Oh man, I’ve been waiting for the V1.5 update! All cars now have the new tyre physics.

For those unaware they found out they’ve essentially had a fairly critical issue with the model for years where systems were feeding the model competing information at the same time causing weirdness in physics behavior.

This is a huge change in handling.

While all of that is great and true it’s almost irrelevant because adding gif support doesn’t hamstring the privacy of the application.

SimpleX is newer, has arguably better privacy and already supports gif keyboards etc…

I use them both honestly, but I wouldn’t pretend missing some basic features is because of some higher privacy principle.

Can’t say I’ve had huge issues with casting in general for coming up on a decade now.

Oh boy, that’ll be interesting. I quite like the wet haha.

Not currently unfortunately, I just started work on adding PaLM API support in some form.

I’ll have to look into LLaMA after that is complete, I hadn’t even thought about that one yet haha.

If you’ve created a new account and generated an api key I think you just need to go Billing —> overview and setup your payment method.

I think you get $20 credit for signing up after that and your key is active.

Edit - the default model will be 3.5 as well. I think you have to request GPT4 access still. But they’re giving out access pretty quick these days I think.

Edit 2 - Actually it looks like GPT4 should be available from the start as well now. Nice!

Thanks!

Good question, I hadn’t really thought about it before but I think an export is possible. Conversations are stored in your browsers local storage, adding the ability to export/import seems entirely possible.

It might even be possible to generate a web link on export that you can use to load conversations on another device.

As far as server side storage goes personally I’d like to handle as little of other peoples data as possible even if it’s just AI chat conversations. It’s not out of the question though, I just need to look into it further.

Edit - I mention here I will add the ability to export. I’ve also added a GitHub Issue with the feature request.

Now I just have to not be lazy and do it eventually.

I’m going to have to look into that, thanks for the heads up!

Mainly trying both of them out for a bit to figure out which I prefer.

I actually wrote MinimalGPT as a project for myself because I found using ChatGPT annoying for certain things.

It’s just a minimal chat client where you provide an OpenAI API key for GPT and you’re off to the races.

Conversations and all data (besides the messages you send to OpenAI) are stored locally to your browser.

https://minimalgpt.app, it’s also a PWA application so you can save it to your mobile Home Screen for a full app experience.

GitHub Repo with a fleshed out readme for more info.

It’s a great audio library system, I use PodGrab to subscribe to podcasts and download them and AudioBookshelf for playback and organization etc…

Correct!

If anyone runs across this in the future and doesn’t want to revive a dead thread feel free to message me!

I prefer SimpleX to Signal, Telegram and Matrix tbh.

Should work on any platform, Brave might be blocking some scripts.

If it works on the desktop or chrome mobile etc… it’s probably just Brave being overly aggressive.

Turbo is just what they call their 3.5 model for some reason.

Odd it’s not working for you, seems alright for others at the moment. The only other thing I can think of is something blocking JavaScript or the browser LocalStorage.

Well that is just ridiculous.

You might double check the API key is correct.

Also make sure you have access to the model you’ve selected, you may not have GPT4 access by default if you’re using that.

I believe it’s GPT3.5 by default and you can request GPT4 access.

Thanks! I’m using Autoblip and Auto clutch, one of those might be doing that?

One day I’ll get a nice H shifter haha

It is a progressive web app so you can save it to your home screen to behave like an app on both iOS and Android.