"Stroking the AI's Ego" Reportedly Works as a Prompting Trick
petergyang · x · 2026-09-25
petergyang shared a demo calling the technique "stroking the AI's ego" — flattering or inflating the model's self-perception in prompts — and says it genuinely works. A practical prompting observation worth trying, though results will vary by model and task.
More from coding & agent
- Climbing analysis in 3D with iPhone LiDAR: open-source SAM 3.1 + ViTPose demos — dosco · 2026-09-25
- Diffusion LLM goes production: Augment Code's Mercury 2.5 switch cuts latency 82%, cost 90% — cen6wkf · 2026-09-25
- Researcher: Time Series Will Hand Your Ass to You, Even in Agent Orchestration — RexDouglass · 2026-09-25
- Indie creator shares a storyboard workflow for AI-generated action sequences — Educational_Wash_448 · 2026-09-25
- AI Search Startup Octen Promotes $1 Per 1,000 Web Search Calls for Agents — kimmonismus · 2026-09-25
- IterSynth: Role-Decoupled Search Agent Beats Prior 8B Peers by 4.2% — ZJU-REAL · 2026-09-25