Our latest optimizer GEPA writes beautiful prompts, even with a “mini” model. Stay tuned for a lot more these coming days.

Matt Pocock muzz Omar Khattab Storm DSPy One of the cool prompt optimization results I saw around GEPA was they found that a prompt instructing the model that it was a StarCraft player made it outperform any other specialized prompt on math Olympiad problems

Matt Pocock DSPy GEPA solves the large data issue, instead of 100+ You can get by with 10 at minimum alphaxiv.org/overview/2507.…

Matt Pocock Maxime Rivest 🧙‍♂️🦙🐧 DSPy The docs for GEPA (a recently added optimizer) has an example of an llm-as-a-judge metric: dspy.ai/tutorials/gepa…

📣 Our next tutorial in our marimo series is out! In this one, we showcase how to use DSPy to build a composable Graph RAG pipeline that does the following: 1. Schema pruning 2. Text2Cypher 3. Answer Generation Chat with your graphs in Kùzu! youtube.com/watch?v=2aepn9…

[2507.19457] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning arxiv.org/abs/2507.19457

Doing an introduction to DSPy DSPy tomorrow at BangPypers meet-up.

It's time to VIBE your DSPy Now you can - transform your prompt-ideas into Signatures - refine them with your feedback - use dynamically after generation - even optimise it with MIPRO or GEPA source and examples of usage bellow 🧵

It can also be optimised by MIPRO or GEPA but I didn't try it. But maybe we can collect dataset of awesome dspy signatures to try it. What do you think? DSPy Omar Khattab Tom Dörr

Don't know what to get your advisor for their birthday? Give them the best gift of all: their time back. Happy (late) birthday Joey Gonzalez :)

I got around to kicking the tires on GEPA prompt optimization in DSPy, seeing if it could match the reported gsm8k benchmark for Qwen3-4b-thinking. Started with the simplest signature: qa_bot = dspy.Predict('question -> answer') GEPA got it from 67.2% to 92.8%.

Drew Breunig Performed some experiment last week using GEPA with DSPy using llama3.1:8b and Qwen3:8b also locally hosted gpt-oss:20/120b on M4 Max 128GB RAM. Source : github.com/SuperagenticAI… Blog: super-agentic.ai/resources/supe… Code is open open source but uses SuperOptiX (proprietary) framework.

Sudhir Gajre Drew Breunig DSPy Not as simple an example as Drew’s but the docs show how to use it below. Welcome to the world of DSPy ! dspy.ai/tutorials/gepa…

Kevin Madura Sudhir Gajre DSPy If you’d like more grounding first, you can check out my intro: dbreunig.com/2024/12/12/pip…

🤖 From this week's issue: a paper on GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning arxiv.org/abs/2507.19457

3 | Your choice of program structure is a moat I’ve prev. posted about this x.com/GabLesperance/… but meaningful defensible advantage comes from your unique composition of models and logic, the proprietary datasets that fuel them, & the continuous optimizations that refine them

4| Startups should ignore FT / RL in favour of LM driven prompt opt. (unless proven otherwise) Prompt optimization provides a faster learning, higher accuracy, cheaper, and more data-efficient solution Don't believe the hype, focus on how fast you can iterate per $ and FTE spent

GEPA optimizes LLMs without costly reinforcement learning venturebeat.com/ai/gepa-optimi…

youtube.com/watch?v=H4o7h6… Thanks Connor Shorten for creating this amazing tutorial on using GEPA to optimize a Listwise Reranker!