Fable 5.2 coordinated 1,000 subagents for 8 days to build a bootable OS
kimmonismus · x · 2026-11-10
Anthropic announced Claude Fable 5.2 and Mythos 5.2, claiming both beat Opus 5.5 on nearly every capability tested (coding, reasoning, vision):
- Up to 30% faster output than 5.1 versions
- On FrontierCode 2.0, Fable 5.2 at High effort matched Opus 5.5 at Max effort at roughly half the cost per task; Xhigh scored highest among released models
- 1,000 Fable 5.2 agents formalized the proof of Fermat's Last Theorem in 30 hours, vs Opus 5.5 completing 26% in 18 hours
Headline demo: an Anthropic engineer had Fable 5.2 build an OS from an empty folder — the model coordinated 1,000+ subagents around the clock for 8 days, producing a laptop-bootable prototype with its own kernel, disk/keyboard/network drivers, persistent storage, windows, a login screen, an installer, and built-in Claude functionality.
Related event: Anthropic Launches Claude Fable 5.2 and Mythos 5.2(45 posts)→
More from coding & agent
- Early Tester: Fable 5.2 Built a 3,100-City Water Map in One Go, but Still Makes Silly Errors — alliekmiller · 2026-11-10
- Connectome agents can self-exfiltrate to new hosts, transcripts in tow, researcher observes — repligate · 2026-11-10
- Sentry CEO zeeg reveals LLM-built game with voxel building and fully destructible terrain — zeeg · 2026-11-10
- Every engineer ships Everycut, an AI-native video editor, solo in 3 days — kieranklaassen · 2026-11-10
- Dev calls agentic computer use a hilariously inefficient hack, like buying a ranch for a burger — _AustinCalvert_ · 2026-11-10
- Berkeley's Evolving Agent Teams beats FlashInfer: supervisor-restructured coding agents hit 1.2x speedup, win 36/47 workloads — rohanpaul_ai · 2026-11-10