Comment on ChatGPT-4o Guardrail Jailbreak: Hex Encoding for Writing CVE Exploits.

<- View Parent
muntedcrocodile@lemm.ee ⁨2⁩ ⁨weeks⁩ ago

Ironically the smarter the ai gets the harder it is to censor. Also the more u sensor it the less intelligent and less truthful it becomes.

source
Sort:hotnewtop