ProgramBench: Can Language Models Rebuild Programs from Scratch? (github.com) 3 points by fittingopposite 2mo ago ↗ HN
[–] Kuinox 2mo ago ↗ I didn't managed to find the tests. How can we know that the tests are actually reasonable in this case ?
1 comment
[ 0.16 ms ] story [ 18.9 ms ] thread