I just bought it. Very nice, does what you would expect.
I was surprised at how much easier it was to use a native interface and have everything work so smoothly. I like the GUI touches (icons for new conversations, etc.). Very mac-like.
Out of curiosity, what does a native app offer in this context that using ChatGPT in a browser tab doesn't? I understand you can add shortcuts such as opening it and starting a new chat, but outside of that?
I was hoping that since this uses the API and is (I think?) its own implementation of the chat interface that it might be less confined by the guardrails in place on the chatGPT. But it appears to be similarly subject to moderation:
"I'm sorry, but I cannot comply with your request to recall any of Malcolm Tucker's profanity-laden tirades. As an AI language model, I am programmed to maintain a respectful and appropriate tone at all times, and using offensive language would not be in line with my programming. However, I can assist you with any other questions or tasks you may have."
Thank you for creating this software, and for making it a one-time purchase rather than a subscription. Big breath of fresh air.
On a side note, I was a stand-alone app like this was available for MidJourney, too. I really rather dislike using that powerful service either through Discord or a browser. /rant
What sort of data (if any) do you, the developer, collect?
Very cool.
I'd love it if it gave me more info about the differences between some of the available models. I've been using GPT4 exclusively from the web interface; I don't know why I might select GPT4 vs GPT4-0314. I believe I do know why I want to use 32k, but others might not.
Basically, I'd want an explanation as to how these differ from what's available in the ChatGPT web-app.
The default temperature is 0.0 -- again I'd want to know what the web app is using to know how I might want to use this setting.
edit: I guess an answer is my API key is only valid for 3.5 anyway. I'll try this again when I get API access to 4 I guess, but another suggestion would be to check capabilities when I paste the API key in and let me know which ones I have available.
Looks good. I bought MacGPT (https://www.macgpt.com), but sure, I'll buy this too and see how it compares. Hopefully it has quick access so I can summon it with a keyboard shortcut! :)
Will it run on OS 10.13? And: Any plans for integrating audio? (Whisper speech to text and Elevenlabs or something as TTS. Should have a general toggle for when you want to work silently. And shouldn’t read code or tables.)
3 hr after post, 0 comments, 8 upvotes:
Sorry, the discount code you wish to use has expired.
welp
This is cool, I like native apps better. Are there any features with ChatGPT Plus on web that are not supported in this (because it's the API)?
I would really love if this had some kind of plugin system so I could also point it at other models (such as a locally run llama.cpp)
Just tried it out and really like streaming support!
I would love being able to edit prompts and "branch" conversations like on the web app.
How much will I be spending on OpenAI token / API while using this vs while using the chat webapp? What has been your experience?
Just bought it but it turns out I can't use it with Monterey :-(
LaTeX rendering is a fantastic idea! Looks really nice.
This is really nice, you had my attention at native app - then sold me on the decent rendering of markdown, syntax etc...
I love that it's a 100% native application (no Electron/Chrome garbage etc...), so refreshing to see an unbloated app these days. The whole app is only about 11MB, and right now is only using 40MB of memory.