Alex Rattray

This also happened to me. I switched to just using `symbols-view` and `autocomplete-ctags`

The speed of `gpt-3.5-turbo` has been greatly improved since March. You may also consider using a smaller `max_tokens` to limit the amount of time the model spends creating the response.

Hey thanks, this is a good call-out. We'll discuss internally. For now that link should work. For SDK-specific vulns, you can also email [email protected].

What are some places you would expect to find this in a library like this? `CONTRIBUTING.md`?

Ah, terrific – we'll get that set up next week! Thank you so much @ericwb !

Got it. Very cool technique. Would you like me to add that to the readme?

Actually, I might be interested in rewriting the readme to be more explicit and explain more things, if you would like that? Right now, I feel you probably need to...

Okay, thanks, I'll try to take a look at reworking the readme soon!

This is fixed in our [upcoming v4](https://github.com/openai/openai-node/discussions/182), which includes conveniences for file uploads.

Really appreciate all the thought put into this @colinhacks ! I'm sadly at the end of a busy day and not able to do a thorough writeup, but in case...