zlacker

[parent] [thread] 0 comments
1. simonw+(OP)[view] [source] 2026-01-31 04:56:55
Sadly this has been tried before and doesn't work.

If an attacker can send enough tokens they can find a combination of tokens that will confuse the LLM into forgetting what the boundary was meant to be, or override it with a new boundary.

[go to top]