We Are Still Unable to Secure LLMs from Malicious Inputs
1–3 of 3 posts
Re: We Are Still Unable to Secure LLMs from Malicious Inputs
#2I think¹ we will always be unable to secure LLMs from malicious inputs unless we drastically limit the types of inputs LLMs can work with.
¹ https://matthodges.com/posts/2025-08-26-music-to-break-model...
Re: We Are Still Unable to Secure LLMs from Malicious Inputs
#3[dead]