New Prompt Optimization Beats GEPA by ~14% and Estimates Performance Bounds
sanmikoyejo · x · 2026-10-29
A companion paper spun out of the thread models prompt optimization as a structured search over prompt variations. The approach not only produces prompts 14% better than state-of-the-art methods like GEPA, but also yields reliable estimates of asymptotic upper bounds throughout the search. Motivation: rubrics and constitutions matter for task improvement and safety, but some judge criteria (like 'comic voice') resist articulation — so what can you expect written constructs to achieve, and how good can a judge get? Links in original post.
More from coding & agent
- TTME beats test-time training on math discovery with 84% fewer FLOPs — rohanpaul_ai · 2026-10-29
- Build an in-house media team with one person and a Grok bot: 3 folders, 6 prompts — VibeMarketer_ · 2026-10-29
- 10 open-source vector DBs for AI agents, from Milvus to sqlite-vec — victor_explore · 2026-10-29
- Claude agent builds its own picture tool and sets its own avatar — nathanborror · 2026-10-29
- Forbidding AI comments: one dev's rules for slop-free Claude Code — seatedro · 2026-10-29
- Naver MCP Server brings Naver OpenAPI search for blogs, news and images to MCP clients — modelcontextprotocol · 2026-10-29