Claude Code’s system prompt shrank 80% as Fable works better with lighter prompts
emollick · x · 2026-07-21
A notable prompt-engineering takeaway for Claude/Fable: treat stronger and weaker models differently. Skills that work on Opus can make Fable worse, and piling on negative instructions can also hurt output.
The thread also notes that Claude Code’s system prompt recently shrank by 80%, reinforcing the idea that lighter prompting can be better for newer model behavior.
Related event: Claude Code System Prompt Reduced by 80%(4 posts)→
More from coding & agent
- DeepMind paper: LLMs can't sample randomly on their own — pass random numbers from code instead — rohanpaul_ai · 2026-10-27
- BELL: Open-Source Stack Combines Browserbase, Eve, iMessage and Stripe Link for Personal Agents — jeff_weinstein · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Two engineers rebuilt a FedEx supplier's billing core in 3.5 months vs an estimated 7-8 — alex_verem · 2026-10-27
- GPT-6.1 Terra scores 48 on AA Coding Agent Index at one-third the cost of GPT-5.6 Terra — ArtificialAnlys · 2026-10-27
- Shift-1 router cuts coding agent spend up to 55% while keeping SWE-bench accuracy — ypatil125 · 2026-10-27