flâneur

Training is not the same as chatting: ChatGPT and other LLMs don’t remember everything you say

simonwillison.net · 1,842 words · saved by 1 readers

I’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 people don’t want to even try them out because they don’t want to contribute to their training data. This is by no means an irrational position to take, but it does often correspond to an incorrect mental model about how these tools work. Short version: ChatGPT and other similar tools do not directly learn from and memorize everything that you say to them. This can be quite unintuitive: these tools imitate a human conversational partner, and humans constantly update their knowledge based on what you say to to them. Computers have much better memory than humans, so surely ChatGPT would remember every detail of everything you ever say to it. Isn’t that what “training” means? That’s not how these tools work. From a computer science point of view, it’s best to think of LLMs as stateless function calls. Given this in

Training is not the same as chatting: ChatGPT and other LLMs don’t remember everything you say Simon Willison’s Weblog Subscribe Sponsored by: Microsoft - Agent projects stall between demo and production. Microsoft's MVP checklist closes that gap. Try it Training is not the same as chatting: ChatGPT and other LLMs don’t remember everything you say 29th May 2024 I’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 people don’t want to even try them out because they don’t w

saved by

related reading