microgpt in MLPL
Screenshots haven’t been added yet. Visit the product to take a look.
microgpt in MLPL is a collection of ports of Andrej Karpathy's minimal GPT training algorithm implemented in ~200 lines of Python, reimagined in Rust and MLPL (an array language with built-in autograd). It trains a GPT model on a dataset of 32,033 names to invent new ones, providing readable literate programming sources with training output and equations. These implementations compare performance and fidelity, demonstrating efficiency trade-offs and byte-identical outputs between Rust and MLPL variants.
Ratings & Reviews
Write a reviewBe the first to share a thoughtful review.
Information
Website checks
Automated checks of the public website by Google Lighthouse 13.5.0. Scores can vary between runs.
Checked Oct 17, 2026
Test this website on PageSpeedWebsite checks refresh automatically each week.
- Performance
- 100 out of 100, Good
- Accessibility
- 95 out of 100, Good
- Best Practices
- 100 out of 100, Good
- SEO
- 100 out of 100, Good
Website checks are queued. Results will appear here when complete.