[untitled]2 points·by coonr·5 mesi fa·0 comments4 commentsPost comment[–]ddmma·5 mesi fareplyGood hygiene. But the gap they admitted—NL attacks, prompt injection—won't get fixed by pointing another LLM at it.LLM auditing LLM is like RAG solving reasoning. Same blindspot, twice.[–]Jang-woo·5 mesi fareplyIt’s encouraging to see the conversation shifting from model performance toward execution responsibility and security structure.[–]nutapongpe·5 mesi fareplyTrand gold[+]Wizberry·5 mesi fa
LLM auditing LLM is like RAG solving reasoning. Same blindspot, twice.