Show HN: Use ChatGPT, Bing, Bard and Claude in One App
github.com
github.com
One stylistic thing that I like about ChatGPT vs Bard's web interface for code is that way it progressively types compared to the instant display. I find that I am able to read the code and get some learning of what it is doing as it is typing compared to reading a big block after the fact.
Alas, I use the streaming mode, because it gives an indicator that the connection to the model is still live, and you can kind of estimate how much longer you'll have to wait for the reply to end. With "batched" mode, you just sit there for anywhere between few seconds and few minutes, wondering if it's still generating response, or if the API connection broke again.
It can also be annoying when I made request a small change and it rewrites the entire block of code compared to only displaying the section I want. I think I could prompt it better in those cases by saying "only show me the code changes" though.
I think it's mostly my laziness. I found GPT-4 with default system message good enough for most use cases, so I tend to just switch over to it, start a new conversation, and blurt my request. Setting specialized "characters" for my requests? Too much hassle. Typing in a proper, explicit request to just give me diffs? Too much writing, breaks flow.
Ironically, I'm both too lazy for giving GPT-4 this kind of editing guidance, while I'm also wasting too much time catering to conversational style.
This already happened. It's called TypingMind.com; I'm happy paying user. It's main selling point is that it isn't dog slow and isn't trying to take down my browser with its bloat, the way OpenAI chat interface is. "Character" creation and selecting is lovely, but half the time I'm too lazy to switch away from the default.
Just imagine it's a human on the other side typing or speaking, and you're getting to hear / see what they type as they type it.
It is, in fact, extremely strange for humans to have the experience of sitting waiting for a complete utterance before processing: it feels more like sending a letter than talking.
There were even chat systems that worked like this, including (I think?) the Unix talk command and one of the popular ICQ-era chat apps (maybe it was ICQ itself?).
Yes. I imagine it and I shudder from suddenly experiencing how annoying that would be.
> There were even chat systems that worked like this, including (I think?) the Unix talk command
Correct. I've used `talk` in high school (and a colorized variant called `ytalk.qq`). It was a fun experience, and I miss it a bit - since then, the only software I used that kind of reproduced it, was Etherpad.
Now, the way `talk` conversations and real-life conversations are tolerable, whereas watching someone (a human or a bot) typing 'till completion is frustrating, is in the speed of the feedback loop. When talking (or `talk`ing), I can interrupt you when I see you saying things I already know. You can interrupt me too. This happens at the level of phonemes/characters, and allows the conversation to flow dynamically - one moment, we'd have a rapid back-and-forth, another moment, I'd listen to you very carefully, etc.
With normal messengers of today, if I were to see you typing (instead of having the - also annoying, but for other reasons[0] - pencil icon), but had no way to interrupt you - I'd be frustrated all the time, being able to know with good confidence what you want to say while you're 1/3rd through your message. Natural language, especially in conversations, is stupidly redundant. I'd just Alt+TAB to HN or something, and wait for you to finish[1].
This is my experience with GPTs. I often want them to just stop typing, but if I hit "Stop", I might just break the response in the wrong moment, creating cleanup work for myself. The side effect of the streaming chat UIs being dog slow makes this even worse: there's no telling how many seconds it'll take for my "Stop" to register. For some reason, this gets both worse and less predictable as the conversation gets longer.
--
[0] - All kinds of interpersonal nonsense, but a big factor is that, with a bot, you know it's actually generating a message and will finish soon (unless the connection fails). With humans? Who the hell knows. They may type you an essay. Or type two sentences for 5 minutes. Or get distracted by cat. Or just be screwing with you. With humans, half the time I'm considering looking for ways to disable typing indicators.
[1] - Which is exactly what I do most the time with people and typing indicators. And GPTs.
this will let chats update in the background aka you can spin up multiple chats at once (though i don’t do this often)
like yeah it’s paid but the dev is very committed and i’m very pleased
not sure I understand how. it isn't "typing" either, it's just slower
May not be a moat, but just a velocity thing, I haven't felt a need to switch out of fomo.
You can also "create a bot" with a custom prompt and share it - the social features of sharing/bookmarking snippets of conversations is pretty fun.
Is that just a meme response now or is there more to it?
The market (and technology) is very immature. We have no idea what potential usecases, integrations, or models will ultimately dominate. Even if there is a single one-model-to-rule-them-all there is still going to be potential for smaller/almost-as-good models to be succession by doing direct integrations with various business or B2C usecases.
The chatbot UI is just one potential usecase that's popular now. That might have dominance in pure brand recognition and userbase, but it's not like they have network-effects or other lock-in either (besides maybe custom API integrations).
Try creating your own browser and see how well it does.
It’s like debating whether “the internet” is a moat, in 1990.
Tech is never a moat. That’s not new or interesting. Business processes can be, brand can be, scale can be. And it is far far far far far far too early to even think about moats in the AI business.
This is what I’m talking about. It’s such a limited perspective on what LLMs mean as products/services. Everyone is so focused on the ChatGPT consumer interface they can’t see beyond it to the thousand niche business usecases. It’s as much an enterprise platform (meaning heavy custom usecases), in addition to a broad consumable API system for developers, and then the Google style search/chat Q&A UI.
Just because Poe/Claude is experimenting with an early consumer mobile app doesn’t mean that’s the business they ultimately plan to be in.
The network/monopoly effects of Google/Chrome/IE for pure consumer plays might make sense but we have no idea what the technical underpinning might look like in a decade. It could be just WebKit plus a few others or it could be more like Databases where you hit a baseline plateau for performance but there’s a hundred businesses built off all the variations.
Because of the second element of HNs domain name. Its a startup-community focussed forum, moat is an important business consideration, but especially so for startups.
There were sites like this that had several search engines side by side in frames so you could compare the results returned from all of them at once.
Will be really interesting to see how all of this plays out.
It grinds my gears a little bit when people pretend that Google came out of nowhere and invented a new paradigm for accessing information and making money by selling ads there.
It was a well recognized problem they solved with Page rank!
https://www.gnod.com/search/ai
Feedback is welcome.
So far I know about 3. I would expect there to be more and more over time. I will keep adding them to the page.
edit: This seems to just be links to other search engines... is there any actual benefit to using this site rather than visiting the engines directly?
You can also click on "more engines" and add Google or whichever engine you usually use and make it your one-stop-dashboard to search/ask the web.
README says they were inspired by ChatHub
Does anyone know of a tool for using Claude-100k? I don't have API access yet.