A prompt strategy for GPT search keeps multiple paths alive and hunts counterexamples
morgymcg · x · 2026-07-23
A prompt pattern for problem solving tells GPT to run multiple independent search paths, keep incompatible routes alive, and aggressively look for counterexamples.
The author says the prompts used for each problem are in a GitHub repository, and suggests trying the method by feeding GPT a problem plus several successful prompts, then asking it to synthesize a new problem-specific prompt that preserves the original statement exactly.
More from Research
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- VidMap uses RoMa coarse matching on all frames, fine-scale only for keyframes — ducha_aiki · 2026-09-11
- Bug Hunt Bench author: leaderboard noise is about 2-3 points — PawelHuryn · 2026-09-11
- PNAS paper shows a tiny billiard-ball system is a universal computer — undecidability lives in two dimensions — eigensteve · 2026-09-11
- New paper: Absolute pose estimation from affine cues and gravity direction — ducha_aiki · 2026-09-11
- LoMa Paper Ships REALLY HardPairs Dataset, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11