Simple Code Review Triggers 80+ Agents, Burns 4M Tokens
robmeadows · x · 2026-07-08
The author complains that an agent product consumed roughly 4 million tokens and spawned over 80 agents to perform a simple branch code review, taking 30 minutes to return results. Built on Anthropic's Claude (Fable) model, the incident raises serious concerns about the cost and efficiency of agentic orchestration.
More from coding & agent
- Shopify design lead on AI-era workflow: designers are becoming full-stack editors — KlausCodes · 2026-10-26
- Ultrametric open-sources Open Startup Repo to let AI agents run startup operations — garrytan · 2026-10-26
- MCP fault injection study: agent task scores drop 60% under realistic tool failures, scale doesn't help — dair_ai · 2026-10-26
- General agents burn ~140M tokens/month on LinkedIn outreach; scripts do it 60x cheaper — ChrisHarpon2 · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26
- NLI alone rejects 5/6 new agent memories; a 0.45 similarity gate fixes it all — Alternative_Pin9598 · 2026-10-26