I know the idea is you save money by saving time but each of these AI services want another $30/mo and they all do kinda the same thing powered by the same models. I’m just so subscription fatigued.
back
4 comments
I hate to do this but this is the type of app that is basically the new todo app. I create small agents like this all time in about 15 seconds, with a simple prompt like:
You are an expert Tailwind CSS developer that I will ask for help. You may need to google the latest docs from Tailwind here: link.
And I get all the help I need.
> You are an expert Tailwind CSS developer that I will ask for help.
Is that part of the prompt necessary anymore? I feel that was a version 3 thing.
My prompts have been getting less verbose & I've been finding little value in introductory phrases, correct grammar or spelling.
I think so. I notice on Meta.ai that if I ask a follow up a question, it often loses context. Cordoning it off to you are this and only this could possibly stop it from straying.
What framework/library/app do you use to execute these agents?
Just make that custom thing on OpenAi website, takes a second.
I don’t do anything locally lately, but I believe you’d either have to pad your prompt with something like what I showed you above or mess with the system prompt.
The stuff is there in the ollama docs, someone else can probably give you more details.
Better yet, just ask gpt about all this lol.
Edit: I might be misusing the word Agent here.
> Edit: I might be misusing the word Agent here.
Yeah I assumed you were using some sort of multi-agent framework where you give agents different prompts/tools and they work together. You just mean a custom GPT.
I was half hoping there was a command line app that could do that, though I also forgot custom GPTs can browse the internet.
I don’t have the hardware to run good models, but if you can run a local one then you can write a small script to set a system prompt with ollama via the command line. Haven’t tried it, but sounds like what you want.
what a great tip, thanks
> I’m just so subscription fatigued.
I can help you with that for only $9.99 a month!
Honestly a FREE and simple web service for managing subscriptions sounds like a great idea. It could sent out emails every month saying how much you're paying for all your subscriptions, for how long you've been subbed to them, etc.
If someone builds this, please do not ask for yet another subscription. At least make it self-hostable and charge for the hosted one.
I think it already exists (and yes it's a subscription based software haha). I think it's called rocketmoney?
The world needs a way to pay for thin AI wrappers without having to turn them into subscription services. There are lots of potential applications where an indie developer can add value on top of LLM's, but can't subsidize GPT-4 usage for the world. OpenAI still doesn't approve of stored bring-your-own-key solutions, nor allow monitoring-and-approval of API costs at the individual consumer level (the new project keys are a step in that direction). The GPT store covers some use cases, and hopefully will get both monetization and a way to expose non-chat interfaces. But until then, everyone with a solution that needs to pass through API costs has to make pricing decisions inconvenient to everyone (in this case, asking too high a price; in other cases, risking overuse or having to heavily restrict usage).
Would you prefer pay-as-you go instead?
I'm working on an LLM powered SaaS and thinking about having some kind of prepaid credit system instead of a subscriptions. I personally hate subscriptions with fiery passion.
Thanks. I might think about a PAYG pricing for this. This is likely a tool you'd use every now and then. Maybe $1 an hour. This means someone using it 30 hours a month pays the fill price (and maybe I cap it) but if you are using it that much, you are getting value.
I would love it if someone would write an article on the economics of LLM pricing.