24hrs with o1 Pro, first impressions.

1. It’s slow. Very slow. The slowest LLM you’ve used in 2 years. Still about a million times faster than a human.

2. It’s better at code. Hard to really tell after 24 hours and I only used it for about an hour so far but it did a better job than o1 which I was using this weekend.

3. Gave it a complex math task for some game design work and it crushed it.

4. Some longer form research on Austrian economics and tariffs last night felt more robust.

All of this adds up to just feeling way more confident in using it. Taking the first answer more often. Possible placebo effect here.

Co-founder, Scout Game.
https://scoutgame.xyz

i ru LLMs locally, much better than paying