Post

What are some of the things you've learned about how LLMs (and LLM-powered systems like ChatGPT) work that were non-obvious but most helped you build a more effective mental model of how to use them?

Jan Ehrhardt

@jehrhardt.dev

4 Jan 2025

LLMs are actually stateless. You put in the historic context as input. Chat is only a UI constraint to build this context iteratively.

asura

@asura.dev

4 Jan 2025

This is a big one. There was a whole thread on bsky the other day where people thought you could "teach" chatGPT. A lot of people need to hear this one. You can't "teach" it (outside of providing context as mentioned).

Simon Willison

@simonwillison.net

Ooh can you link to the thread? I wrote about this misconception a while ago: simonwillison.net/2024/May/29/...

simonwillison.netTraining is not the same as chatting: ChatGPT and other LLMs don’t remember everything you sayI’m beginning to suspect that one of the most common misconceptions about LLMs such as ChatGPT involves how “training” works. A common complaint I see about these tools is that …

4/1/25, 11:07 pm0 reposts23 likes

asura

@asura.dev

4 Jan 2025

I'll try to find it when I'm on a PC. A quick check back at my mentions, etc, and there's nothing there. It had to have been deleted and/or I was blocked. :P Saying ChatGPT doesn't eat cats and isn't secretly withdrawing $30/month from your wallet is a Speedrun Any% Block here. :P