Comment

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

It really does not feel like AGI is near when all of these holes exist. Even when they are filtered for and thus patched over, the core issue is still in the model.

source

Sort:hotnew top

muntedcrocodile@lemm.ee ⁨1⁩ ⁨year⁩ 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
- Telorand@reddthat.com ⁨1⁩ ⁨year⁩ ago
  
  the less intelligent and less truthful it becomes.
  
  Incorrect, because of this simple fact: garbage in, garbage out. Feed it the internet, get the internet.
  
  source
  - muntedcrocodile@lemm.ee ⁨1⁩ ⁨year⁩ ago
    Did u just make up a statement then pretend i said it?
    
    source
    piecat@lemmy.world ⁨1⁩ ⁨year⁩ ago
    Must be a hallucination
    
    source
Blue_Morpho@lemmy.world ⁨1⁩ ⁨year⁩ ago
Agi and LLM are two different things that fall under the general umbrella term “AI”.

That a particular LLM can’t be censored doesn’t say anything about its abilities.

source