AI & machine learning2025 · shared on Hacker News
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Explore GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ymeetpateltech ·
Claude Skills
816 points427 comments
Ynanark ·
The case for the return of fine-tuning
167 points81 comments
YSerCe ·
A Comprehensive Survey of Self-Evolving AI Agents [pdf]
94 points29 comments
Ymooreds ·
Agent Skills
53 points37 comments
YLakshyAAAgrawal ·
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
8 points0 comments
YLakshyAAAgrawal ·
Show HN: Optimize_anything: A Universal API for Optimizing Any Text Parameter
6 points0 comments
Yhandfuloflight ·
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
3 points0 comments
YLakshyAAAgrawal ·
Optimize_anything: A Universal API for Optimizing Any Text Parameter
1 points1 comments