Mike Knoop @mikeknoop · 04 Sep 2026
New chart from Astra testing on ARC v3 Astra often emits zero reasoning tokens per action at lower reasoning levels. We've never seen this before. And surprisingly Astra low is 2X more accurate than Sol max. This suggests Astra is leveraging a secondary test-time adaptation https://t.co/yuTzZn60MX
11 004Views
209Likes
21Reposts
24Replies
7Quotes
62Bookmarks
Is that a lot?
1.00×vs this author's median11 004 views is typical
40Percentile for this authorof 5 recent posts
4.87×vs 10K–100K median2 259 views is typical
44.29%Reachviews ÷ followers
2.37%Engagement rateof viewers reacted