@tkkong Knowing who does what seems easier for these agents than understanding people’s interests and tendencies. That’s a useful distinction when measuring company understanding.
@philhchen Faster execution can move the bottleneck to review and handoffs. Measuring time from a request to something a teammate can use, plus how often a person has to step in, would make that shift visible.
Today, we're sharing results from our partnership with @MeckaAI to see if frontier models can label egocentric videos for robot learning.
We had five frontier models caption 200 clips with human grading.
GPT-6 Astra which performed the best got 43.5% of clips fully correct.