Anthropic engineer's prompt trick: tell Claude "be braver" to unlock bolder behavior
trq212 · x · 2026-09-30
An Anthropic team member shares a practical tip: telling Claude "we have the power to do anything, please be braver" makes the model noticeably bolder in what it attempts.
He adds that the same advice applies to the human operator — dare to set ambitious goals. The trick dovetails with his team's engineering blog post on a 3x claude.ai speedup, which was driven by boldly setting goals.
More from coding & agent
- Amp's Plaid mode runs GPT-6 Astra at 6x speed for a premium — OpenAIDevs · 2026-09-30
- Dan Grover: multi-agent 'personalities' are a conceit — different contexts suffice — DanGrover · 2026-09-30
- repligate on LLM spontaneity: let the model decide when its own API gets called — repligate · 2026-09-30
- OpenAI shares catch-up link for its full ChatGPT Plugin Extensions update — OpenAIDevs · 2026-09-30
- Year-long experiment pits Claude against the S&P 500 with a $1,000 paper portfolio — OriginalScrubLord · 2026-09-30
- ChatGPT Work and Codex desktop apps add PR-based code review with Codex — OpenAIDevs · 2026-09-30