What prompt gets the most interesting ideas out of LLMs? A researcher's ongoing experiment
arjunrajlab · x · 2026-10-16
The opening post of arjunrajlab's thread on LLM ideation: he tested whether poems for free association, random words, or personas elicit the most interesting ideas. His short answer: just ask the model to come up with non-obvious ideas. Follow-up posts in the thread add that an AI judge/filter helps surface good ideas and that the Opus vs Sonnet/Haiku gap is stark.
Related event: Asking for Non-Obvious Ideas Boosts LLM Creativity Most, Study Finds(3 posts)→
More from coding & agent
- ThePrimeagen mocks AI coding: infinite tokens still produce an Electron app — seatedro · 2026-10-17
- Generative UI 101: Building Live Interfaces with Agents on Opus 5.5 and Rivals — EXM7777 · 2026-10-17
- MCP server review: gate tool writes on auth/traversal findings, not test score — SamuelFmedeiros · 2026-10-17
- DeepSeek shows rapid vision gains: agent self-checks screenshots to build 3D scene — cedric_chee · 2026-10-17
- He gave an AI agent phone and email access to collect a $500 unpaid invoice — curious_vii · 2026-10-17
- AI:AM transcript: agent lockouts, hidden valence, and formal proofs for Linux kernel bugs — The Cognitive Revolution · 2026-10-17