Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Show HN: I reimplemented TRM – trains on Sudoku 6×6 in minutes on an A10 (github.com/olivkoch)
2 points by whiplash451 5 days ago | hide | past | favorite | 1 comment
Hi folks!

Tiny Recursive Models reach impressive results on ARC AGI. I implemented a version from scratch, with ease of experimentation in mind:

- cleaner config: hydra, uv, lightning - smaller datasets for faster iteration (Sudoku 6x6 and 9x9) - introduction, in-code video

All important implementation details have been carefully kept. The results of the paper are reproducible (Sudoku Extreme, Maze Hard).

Feedback/contributions welcome.





Is it possible to measure which rules are more useful in each case?

When my older daughter was a kid, she used to play Sudoku 6x6. I notices she was trying the rules in a weird order, that was different from mine that played 9x9.

After playing a few 6x6 I notice some of the rules were more useful in 6x6 than in 9x9 and she was right to try them in a different order.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: