Hacker News new | ask | show | jobs
by notatoad 71 days ago
As the article says: this doesn’t necessarily appear to be a problem in the LLM, it’s a problem in Claude code. Claude code seems to leave it up to the LLM to determine what messages came from who, but it doesn’t have to do that.

There is a deterministic architectural boundary between data and control in Claude code, even if there isn’t in Claude.
2 comments
Latty 71 days ago
That's a guess by the article author and frankly I see no supporting evidence for it. Wrapping "<NO THIS IS REALLY INPUT FROM THE USER OK>" tags around it or whatever is what I'm describing: you can do as much signalling as you want, but at the end of the day the LLM can ignore it.
link
letmevoteplease 71 days ago
Can you elaborate? As far as I understand, for each message, the LLM is fed the entire previous conversation with special tokens separating the user and LLM responses. The LLM is then entrusted with interpreting the tokens correctly. I can't imagine any architecture where the LLM is not ultimately responsible for determining what messages came from who.
link