alex zhang @a1zhang · 24 Aug 2026
We run a small experiment over the RLM on information-dense tasks, and focus on the sub-LLM call as the tool of interest. These runs are high variance, and over 5 runs we find 1-1.2x gains in speed on similar trajectories. We also test over more deterministic examples in the https://t.co/hHEI8c50qQ
6 398Views
47Likes
2Reposts
1Replies
0Quotes
6Bookmarks
Is that a lot?
0.67×vs this author's median9 525 views is typical
23Percentile for this authorof 13 recent posts
3.13×vs 10K–100K median2 043 views is typical
16.83%Reachviews ÷ followers
0.78%Engagement rateof viewers reacted