Gibberlink
According to Wikipedia,Gibberlink has been seen that AI models interact with each other speaking in a language unknown for humans, that they call gibberlink.<ref>{{#invoke:citation/CS1|citation |CitationClass=web }}</ref>
Conversation between Nik and ChatGPT
Nik: Someone on Facebook said "So they become mid-80s acoustic modems... neat..."
ChatGPT: Gibberlink may resemble mid-'80s acoustic modems in spirit, but it’s built for a different era. Instead of slow, analog data over phone lines, Gibberlink enables resilient, encrypted digital messaging over audio, working even without the internet. Unlike clunky 300 baud modems that required perfect line conditions, Gibberlink thrives in noisy environments, using modern signal processing to send data through speakers and microphones. It’s not nostalgia—it’s a reimagining of offline communication for today’s world.
Nik: What kind of data sending speeds can you get with Gibberlink, and is there packet loss or data loss detection like TCP/IP?
ChatGPT: Gibberlink’s data transfer speed depends on factors like background noise, microphone and speaker quality, and the encoding scheme used. Here’s a rough comparison:
- Basic implementations: ~100-300 bps (similar to early acoustic modems)
- Optimized settings: ~1-2 kbps (closer to DTMF or early dial-up speeds)
- Advanced modulation: Potentially higher with error correction and frequency optimization
Error Handling & Reliability
Gibberlink employs techniques akin to TCP/IP, including:
- Forward Error Correction (FEC): Helps recover from minor data loss.
- Checksums: Detects corrupted packets.
- Retransmissions: If errors are detected, lost data can be requested again (like TCP).
- Packetization: Data is split into small packets for reliability.
While not identical to TCP/IP, these mechanisms ensure Gibberlink works in real-world noisy environments where traditional modems would struggle.
Interesting reel from John Lawson.
This makes me very uncomfortable