Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT Store Launch

news.ycombinator.com

Post reply on HN
Print view View original

61–69 of 69 posts

Re: GPT Store Launch

#61

Post by ianbicking »

pona-a wrote: post #57
ianbicking wrote: post #43

I'm sure there will be improvements, but making a custom GPT a few weeks ago I was very unimpressed: 1. The GPT builder itself didn't feel like it was a well-tuned prompt (i.e., the prompt they use to guide prompt creation). It created long-winded prompts that left out information and didn't pay attention to what I said. Anything I enter into the GPT builder interface is probably very important! 2. The quotas are fai…

Maybe you can hack some context management and hidden state with custom functions? The scratch buffer can literally be an endpoint that returns OK and has a field like "plain: list[str]", assuming it keeps function call data in memory. Better context memory can be done perhaps by reminding in the system prompt to always call getPinned() each 5 messages, perhaps... But yes, the whole thing does seem bound to regress t…

Yeah, you can definitely do a lot with Actions, and I've seen some examples of that. But if I want to deploy a service then I'd rather make a nice frontend along with it, and Custom GPTs aren't that! (But the fact I don't have to monetize just to support OpenAI API costs is still very appealing.)

At the moment Actions are pretty brutal to the experience, with constant confirmations and they seem to halve both the speed and the quota since I think it takes two GPT responses, one to assemble the Action and another to react to the result. Using a Custom GPT that uses extensive actions means sitting and watching it think, waiting to hit a button, then sitting and watching it think for a long time, only to run out of quota before you get to anything interesting.

Re: GPT Store Launch

#62

Post by objectivetruth »

ceejayoz wrote: post #55
mattbrewsbytes wrote: post #54

Earlier quoted context omitted.

That doesn’t track. I develop a custom model by paying them $x/month and they give me a discount based on usage? If somehow my new custom gpt goes viral and gets lots of usage I don’t see how that is connected with more money, if that is their intent. Its not really clear how this is a store or how money is changing hands here.

> If somehow my new custom gpt goes viral and gets lots of usage I don’t see how that is connected with more money, if that is their intent. They're charging everyone using your model, per API call made. They write you a check for X% of that resulting revenue.

[dead]

Re: GPT Store Launch

#63

Post by Yusefmosiah »

callalex wrote: post #60
Yusefmosiah wrote: post #51

Earlier quoted context omitted.

I'm building Choir. Choir humanizes ChatGPT, augmenting the AI response with messages from humans that are relevant to your prompt. Each prompt you write into Choir gets saved to our database, so the more usage Choir gets, the smarter the Choir collective intelligence becomes. Check it out at https://choir.chat — it redirects directly to the Choir custom GPT.

What is that useful for?

It’s useful if you want a more creative output. Good for brainstorming, thinking out loud, and refining ideas.

Re: GPT Store Launch

#64

Post by replwoacause »

Anybody else having issues with the app on iOS where the model changes from 4 to 3.5 after the first response? As a paid user, it’s very frustrating to have my preferences overridden and the quality of 3.5 answers is comparatively lower. In fact almost so poor as to be useless, so the mobile app is currently unusable.

Re: GPT Store Launch

#65

Post by replwoacause »

kdtsh wrote: post #53
yosito wrote: post #37

It will be interesting to see if anyone has made any worthwhile custom GPTs. I've tried making custom GPTs and, to be frank, I found the functionality extremely basic and barely more effective than just copy/pasting a custom prompt.

AutoExpert[1] is indispensable to my use of ChatGPT now, and I’ve found that the GPT release is ‘better’ now than the custom instructions based release. If you haven’t used it I highly recommend it. [1] https://github.com/spdustin/ChatGPT-AutoExpert

I’ve seen a few of these floating around. I think one was called professor synapse. I honestly couldn’t discern an improvement when I tried it. Is this one better? Can anybody comment on whether this approach has merit or if it’s mostly hype?

Re: GPT Store Launch

#66

Post by debian3 »

replwoacause wrote: post #64

Anybody else having issues with the app on iOS where the model changes from 4 to 3.5 after the first response? As a paid user, it’s very frustrating to have my preferences overridden and the quality of 3.5 answers is comparatively lower. In fact almost so poor as to be useless, so the mobile app is currently unusable.

Mine stay on v4

Re: GPT Store Launch

#67

Post by esjeon »

I might be overthinking, but this "store" thing would not work that well. I blame GPT here, because I'm quite certain that GPT itself can be used to analyze and clone GPT apps, perhaps fully automatically. Even those extra knowledge added by app developers would get extracted through jailbreak, which also can be automated. The store will end up being littered with auto-generated clones.

Re: GPT Store Launch

#68

Post by qingcharles »

ianbicking wrote: post #43

I'm sure there will be improvements, but making a custom GPT a few weeks ago I was very unimpressed: 1. The GPT builder itself didn't feel like it was a well-tuned prompt (i.e., the prompt they use to guide prompt creation). It created long-winded prompts that left out information and didn't pay attention to what I said. Anything I enter into the GPT builder interface is probably very important! 2. The quotas are fai…

I use several custom GPTs that I built inside GPT Pro and they have doubled my productivity over using GPT alone, which had already doubled my productivity.

Every time I get a response that is off from the custom then I give it a nudge to edit its configuration. The main issue is that its configuration doesn't have enough space for all the rules and it likes to ditch more minor rules when you give it something extra to remember.

Re: GPT Store Launch

#69

Post by david_shi »

minimaxir wrote: post #5
neverrroot wrote: post #2

This looks like an interesting opportunity to learn something new. Anyone knows about any open source projects in this area?

GPTs are essentially a proprietary moat-building of several open-source workflows, most especially system prompt engineering, tool-usage, and RAG. Unfortunately there's no magic open-source solution since there's a lot of moving pieces involved that are bespoke to a given use case, and the ones that claim to be magic are libraries like LangChain, which aren't.

There really should be open source versions.

It's perplexing why there aren't, especially when the individual components are relatively straightforward (code interpreter, RAG, search, function calling, image generation).

Post reply on HN