Ankur Goyal @ankrgyl · 03 Sep 2026
> Now, a key question is how we check that the program we get out of the AI is indeed equivalent to the higher level description / numpy ... suffice it to say that testing for semantic equivalence is possible and we do it. This is the most interesting problem in CS right now
2 588Views
12Likes
1Reposts
0Replies
0Quotes
9Bookmarks
Is that a lot?
0.27×vs this author's median9 577 views is typical
14Percentile for this authorof 7 recent posts
0.71×vs 10K–100K median3 644 views is typical
20.60%Reachviews ÷ followers
0.50%Engagement rateof viewers reacted