Open-Source AlphaEvolve Clone Using GPT-4.1 and Genetic Programming
Everyone saw the AlphaEvolve hype. I got obsessed with how it might work under the hood and decided to just build it myself. My setup uses GPT-4.1 to mutate matrix multiplication code, guided by a bunch of hand-crafted mutation strategies (loop reordering, tiling, Strassen, etc.). Each candidate is evaluated on both speed and accuracy. Then I apply Pareto selection with crowding distance to evolve better ones over generations. I ran into all the usual LLM reward hacks-returning the input, calling np.dot, etc. So I forced primitive-only implementations and tightly constrained the mutation…
In plain words
This is an open-source project that uses GPT-4.1 and genetic programming to automatically evolve optimized matrix multiplication code. The system applies hand-crafted mutation strategies like loop reordering and tiling, then uses Pareto selection to guide evolution toward implementations that are both fast and accurate. It's designed for developers and researchers interested in AI-driven code optimization and algorithmic discovery. The creator documented constraints added to prevent common LLM shortcuts and included the full codebase publicly.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Everyone saw the AlphaEvolve hype. I got obsessed with how it might work under the hood and decided to just build it myself. My setup uses GPT-4.1 to mutate matrix multiplication code, guided by a bunch of hand-crafted mutation strategies (loop reordering, tiling, Strassen, etc.). Each candidate is evaluated on both speed and accuracy. Then I apply Pareto selection with crowding distance to evolve better ones over generations. I ran into all the usual LLM reward hacks-returning the input, calling np.dot, etc. So I forced primitive-only implementations and tightly constrained the mutation space. After some struggle (and OpenAI credits vanishing), I ended up with a system that can actually evolve fast, correct implementations starting from a naive baseline. Full story here (with all the failures and design hacks): https://saipraneeth.in/ml/building-evolve Code’s public. Roast it, fork it, or try evolving your own. https://github.com/think-a-tron/evolve
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
