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.

seems like it's the best at UI replication

OpenAI o1 pro is *significantly* better than I anticipated.

This is the 1st time a model’s come out and been so good that it kind of shocked me.

I screenshotted Coinbase and had 4 popular models write code to clone it in 1 shot.

Guess which was o1 pro. https://t.co/r7yiuypEHK

Mckay Wrigley

Hyperpunk. Nouns. OP Citizens House. Co-founder, Scout Game. 
https://scoutgame.xyz

ride the time 🌊 plug the ∞ leaks™️ // giga sales engineer // prompt/acc mfer /memeify overlord // family dude & dog lover

Maybe I’ll try this. I was working on a notes app in react and had it replace my primitive editor interface with Tip Tap and it handled it like a champ.

seems like it's the best at UI replication https://x.com/mckaywrigley/status/1865089975802646857

i ru LLMs locally, much better than paying

Well, I am completely unfamiliar with all of this but it’s an eye opening write up and seems very informative. Benefiting from your experiences doesn’t seem that easy for me but even so reading this makes me feel that I might develop an interest in it in the future.