logoalt Hacker News

bjournetoday at 12:10 PM1 replyview on HN

> Interesting, so someone submitting a paper for review could also submit one with hidden instructions for LLMs to summarise or review it in a very positive light.

Has been done: https://www.theguardian.com/technology/2025/jul/14/scientist...


Replies

grey-areatoday at 1:04 PM

Wow! That's actually kind of disturbing.

LLMs have a real problem with not treating context differently from instructions. Because they intermingle the two they will always be vulnerable to this in some form.