AnalysisAI Models
Jun 29, 7:35 PM
AA-Briefcase scores show rapid AI gains on complex consulting tasks
Ethan Mollick
@emollick.bsky.socialProfessor at Wharton, studying AI and its implications for education, entrepreneurship, and work. Author of Co-Intelligence. Book: https://a.co/d/bC2kSj1 Substack: https://www.oneusefulthing.org/ Web: https://mgmt.wharton.upenn.edu/profile/emollick
Ethan Mollick
@emollick.bsky.social
I took the new AA-Briefcase scores from Artificial Analysis (basically having the AI do multi-week consulting gigs with a lot of complexity) and graphed the frontier curve for open and closed models: 1) Surprise, rapid gains! 2) The open weights gap is still quite real.
·
Jun 29, 7:35 PM