Aidan Gomez @aidangomez · 27 Aug 2026
Parsing turns out to be one of the biggest bottlenecks to LLMs being able to make effective use of enterprise data. Previously, you had to choose between high-quality understanding that is unscalable and costs $$$ or shit quality lossy-parsing that is scalable. NOT ANYMORE https://t.co/chelL8R50d
12 902Views
137Likes
10Reposts
16Replies
2Quotes
36Bookmarks
Is that a lot?
1.03×vs this author's median12 551 views is typical
50Percentile for this authorof 6 recent posts
4.46×vs 10K–100K median2 896 views is typical
32.27%Reachviews ÷ followers
1.28%Engagement rateof viewers reacted