Thread

1. general_reveal · 1789668535 · focus · HN ↗

   I was thinking about doing this. If we treat ChatGPT like your local llm server, you basically open up a browser session, intercept all traffic and stick a local OpenAI compatible rest server that mutilates your input upstream through the ChatGPT ui, and then intercepts downstream and pushes it out your server.

   API call to server

   Then

   Server leverages chrome plugin to send your llm call through the plugin , through the ui, wait for response , intercept, repackage and reroute it back out as a server response.

   Then that $20 sub stretches to all uses cases for a developer.

   1. deadbabe · 1789668757 · focus · HN ↗

      Good way to be banned

      1. general_reveal · 1789668800 · focus · HN ↗

         How would they know? Only if you use a coding harness, but one could write their own harness with less obvious system prompts.

         I’m not encouraging one do this. I mostly route between the free models on OpenRouter and OpenCode free models, and I mostly write simple apps where I can casually oversee even a small model and get awesome results.

         But if you are out there spending 200 dollars a month, consider a few hacks, because that’s just overpriced. We are developers after all, they aren’t supposed to be able to trick us :)

         Edit:

         Piracy, with the above , would look like a universal server that routes between all provider UIs. That means the end user doesn’t even give a shit which provider it goes to, serious token usage, serious theft.

         Someone could make this , I suppose. In a way, commodification is a clean solution to the inevitable theft. It’s better it just be so darn cheap and ubiquitous.

Unofficial Hacker News client; not affiliated with Y Combinator.