Thinking Machines @thinkymachines · 27 Aug 2026
Cleaning data and aligning the reward function for RLVR takes expertise and effort upfront, but the result is a model that's state-of-the-art on a complex task. Guest post by researchers at UIUC and Bridgewater, in collaboration with our team. https://t.co/1UHTXFcZnW
68 660Views
493Likes
40Reposts
10Replies
5Quotes
262Bookmarks
Is that a lot?
0.31×vs this author's median219 383 views is typical
0Percentile for this authorof 4 recent posts
3.10×vs 100K–1M median22 159 views is typical
37.68%Reachviews ÷ followers
0.80%Engagement rateof viewers reacted