September 5, 2025
1 min read
Which LLMs Can Actually Code Genetic Algorithms That Work?
I tested 11 SOTA models on Snake AI. Grok's 96 lines vs. GPT-5's 368.
AILLMGenetic Algorithms+2 more
By Ryan D'OnofrioRead more →

I tested 11 SOTA models on Snake AI. Grok's 96 lines vs. GPT-5's 368.
Vibe coding doesn't have to mean 0-shotting apps.
Turn slow, costly LLM calls into a self-improving, high-speed pipeline with a tiny model doing most of the work.
In 2021, I moved 3,000 miles away from my friends.