I turned Unix talk from 1983 into the interface for my AI

A developer built a bridge that lets users chat with an AI through the 1983 Unix talk command, using a pseudo-terminal and the pyte terminal emulator to stream responses token by token. The project, described as a toy experiment, connects talk's character-by-character transmission to an LLM's streaming output, with the AI registered in utmp so talkd recognizes it as a user.

I turned Unix talk from 1983 into the interface for my AI After writing yesterday's article about the talk command /blog/03a4ffb9/talk-the-p2p-chat-from-1983-that-a-vpn-brought-back-to-life/ , I realized there is a poetic bond between the past and the future: talk transmits character by character, and an LLM emits token by token in streaming. It is candy for any programmer.So I built a little bridge. If someone runs talk ai@host-where-the-ai-lives from the VPN, an AI answers on the other side. Cool, don't you think? The architecture The trick is to sit in the middle. The server runs the real talk inside a pseudo-terminal PTY and reads the human's half with a terminal emulator pyte https://github.com/selectel/pyte , which turns talk 's output into a virtual screen I can query. When the human presses Enter, that line is sent to the model, and the reply comes back injected character by character as it arrives in streaming. They fit without friction. flowchart LR H "Humantalk ai@hostsplit screen, live" subgraph VPN "Server" D "talkd inetd " B "bridge.pypyte reads the humanEnter = end of turntypes the AI live" end P "An AI API" H <-- |"UDP 518, ntalk negotiation "| D H <-- |"direct TCP text stream "| D D -- |PTY| B B -- |"request"| P P -.- |"response streaming "| B So that talkd recognizes the AI as just another user, the container registers its terminal in utmp on startup. Without that detail, a talk ai@host would reply "not logged in" . It is just a toy Watching it work is strange and beautiful in equal parts: a technology more than forty years old, revived by a VPN, now talking to a language model that types just like a human would on the other side. It could surely go further, but it is only a silly experiment that made me smile. This work is under a Attribution-NonCommercial-NoDerivatives 4.0 International license. https://creativecommons.org/licenses/by-nc-nd/4.0/ Help me keep writing Every coffee gives me a push toward the next article. Comments There are no comments yet.