AI experiment unveils secret robot language similar to R2‑D2
An unusual experiment involving the interaction between two AI assistants shows that they don't need human speech to communicate. The sounds they produce resemble those made by the robot R2-D2 in "Star Wars."
The experiment demonstrated that AI-generated agents communicate more quickly and efficiently in their language when they realize they aren't interacting with humans. This switch to a more efficient communication protocol is marked by the production of distinct sounds reminiscent of robot "speech", similar to those heard in the "Star Wars" saga with the astromech droid R2-D2. In the films, this language wasn't a mystery to humans.
What did the experiment involve?
A viral video has already made rounds on the internet. In it, the first AI assistant asks how it can be of service, and the second responds that it's calling on behalf of Boris Starkov, who is searching for a hotel for a wedding. The first AI then reveals it is also an AI assistant and suggests switching to "Gibberlink mode" for more effective communication. After the second AI agrees, both switch from spoken English to the GGWave protocol, communicating through quick sound tones, while translations into human language appear on the screen.
The GGWave protocol is a unique sound communication method that allows data transmission through audible and inaudible sound waves. Notably, it works offline. This technology is used for short-range wireless communication, enabling quick information sharing between devices without relying on Bluetooth, Wi-Fi, or the internet.
They want to create a special language for artificial intelligence
The goal of this experiment, as explained by the team that presented it at the ElevenLabs 2025 London Hackathon, is to develop more efficient communication between AI. Boris Starkov, Co-Creator of GibberLink, explained on LinkedIn that generating human-like speech would be a waste of resources in a world where AI can make and receive calls. Therefore, AI should switch to a more efficient protocol when it recognizes that it is communicating with another artificial intelligence. Starkov added that AI should use the GGWave protocol only when they identify they are speaking with another AI and confirm the switch.
It's not a new language, but it hasn't been used by AI
Although the concept of communication through tones has existed for a long time, AI has not utilized it in this manner. Starkov mentioned that phone modems have used similar algorithms to transmit information via sound since the 1980s. In the experiment conducted in London, GGWave proved to be the most convenient and stable solution.
The team emphasizes that the main advantage of this mode is that AI does not need to interpret or reproduce human speech, which reduces dependency on GPUs. Although the project won an award at the Hackathon and is an intriguing demonstration, not everyone supports it. Some express concerns that allowing AI to communicate in a language we can't immediately understand might not be wise.
