Robert Nishihara @robertnishihara · 01 Jun 2025
We're missing techniques for "training-time reasoning." Right now there's a lot of progress on inference-time reasoning, which is incredibly cool (I use o3 all the time). If I think about how I learn stuff, e.g., when reading a technical paper, it's very compute intensive. Most
66 306Views
63Likes
5Reposts
2Replies
4Quotes
0Bookmarks
Is that a lot?
2.93×vs this author's median22 635 views is typical
71Percentile for this authorof 7 recent posts
22.9×vs 10K–100K median2 896 views is typical
3.9× audienceReachviews ÷ followers
0.11%Engagement rateof viewers reacted