Embedded AI - Intelligence at the Deep Edge podcast

Are LLMs Creating Languages to Speak with Each Other?

0:00
24:55
Retroceder 15 segundos
Avanzar 15 segundos

Send us Fan Mail

Is AI developing a secret, unreadable language beyond human comprehension? In this episode, we unpack the origins, popular myths, and technical realities surrounding "neuralese"—the continuous vector communications and latent reasoning spaces used by neural networks.

Starting with its humble academic origin in a 2017 paper on inter-agent vector exchange, we examine how the concept evolved into viral internet panic. We systematically deconstruct viral "secret AI language" headlines—from Google’s zero-shot translation interlingua and Facebook’s negotiation bots to Gibberlink and Fable 5 rumor chains—showing that every incident stems from mundane causes like reward hacking, tokenization noise, or human-designed protocols.

Finally, we dive into the technical core: the performance trade-offs of latent reasoning architectures (such as COCONUT and recurrent depth), the fragility of chain-of-thought (CoT) monitorability, and how classic embedded-systems engineering (opaque buses, DBC schemas, and independent integrity checks) provides the right architectural model for AI safety oversight.

Support the show

If you are interested in learning more then please subscribe to the podcast or head over to https://medium.com/@reefwing, where there is lots more content on AI, IoT, robotics, drones, and development. To support us in bringing you this material, you can buy me a coffee or just provide feedback. We love feedback!

Otros episodios de "Embedded AI - Intelligence at the Deep Edge"