I spent the day with o1-preview-2024-09-12. Ignoring costs, because that wasn't really my concern today, my impression falls pretty much in line with its results on LiveBench Language benchmark, a benchmark I feel is fairly reflective of model capability.

I only listen to Russillo during the NBA season, and yet, he's still my 2nd most listened to pod. Maybe the season is too long!😂

I've been really locked into model tool-use and what devs are really doing there. Right now my interest is in exploring the Anthropic computer-use capabilities. This paper is a really great exploration into agents that navigate GUI's.

arxiv.org/pdf/2411.10323