alex zhang @a1zhang · 24 Aug 2026
We want to speculate in two cases: 1. To overlap with the LLM streaming outputs, especially when thinking. 2. To overlap with actual REPL execution time, which can be expensive. This can be thought of as JIT compiling when you have stronger priors about tool calls. https://t.co/zOcKNjnIaD
9 525Views
94Likes
4Reposts
1Replies
1Quotes
21Bookmarks
Is that a lot?
1.00×vs this author's median9 525 views is typical
46Percentile for this authorof 13 recent posts
4.89×vs 10K–100K median1 948 views is typical
25.06%Reachviews ÷ followers
1.05%Engagement rateof viewers reacted