I was annoyed by the default OpenAI ChatGPT slow-typing animation and logging me out every day, so I built a new UI client on top of its API. 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 libr…
Show HN: I built a better UI for ChatGPT
81–90 of 95 posts
Re: Show HN: I built a better UI for ChatGPT
#82[1] https://twitter.com/adamdangelo/status/1631714221171023873
Re: Show HN: I built a better UI for ChatGPT
#83Earlier quoted context omitted.
It is open source. Your browser retrives all the JS and html sources. Even if it were somehow closed source, it doesn't really matter. You can view web requests and other, and see for yourself.
What Just because you can see HTML and JS that THE BACKEND SENT doesn't mean you can see the actual logic (code)
Theoretically, you should be able to block any outgoing connections to the website domain (after it loads all necessary HTML and JS), and it should still work fine. Saying "theoretically" because it might attempt delay-loading some static assets, but you get the idea. No idea how this specific website functions, as I haven't looked deep into it yet, but that's the principle behind "static websites" like this one.
Re: Show HN: I built a better UI for ChatGPT
#84Earlier quoted context omitted.
The ability to reverse engineer the source through the browser doesn't make something qualify as open source anymore than reverse engineering a binary with some other tool. 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?
It's not similar to a binary file, since re a binary file is a pain in the ass and looking at JS with some obfuscation is much easier. Your example is valid, but it's like asking "how can I know that my iPhone doesn't record me while I'm sleeping?"
Re: Show HN: I built a better UI for ChatGPT
#85Add serpapi on top of that, and you might just become my phone’s most used app.
Re: Show HN: I built a better UI for ChatGPT
#86Earlier quoted context omitted.
It's a static web app, you can host it yourself 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.
Entrust your AI key to a closed binary? Bot what could possibly go wrong?
Re: Show HN: I built a better UI for ChatGPT
#87Earlier quoted context omitted.
Don't worry there are only about 10,000 people working on similar apps right now ;)
I whipped up a quick cli script myself haha 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.
Re: Show HN: I built a better UI for ChatGPT
#88Earlier quoted context omitted.
I whipped up a quick cli script myself haha 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.
CLI is a UI, too.
Re: Show HN: I built a better UI for ChatGPT
#89Earlier quoted context omitted.
I whipped up a quick cli script myself haha 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.
CLI is a UI, too.
If anyone fancies a tinker I imagine future editions of a CLI AI having a --context to include former prompts*, --stfu|--concise to make it respond concisely (as I was originally just responding "I know mate, haha" I also need this flag adding), probably a --model= to override that bit too, maybe even a --preamble=./prompt.txt
... it definitely needs a --json flag to prompt and enforce "I only want json and I'll parse it out of the response myself if I need to"
* Not just keeping a buffer and re-sending it, I believe context asks GPT to summarise the conversation so far and then uses the output of that for context memory. It'd need some tinkering.
I'll get round to it myself eventually, for now being able to ask little things like "is it defence or defense" and "what company owns the coco pops brand" is doing me just fine
I did realise I can now potentially pipe things into and out of GPT too, but have yet to come up with a use other than outputting through TTS e.g.
> ./ai is it defence or defense | festival --tts