A tested prompt tones down Fable 5.1's "claudese"; Anthropic ships official prompting guide
omarsar0 · x · 2026-09-03
Developer omarsar0 shares a prompt he tested that actually works to reduce Claude Fable 5.1's signature "claudese" writing style. The linked resource is Anthropic's new official guide, Prompting Claude Fable 5.1, covering behavioral differences and fixes for a dozen scenarios: choosing effort levels, batching independent tool calls in agent loops, keeping conversation history append-only, tuning writing density, formatting in chat, quoting retrieved sources, finishing the whole task without re-asking, preserving constraints in compaction summaries, and limiting changes/tests to what the task asked for.
Related event: Anthropic Releases Official Prompting Guide for Claude Fable 5.1(9 posts)→
More from Models
- Bug Hunt Bench ranks frontier coding models on 105 planted real-repo bugs — PawelHuryn · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- 105 hidden bugs, 2 repos: DeepSeek V4.1 Flash fixes 24 at $1.80 vs Opus 5's 27 at $51.33 — ChartsJournalX · 2026-09-11
- awesome-llm-leaderboards: an open-source directory of LLM leaderboards, pricing tables, comparison tools — Last_Establishment_1 · 2026-09-11
- Anthropic claims it works to keep eval environments unidentifiable to models — MaxKannen · 2026-09-11
- Nex N2.5 Pro released on Hugging Face with 407GB of weights — jinnyjuice · 2026-09-11