back

by pentagrama·3d ago·view on hn ↗
Interesting to see the Linux version released. On Windows, though, my experience with the new ChatGPT app since Codex was folded into it hasn't been great.

I'm a Codex user, and when it was still a standalone app it worked really well for me. Since it became part of the new ChatGPT app, the app feels noticeably slower and, at least on my machine, is currently using around 1.27 GB of RAM [1].

The old ChatGPT app, which has now been renamed "ChatGPT Classic", feels much faster and is using around 478 MB under the same conditions.

I have a reasonably powerful PC, so the difference is pretty noticeable. I assume Classic will eventually be discontinued, but so far the transition to the new app on Windows hasn't been particularly good for me.

[1] https://imgur.com/a/nQkneGL

2 comments
> The old ChatGPT app, which has now been renamed "ChatGPT Classic", feels much faster and is using around 478 MB under the same conditions.

That's definitely better, but all things considered, this is still an absurd amount of memory for a text chat client, even if you account things like hardware composited high-definition UI surfaces etc. into it.

The old app also had a habit of spinning at least one CPU core at 100% due to some runaway "shimmer" animation when an image wouldn't load or something...

> my experience with the new ChatGPT app since Codex was folded into it hasn't been great.

My main gripe beyond the performance issues is that OpenAI doesn't yet seem to know where they want to go with Codex and "ChatGPT Work", and is changing the paradigms daily, making it feel like there's no point in even trying to understand them.

It's really unclear to me which conversations (and lately scheduled tasks) are local and which are cloud-based.

Codex app was always unoptimized , but the competitores arent great either.

However it’s still a an agent app, it gets the job done and has great tooling.

Eventually the whole thing will probably be remade in a more performant way and be announced in a blog post as one shotted by gpt 6.x