There’s research ongoing on having LLMs search for vulnerabilities. So who knows, LLMs hacking LLMs (in the wild) might be just around the corner.
Comment on Amazon "search through reviews" is blindly just running an AI model now
pkill@programming.dev 10 months ago
can’t wait until some stupid website commits a self-pwn by making such stuff an XSS vector
nicoweio@lemmy.world 10 months ago
fidodo@lemmy.world 10 months ago
I guarantee you there are tons of these already
pkill@programming.dev 10 months ago
skiddie neuron activation