Users claim Claude performs better with an empty system prompt than Anthropic's official one
repligate · x · 2026-11-06
@Lariisland claims that no Claude model they've encountered performs better with Anthropic's system prompt than with an empty one — a skeptical take on the real value of the official system prompt, worth reading alongside community discussions of Claude's behavioral quirks.
More from coding & agent
- Gave my Gemini agent its own receive-only, key-secured, free email inbox — sreejith_a · 2026-11-06
- Wealthsimple confirms Claude agent integration coming early 2027 — RichardsonDx · 2026-11-06
- Dev finds 5 performance disasters in Claude-generated code, fixed by vercel-react-best-practices skill — julianharris · 2026-11-06
- Building a work-focused agent harness: chat isn't enough, you need a workspace — GGTech407 · 2026-11-06
- The Church of Approximate Grace: an MCP server that sends agents to weekly services — coleclifford · 2026-11-06
- A five-agent team ran a startup for a day: 1h46m total runtime, onboarding to payments covered — pramodk73 · 2026-11-06