tweetindex

Apodex @Apodex_AI · 19 Aug 2026

Most AI benchmarks test retrieval — can a model find the known answer? However, the hardest problems in science require discovery, can a system earn an answer nobody has yet? Meet TRACES 🧭 — the world's first benchmark for measuring discoverative AI: AI that can work through https://t.co/rpTNHX6tzz
1 686 938Views
1 053Likes
708Reposts
524Replies
408Quotes
470Bookmarks

Is that a lot?

358×vs this author's median4 706 views is typical
75Percentile for this authorof 4 recent posts
440×vs under 10K median3 830 views is typical
315.7× audienceReachviews ÷ followers
0.16%Engagement rateof viewers reacted

Compare with the benchmark table →

Open on X →