Gabriel P. Andrade @gab_p_andrade · 08 Jul 2026
8/ None of this requires AI (recall the 🥔). But an LLM with committed weights, a fixed prompt, and reproducible inference approximates credible neutrality...while being accurate enough on well-specified questions to make the threshold a real barrier.
93Views
4Likes
0Reposts
1Replies
0Quotes
1Bookmarks
Is that a lot?
0.64×vs this author's median145 views is typical
9Percentile for this authorof 11 recent posts
0.02×vs under 10K median4 686 views is typical
13.32%Reachviews ÷ followers
5.38%Engagement rateof viewers reacted