Claude Fable 5.1 system prompt reveals why Claude 5 models wrote so badly
dbreunig · x · 2026-09-08
dbreunig analyzes Claude Fable 5.1's system prompt, arguing diffs over time reveal product design decisions. Key finding: Fable 5 and Opus 5 were bad writers because they "wrote in bulleted lists while actively avoiding bullets" — a prompt rule that banned bullets without explaining why, compressing curt points into dense paragraphs. The 5.1 prompt dials the rule back and adds motivation (bullets feel less personal and friendly) plus an exception — a textbook system-prompt hot fix. He also notes the overuse of "honestly" was either hard to train out of 5.1 or the bug was filed too late. A good window into how labs balance persona and capability as their user base scales.
More from Models
- Codex users report banked resets failing to arrive on schedule — No-Construction2209 · 2026-09-08
- Anthropic adding usage details button and Claude Code settings to iOS app — testingcatalog · 2026-09-08
- OpenAI demos GPT-6 Astra: from logo generation to interactive design prototypes — OpenAI · 2026-09-08
- Astra vs. Fable 5.1 on Real ML Tasks: Astra More Agentic, Fable Writes Better — burkov · 2026-09-08
- GPT-6 Astra plays Factorio live on Twitch — danielv123 · 2026-09-08
- Astra runs for 80 minutes then delivers nothing: users hit reliability wall — mideps · 2026-09-08