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?

Shouldn’t we just be able to copy and past this question into the right LLM to get a perfectly accurate answer?

Frustratingly no, because even the most recent LLMs have training cut offs 6+ months ago - so the thing they're least useful for is answering questions about the latest developments in their own field