Steve Yegge: only Claude Fable is worth a damn, and it's too expensive — orchestrators won't work for a year
Steve_Yegge · x · 2026-09-16
Steve Yegge's new essay Seats and Sunsets centers on the "fuel apocalypse" — token consumption — in agent orchestration:
- Fuel apocalypse: He argues Claude Fable 5 is broadly the only model in the industry worth trusting as an AI employee — and even it fails at roughly half the job (no self-pacing, spams colleagues with long emails). Weaker models like the Astras and Opus 5s are fine as personal assistants or for single coding tasks, but running a real-world factory needs Fable-tier intelligence in at least some roles, or it eats itself.
- Too expensive to work: Fable is the only good model, but its cost means nobody's orchestrators work today — including his own.
- No relief for a year: he bluntly predicts the situation won't improve for another year.
- He also details Wheelhouse, the more mature successor to Gas Town (both Beads machines) he built for his video game Wyvern, and floats turning his agent/orchestrator writing into a weekly newsletter.
Essential reading on agent engineering economics: the tradeoff between model capability and token cost.
More from coding & agent
- Agent Flywheel guide: exhaustive markdown plans, beads tasks and agent swarms to cut token waste — doodlestein · 2026-09-16
- A tiered approach to token budgeting when developing with agent swarms — doodlestein · 2026-09-16
- Doctor builds WebMCP-enabled DICOM viewer so Codex can read scans and write reports — iamrobotbear · 2026-09-16
- Designer's bet: the agent with the best computer-use model will be the 10x unlock — _AustinCalvert_ · 2026-09-16
- Meta's Muse agent security blueprint: freedom to act, not to rewrite permissions — TheTuringPost · 2026-09-16
- Zero Agent Trained on Synthetic Data From a Simulated World of Talking Characters — generativist · 2026-09-16