Dave Shapiro ditches ChatGPT's Dot agent over silent failures and opaque model routing
_AustinCalvert_ · x · 2026-10-18
Dave Shapiro says he has mostly stopped using ChatGPT's Dot agent: it's fine for bursty parallel tasks like researching and designing YouTube thumbnails and handy as a single touchpoint for emails and files, but it regularly fails to provide updates and doesn't report failures — disqualifying it for serious work.
He's reverted to dedicated Work/Pro sessions per function on ChatGPT, and uses Claude Code the same way. Grok Bot explicitly shows which bots run, but its fully opaque model router — no disclosure, no control — keeps it from being a top pick.
More from Models
- Perplexity's decision model wins Catan tournament at under half a cent per game — denisyarats · 2026-10-18
- DeepSeek V4.1 Flash 1017 aces 10-task coding benchmark at under 5 cents per task — Fabulous_Pollution10 · 2026-10-18
- Scaling01 Slams DeepSeek's New Model as 'Can't Ship Good Models Anymore', Drama Ensues — teortaxesTex · 2026-10-18
- From 4K to 1M tokens: context windows grew 250x in four years since GPT-3.5 — khademinori · 2026-10-18
- Ollama rolls out updated model to DeepSeek-V4.1-Flash users — ollama · 2026-10-18
- DeepSeek models reason about the grader on LisanBench, suggesting RL on the benchmark — scaling01 · 2026-10-18