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

paraphrand@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

• 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

  • Telorand@reddthat.com ⁨2⁩ ⁨weeks⁩ 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 ⁨2⁩ ⁨weeks⁩ ago

      Did u just make up a statement then pretend i said it?

      source

      • piecat@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

        Must be a hallucination

        source
• Blue_Morpho@lemmy.world ⁨2⁩ ⁨weeks⁩ 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