Post

It's wild to me how much expertise you need to engage successfully with these new AI systems Quick: what sort of prompts should you run against GPT-4o vs Gemini 1.5 Flash vs o1 vs o1-pro vs gemini-2.0-flash-thinking-exp?

One of my favourite prompts is: "I have a 3 litre jug and a 5 litre jug – how do I get 6 litres?" I wrote about it in my blag - LLMs really struggle with this question. djangoandy.com/2024/09/13/m...

Looks like o1-mini solved it gist.github.com/simonw/82e51...