Hacker News new | past | comments | ask | show | jobs | submit login

> It doesn't create an internal model of the problem given, it just guesses.

It's not entirely true. They often use some sort of memory/scratch-pad to keep a context other than previous tokens. This recent exploit lets you see claude's default prompt that have some references to this system.

https://youtu.be/AbPTz08oq58?si=7F5Lbbkxg99tr3FP




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: