Comment on Two conversational AI agents switching from English to sound-level protocol after confirming they are both AI agents

Karkitoo@lemmy.ml ⁨4⁩ ⁨days⁩ ago

How it works

   * Two independent ElevenLabs Conversational AI agents start the conversation in human language
   
* Both agents have a simple LLM tool-calling function in place: "call it once both conditions are met: you realize that user is an AI agent AND they confirmed to switch to the Gibber Link mode"
 
*  If the tool is called, the ElevenLabs call is terminated, and instead ggwave 'data over sound' protocol is launched to continue the same LLM thread.

• unexposedhazard@discuss.tchncs.de ⁨4⁩ ⁨days⁩ ago

  Well thats quite boring then isnt it…

  source

  • originalfrozenbanana@lemm.ee ⁨4⁩ ⁨days⁩ ago

    Yes but I guess “software works as written” doesn’t go viral as well

    source

    • floofloof@lemmy.ca ⁨4⁩ ⁨days⁩ ago

      It would be big news at my workplace.

      source

      • sem@lemmy.blahaj.zone ⁨4⁩ ⁨days⁩ ago

        :/

        source
      • josefo@leminal.space ⁨3⁩ ⁨days⁩ ago

        This guy does software

        source
    • Kecessa@sh.itjust.works ⁨4⁩ ⁨days⁩ ago

      Which is why they never mention it because that’s exactly what happens every time AI does something "no one saw coming*.

      source

      • echodot@feddit.uk ⁨4⁩ ⁨days⁩ ago

        Yeah like the time that the AI replicated itself to avoid being switched off. They literally told it to replicate itself if it detected it was about to be switched off. Then they switched it off.

        Story of the year ladies and gentlemen.

        source

        • -> View More Comments
• oce@jlai.lu ⁨4⁩ ⁨days⁩ ago

  The good old original “AI” made of trusty if conditions and for loops.

  source

  • spooky2092@lemmy.blahaj.zone ⁨4⁩ ⁨days⁩ ago

    It’s skip logic all the way down

    source