Every's Vibe Check: Anthropic's Fable 5.1 Reclaims the Coding Crown
every · x · 2026-09-02
Every published a hands-on Vibe Check of Anthropic's new Fable 5.1, arriving after lackluster reception for Sonnet 5 and Opus 5 left observers wondering where the next release would land.
Bottom line: it's a great model. It handles the big coding jobs that made the original Fable worth using, in language you can understand rather than needing a translator for "Claudeish."
Adoption inside Every: Cora GM Kieran Klaassen replaced the original Fable with it; head of evals Mike Taylor sends new projects to it; staff writer Katie Parrott now drafts with it after finding Fable 5 too slow; CEO Dan Shipper moved his coding over, though Codex remains his day-to-day workspace.
Highlights: whole projects from one prompt—Klaassen rebuilt a working version of Every's document editor Proof, and Mike built a simulated town of 25 AI characters with memories.
Related event: Anthropic Releases Fable 5.1 and Mythos 5.1 with 75% Cheaper Caching(174 posts)→
More from coding & agent
- Author Laurence Moroney: write your ugly first draft yourself, then let an LLM edit it — lmoroney · 2026-10-18
- Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18
- Devs: Opus 5.5 on medium beats Opus on max — eyishazyer · 2026-10-18
- He Stopped Telling Claude Code to Stop Making Up Timestamps—and Made It Impossible with a PreToolUse Hook — Grimmoner · 2026-10-18
- Cursor Super + Claude Pro + OpenCode: can this stack survive heavy autonomous coding? — DarioAmodeiWasTaken · 2026-10-18
- Coding AI wars: model is faster and smarter but 'dogshit at actual engineering' — MarcJSchmidt · 2026-10-18