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
- AI Infers Code Architecture and Integrates New Provider in Under 10 Minutes — dfinke · 2026-07-22
- OpenAI Exec Boaz Barak Urges Developers to Try Codex Desktop Over CLI — soumitrashukla9 · 2026-07-22
- ChatGPT merges Codex and adds GPT-5.6 tiers for knowledge work — jxnlco · 2026-07-22
- PyTorch CTO to Explore Open Source AI Inference Economics and Workflow Optimization — PyTorch · 2026-07-22
- Evolution of AI Memory: From Simple Storage to Unified Dynamic Knowledge Graphs — qdrant_engine · 2026-07-22
- Six underrated AI skills: copywriting, planning, and domain expertise — tomcrawshaw01 · 2026-07-21