←back to thread

'Positive review only': Researchers hide AI prompts in papers

(asia.nikkei.com)
177 points ohjeez | 1 comments | 05 Jul 25 15:15 UTC | HN request time: 0.2s | source
Show context
gmerc ◴[05 Jul 25 15:38 UTC] No.44473491[source]▶
Good. Everyone should do this everywhere, not just in research papers. Because that's the only way we get the necessary focus on fixing the prompt injection nonsense, which requires a new architecture
replies(3): >>44473658 #>>44473930 #>>44474283 #
SheinhardtWigCo ◴[05 Jul 25 16:05 UTC] No.44473658[source]▶
The current situation is like if everyone was using SQL in production, but escaping and prepared statements had never been invented.
replies(1): >>44474311 #
1. dandanua ◴[05 Jul 25 17:44 UTC] No.44474311[source]▶
And now we want to apply agents on top of it. What could go wrong.