Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I only vaguely follow the developments in LLMs, so this might be a dumb question. But my understanding was that LLMs have a fixed context window, and they don’t “remember” things outside of this. So couldn’t you theoretically just keep talking to an LLM until it forgets the system prompt? And as system prompts get larger and larger, doesn’t that “attack” get more and more viable?


Most providers will just end the chat if it reaches the max context window.




Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

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

Search: