lasu

Joined 4 months ago

Karma

26

Submissions

3

Member since

Jun 5

View on Hacker News

Recent submissions

Comment · 17 days ago

The benchmarks are what allows the AI researchers to improve the models. The AI doesn't get better on its own.

Show HN: Parsimony – an open-source benchmark for how much code AI models add parsimony.lasu.dev

77 lasu 18 days ago 19 comments