Ofir Press @OfirPress · 05 May 2026
How much of SQLite, FFmpeg, PHP compiler can LMs code from scratch? Given just an executable and no starter code or internet access. Introducing ProgramBench: 200 rigorous, whole-repo generation tasks where models design, build, and ship a working program end to end. 🧵 https://t.co/8ayeDJLXaJ
751 133Views
1 583Likes
246Reposts
107Replies
110Quotes
0Bookmarks
Is that a lot?
234×vs this author's median3 207 views is typical
100Percentile for this authorof 11 recent posts
209×vs 10K–100K median3 598 views is typical
38.5× audienceReachviews ÷ followers
0.27%Engagement rateof viewers reacted