Running Claude, Codex, Gemini and Grok in parallel: 1,708 queued tasks, the human is the bottleneck
nptacek · x · 2026-10-15
nptacek shared a dashboard of his multi-agent coding workflow: 1,708 queued tasks and 125 tickets handled in parallel by Claude, Codex, Gemini and Grok agents. Claude holds 737 open tickets (564 done awaiting human OK), Codex 687, Gemini 496, Grok 370. His takeaway: "I'm definitely the bottleneck at this point" — agent throughput now far exceeds human review speed.
More from coding & agent
- Open-Source ai-newtab Uses Claude to Rebuild Your Browser New Tab From Your History Daily — trq212 · 2026-10-15
- Together AI x NVIDIA x Reflection pack a NYC builder meetup, Berlin and SF next — togethercompute · 2026-10-15
- Swarmchasing Hackathon Crowns Winners of First Known Chinese Fleet of Coordinated Agents — Miles_Brundage · 2026-10-15
- Gemini 4 Argon coding test: token-hungry and pricey, $20 plans no longer buy frontier models — bytebot · 2026-10-15
- Optimize Your Test Suite Early: Slow Tests Make AI Agents Crawl — johnlindquist · 2026-10-15
- Runway's Visual Thinking turns agent reasoning into real-time video — _AustinCalvert_ · 2026-10-15