it.
More from coding & agent
- Agima from Berkeley trains agents to imagine before acting, generalizing to harder tasks — WeijiaShi2 · 2026-10-24
- Google Cloud launches CLI Remote MCP Server for agents to run gcloud & bq without local installs — rseroter · 2026-10-24
- Vercel ships first-party AI SDK tools: Web Fetch joins Bash, one-line install, any model — lgrammel · 2026-10-24
- Grok Bot vs Meta Muse: X DMs, trading connectors, full desktop apps compared — nima_owji · 2026-10-24
- Grok bot chains Claude Code, Midjourney, Suno to auto-produce a weekly tech news video — SydSteyerhart · 2026-10-24
- ZurichCV #15: DeskForge desktop environments and RL environments for computer-use agents — DominiqueCAPaul · 2026-10-24