Can already see the whisper model makings its way through the product :)
It's basically doing the same thing. I found that using API keys is also significantly cheaper than using the subscription with moderate usage.
Congrats on the release.
Do you then reference those open source apps?
https://gist.github.com/cohan/7d2abfa56b2dfdaae98bf70e84c622...
All of these UIs when there's a perfectly good command line right there! The CLI is always the best way for text.
> ai what is that song with moms spaghetti
"Lose Yourself" by Eminem
Sorted.
Something like
> ai give me an index match formula to link between sheets New and Current
different flavours: 'fix' acts as `thefuck` replacement in 30 lines of python
I imagine someone can do much better than I did in a few minutes, but yeah use the UI that already exists instead of sprinkling electron on something text based.
In future editions of CLI AI I'd imagine a --context flag might be useful, probably a --model to override that bit too, if anyone fancies doing this properly? :)
I’d assumed ChatGPT’s slow-typing was actually the model’s real-time output, streamed to the browser token-by-token. When I’ve made GPT3 API calls it’s worked like this, with streaming switched off I might need to wait ~20 seconds for a long response back.
I just tried your UI, and it’s so much faster! Was my assumption about real-time output wrong?
Great project, looking forward to using it more :)
Note for anybody else wondering, it's not open source, you have to download a binary. More FAQ by clicking the Gift (?) icon at the top and scrolling down.
Sarcasm?
Nothing dang can do though is hundreds of people hate it though. Things with actual security issues for example he'll likely just be quiet about it.
Theoretically, you should block any outgoing connections to the website domain (after it loads all necessary HTML and JS), and it should still work fine. "Theoretically" because it might attempt delay-loading some static assets, but you get the idea.
I can view web requests but let's say on the 365th web request it sends my API key to an unknown location. How would I know if this was closed source?
Your example is valid, but it's like asking "how can I know that my iPhone doesn't record me while I'm sleeping?"
It's a static web app, you can host it yourself, data is stored locally on your browser, API requests are made directly to OpenAI API without any middle server.
It has some more convenient features that make your that experience way better. Like search chat history, prompt library, integrations, etc.
Would love to hear all the feedback!