tweetindex

elie @eliebakouch · 15 Aug 2026

We ran the largest open experiment on how frontier models do AI research. 100+ autonomous runs across 10+ models, sandboxed on 8xH200s for up to 8 days, iterating on the nanoGPT optimizer track. Best runs closed 82% of the gap to a record built by dozens of humans over months. https://t.co/OcdygMcZpS
588 486Views
1 881Likes
213Reposts
74Replies
105Quotes
0Bookmarks

Is that a lot?

18.7×vs this author's median31 519 views is typical
86Percentile for this authorof 7 recent posts
203×vs 10K–100K median2 896 views is typical
24.4× audienceReachviews ÷ followers
0.39%Engagement rateof viewers reacted

Compare with the benchmark table →

Open on X →