@harold_matmul: it was my idea :) Using GEPA is a very natural workflow for creating LLM programs. The iteration speed is very quick, a…
Summary
A user thanks for the GEPA tool, highlighting its natural workflow for LLM programs, fast iteration, and ability to bias optimization with data-derived priors.
View Cached Full Text
Cached at: 06/03/26, 05:54 PM
@lateinteraction it was my idea :)
Using GEPA is a very natural workflow for creating LLM programs. The iteration speed is very quick, and it easily allows researchers to bias the optimization with some priors (usually derived from just looking at the data).
Thanks a lot for the great tool!
Similar Articles
@harold_matmul: dspy.GEPA used in pretraining data curation in the new Microsoft AI effort :-)
The article explains how GEPA (Genetic-Pareto Optimization) within DSPy is used for efficient prompt tuning, specifically applied to pretraining data curation at Microsoft AI, allowing researchers to replace manual prompt engineering with automated compute-driven optimization.
@tech_optimist: Absolutely amazing work combining RLMs and GEPA. Looking forward to part 2!
A tweet praising the combination of RLMs and GEPA, expressing anticipation for a follow-up.
@lateinteraction: dspy.GEPA used in pretraining data curation in the new Microsoft AI effort :-)
GEPA-optimized LLM judges from dspy are used for data filtering in Microsoft's MAI-Thinking-1 model pre-training pipeline.
@zihengh1: LLM-as-a-judge is now everywhere for automated evaluation. But it can be slow, expensive, and opaque. What if we ask th…
Introduces PAJAMA, a hybrid evaluation system that improves upon the LLM-as-a-judge approach by extracting rubrics and executing them programmatically, pushing the Pareto frontier of speed, cost, and transparency.
@shawntenam: GEPA (http://github.com/gepa-ai/gepa) bumped Haiku 4.5 from 65% to 85% pass rate by auto-optimizing my prompt instructi…
GEPA is an open-source tool that automatically optimizes prompt instructions using execution traces and scores, raising Claude Haiku 4.5's pass rate from 65% to 85% without requiring a model swap.