tweetindex

Ethan Mollick @emollick · 02 Sep 2026

Prinz has been running legal benchmarks against AI systems and the latest models are very good... but cheaper/low reasoning models are not very good. So, how do you make sure your vendor selling an AI solution is incentivized to serve the good (and therefore expensive) models?
24 355Views
155Likes
6Reposts
20Replies
0Quotes
47Bookmarks

Is that a lot?

0.83×vs this author's median29 213 views is typical
25Percentile for this authorof 4 recent posts
1.11×vs 100K–1M median21 891 views is typical
6.38%Reachviews ÷ followers
0.74%Engagement rateof viewers reacted

Compare with the benchmark table →

Open on X →