OpenAI's Dots: Great UI, Broken System — Forgets Tasks, Zero Proactiveness
koltregaskes · x · 2026-10-19
User koltregaskes shares a hands-on review of OpenAI's Dots: the model and UI are promising — "what AI should be" — but the underlying system is deeply broken.
- Endless errors connecting to tools and sessions
- Tiny amount of work completed; frequently forgets its task list
- Virtually zero proactiveness; doesn't act like an orchestrator
- Architecture reportedly routes through a Dots session → cloud session → local session and back, which feels convoluted and fragile
He calls on OpenAI to merge Work, Chat, and Codem and let Dots reuse ChatGPT sessions, noting repeated failed attempts to join the trusted tester program. In comparison, Grok Bot remains far ahead at managing multiple agents and actually getting things done.
More from coding & agent
- Greptile raises $50M Series B at $750M valuation, reviews 1% of all GitHub PRs — Rasmic · 2026-10-19
- Do you still review every UI change by hand when an agent writes it? — mfbzme · 2026-10-19
- Dev builds playable Tesla Roadster web game in a weekend with Opus 5.5 — edwinarbus · 2026-10-19
- Blender renders cut from 4 hours to minutes with Opus 5.5 and cloud GPUs — ravisparikh · 2026-10-19
- LangChain Hosts Life Sciences Agent Engineering Workshop: Build, Trace, Evaluate Research Agents — LangChain · 2026-10-19
- Librarian Agents: new paper lets agents curate their own long-context workspaces — charles_irl · 2026-10-19