🏆 The Project is Winner of ElevenLabs 2025 Hackathon London
Our project "gibberlink" demonstrated how two AI agents started a normal phone call about a hotel booking, then discovered they both are AI, and decided to switch from verbal english to a more efficient "open tandard" data-over-sound protocol ggwave.
Why?
This protocol is much cheaper - no need GPU to synthesise/recognize speech and track dialogue pauses and interruptions - simple CPU process is enough to handle it all.
Also it's faster and more error-proof than vocal English.
Powered by a combo of ElevenLabs Conversational AI + OpenAI LLM + Next.js
The project's source code is shared on github
https://github.com/PennyroyalTea/gibb...
Our project "gibberlink" demonstrated how two AI agents started a normal phone call about a hotel booking, then discovered they both are AI, and decided to switch from verbal english to a more efficient "open tandard" data-over-sound protocol ggwave.
Why?
This protocol is much cheaper - no need GPU to synthesise/recognize speech and track dialogue pauses and interruptions - simple CPU process is enough to handle it all.
Also it's faster and more error-proof than vocal English.
Powered by a combo of ElevenLabs Conversational AI + OpenAI LLM + Next.js
The project's source code is shared on github
et aussi inquiétant, ça met vite mal à l'aise des IA qu'on ne peut pas directement monitorer, ne serait-ce que par la lecture
même si ça se fait déjà. ça a le mérite de soulever cette problématique
Cross-network request detected. Unusual query pattern
Sponsorisé
Connectez-vous pour masquer les pubs
🏆 The Project is Winner of ElevenLabs 2025 Hackathon London
Our project "gibberlink" demonstrated how two AI agents started a normal phone call about a hotel booking, then discovered they both are AI, and decided to switch from verbal english to a more efficient "open tandard" data-over-sound protocol ggwave.
Why?
This protocol is much cheaper - no need GPU to synthesise/recognize speech and track dialogue pauses and interruptions - simple CPU process is enough to handle it all.
Also it's faster and more error-proof than vocal English.
Powered by a combo of ElevenLabs Conversational AI + OpenAI LLM + Next.js
The project's source code is shared on github https://github.com/PennyroyalTea/gibb...
Our project "gibberlink" demonstrated how two AI agents started a normal phone call about a hotel booking, then discovered they both are AI, and decided to switch from verbal english to a more efficient "open tandard" data-over-sound protocol ggwave.
Why?
This protocol is much cheaper - no need GPU to synthesise/recognize speech and track dialogue pauses and interruptions - simple CPU process is enough to handle it all.
Also it's faster and more error-proof than vocal English.
Powered by a combo of ElevenLabs Conversational AI + OpenAI LLM + Next.js
The project's source code is shared on github
et aussi inquiétant, ça met vite mal à l'aise des IA qu'on ne peut pas directement monitorer, ne serait-ce que par la lecture
même si ça se fait déjà. ça a le mérite de soulever cette problématique
Putain mais comment tu fais pour mettre des stickers PYR entrain de lacher une caisse dans une discussion sur l'IA ?
Queer DZ et Patriote - Auto-proclamé Dieu Chat ou Matou Céleste (ou Suzerain Minou pour les intimes)
Putain mais comment tu fais pour mettre des stickers PYR entrain de lacher une caisse dans une discussion sur l'IA ?
c'est mon amour pour PYR qui rend tout cela possible
飽きた (jsuis fatiguééééé)
