tweetindex

elie @eliebakouch · 15 Aug 2026

to my knowledge this is the largest open experiment on autonomous agents iterating on a research environment we scaled runtime, compute, diversity of models and harnesses. as a comparison, similar tasks on oai/anthropic system cards are anthropic "optimizing an llm training on https://t.co/FM8ywpmFk7
105 782Views
831Likes
76Reposts
51Replies
11Quotes
460Bookmarks

Is that a lot?

3.36×vs this author's median31 519 views is typical
57Percentile for this authorof 7 recent posts
38.5×vs 10K–100K median2 751 views is typical
4.4× audienceReachviews ÷ followers
0.92%Engagement rateof viewers reacted

Compare with the benchmark table →

Open on X →