Hacker News Reader

the damn chat.openai.com webapp lags a lot as well on long chats, typing takes so long.

In my experience the input field lags on short chats too, sometimes in the middle of writing the second or third prompt. Are they running some kind of prospective evaluation or something?

When you are writing completely new prompt - it sends every character to server when writing and tries to make suggestions based on that.

And keeps doing it in intervals in /prepare endpoint, during each prompt.

So if you are working with something sensitive - don't write it to browser directly and edit it there.

But then why does it become dog slow when the chat becomes bigger?

I believe this is because they don’t lazyload the document.

The entire conversation sits in the DOM.

Yeah - is such a large dom of essentially text expected to be that slow?

For what it's worth I use a small script that essentially deletes old chat messages DOM nodes which significantly speeds it up.

Yes, because under the hood it’s much more than just text. It’s not hard to imagine dozens if not hundreds of elements are contained within each prompt+reply pair.

I bet there’s also some React performance issues involved here too

There are some real table stakes FE perf issues with the ChatGPT site

Reply on news.ycombinator.com