It's right there in the code.

https://github.com/clmnin/summarize.site/blob/0e4da39fa4355a...

POST request with access token from the browser's cache after the user has logged in with their OpenAI account.

Yup. You need to SSE it though. Pretty simple actually (I'm OP, btw)

I didn't know what SSE was, so I asked ChatGPT:

> What does 'SSE' stand for in the following code sample: <pasted fetch-sse.js>

"In this code sample, 'SSE' likely stands for "Server-Sent Events". It is the name of the fetchSSE function and it is used to fetch data from a server using the Server-Sent Events protocol. This protocol allows a server to push data to a client in real-time, rather than requiring the client to continually poll the server for updates."

Not sure how accurate this is but it gave me enough information to look into it more!

I don't think ChatGPT is available via APIs. Most unofficial APIs are headless browser

I think they are using the same api as ChatGPT https://github.com/clmnin/summarize.site/blob/0e4da39fa4355a...

Is this even legal?

The only thing here is instead of copy-pasting it into ChatGPT, you get to use a browser extension that does the job. Pretty convenient actually.

So technically, we are still using https://chat.openai.com/chat, with the UI

This guy [1] (on twitter) says they are using Davinci 003, and claiming it is what ChatGPT uses.

[1] https://twitter.com/VarunMayya/status/1599736091946659845

ChatGPT is in fact just a chat prompt on top of Davinci3, plus a markdown renderer

Do we know what the prompt is?

The posts of comments to chatgpt reference davinci-002