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

Building for an audience of one: starting and finishing side projects with AI

codemade.net

Post reply on HN
Print view View original

31–40 of 70 posts

Re: Building for an audience of one: starting and finishing side projects with AI

#31

Post by sicher »

citizenpaul wrote: post #29

>The age of actually finishing side projects is here This is a really good summary of how I've experienced AI put into words. I'm not really sure how this can be monetized though. I'm not going to burn $200-1k per day on agents to do some side projects that have been on the back burner. The only reason I'm doing it now is the heavily subsidized or free available models all over the place.

I'm paying for claude max which is 90 euros a month. It's just enough for my needs. I typically run 2 agents in parallel and seldom run out of tokens.

Re: Building for an audience of one: starting and finishing side projects with AI

#32

Post by sicher »

citizenpaul wrote: post #29

>The age of actually finishing side projects is here This is a really good summary of how I've experienced AI put into words. I'm not really sure how this can be monetized though. I'm not going to burn $200-1k per day on agents to do some side projects that have been on the back burner. The only reason I'm doing it now is the heavily subsidized or free available models all over the place.

Oh, I think I misunderstood. Do you mean if we paid the real cost of the compute it would be the numbers you mention?

Re: Building for an audience of one: starting and finishing side projects with AI

#33

Post by RugnirViking »

ath3nd wrote: post #21
echelon wrote: post #20

Earlier quoted context omitted.

Anyone who hasn't tried AI for coding absolutely should. This is the future. I don't think we'll ever manually write code again. It's just so much faster.

> This is the future. NFTs and crypto were also the future. > I don't think we'll ever manually write code again. It's just so much faster. More work for the people who like to fix tech debt.

> NFTs and crypto were also the future.

I find this the least convincing argument ever. Its only a gotcha if you assume all/most of the people excited about one were excited about the other. Personally I never met a real person who gave a shit about crypto, much less nfts. But AI interest is everywhere, with it roughly 50/50 in my life of people who are uneasy with it vs use it regularly.

I don't disagree about monumentous amounts of tech debt and risk being created. Its my hope for my own job and skills being relevant going into the future. I do like playing with it, understanding it as a tool. But it is just a tool, not a machine god, and regularly fallible.

Re: Building for an audience of one: starting and finishing side projects with AI

#34

Post by realharo »

embedding-shape wrote: post #28
realharo wrote: post #17

Earlier quoted context omitted.

Usually online communities have dedicated days for such things. Like a "side project Sunday" or such, with one large thread.

HN has that every day, and a dedicated section for it: Show HN. Link in the top bar :)

Yeah, but that's not the same, as most readers will just skip over that. What I said is more similar to HN's monthly "who's hiring" threads or "what are you working on" threads. Like https://news.ycombinator.com/item?id=46937696. I find those much more interesting.

Re: Building for an audience of one: starting and finishing side projects with AI

#35

Post by concats »

> Sidenote: I wonder what's going to happen when the crazy money runs out and Anthropic, OpenAI & co have to start charging for more than it costs them to run the models. Hopefully by then the open source models will have caught up?

How brutal will the enshittification phase of these products be?

Will the 10x cost or whatever be something that future employers will have to pay, or will it be a more visible impact for all of us? Assuming no AGI scenario here and the investments will have to be paid back with further subscription services like today.

I really hope Open Source (Open Weights) keep up with the development, and that a continuation of Moore's Law (the bastardized performance per € version) makes local models increasingly accessible.

Re: Building for an audience of one: starting and finishing side projects with AI

#36

Post by theteapot »

Right now I'm trying to get an AI (actually two ChatGPT and Grok) to write me a simple HomeAssistant integration that blinks a virtual light on and off driven by a random boolean virtual sensor. I just started using HomeAssistant and don't know it well. +2H and a few iterations in, still doesn't work. Winning.

Re: Building for an audience of one: starting and finishing side projects with AI

#37

Post by rustyhancock »

canada_dry wrote: post #9

This is what I've been doing for a couple years now: having AI help to code/test projects that I've had in my long TODO list but would never realistically started/completed. AI is now pretty capable of producing decent code if your specifications are decent. I still think that non-programmers are going to have a tough time with vibe coding. Nuances and nomenclature in the language you are targeting and programming de…

I've a similar history of AI use as you but every so often I simply describe what I want and try out what it creates. Honestly in these past 2 years the pace of improvement has been stunning.

Yesterday I was inside one of the tools that a just build it prompt created and I asked it to use a NewType pattern for some of the internals.

It wasn't until I was in bed that I thought why? If I'm never reading that code and the agent doesn't benefit from it? Why am I dragging my cognitive baggage into the code base?

Would a future lay vibe coder care what a New type pattern is? Why it helps? Who it helps?

I think the pedagogy of programming will change so that effective prompting will be more accessible.

Re: Building for an audience of one: starting and finishing side projects with AI

#38

Post by mvcosta91 »

theteapot wrote: post #36

Right now I'm trying to get an AI (actually two ChatGPT and Grok) to write me a simple HomeAssistant integration that blinks a virtual light on and off driven by a random boolean virtual sensor. I just started using HomeAssistant and don't know it well. +2H and a few iterations in, still doesn't work. Winning.

Forget both of them and throw everything at my boi Opus 4.6.

Re: Building for an audience of one: starting and finishing side projects with AI

#39

Post by ainch »

concats wrote: post #35

> Sidenote: I wonder what's going to happen when the crazy money runs out and Anthropic, OpenAI & co have to start charging for more than it costs them to run the models. Hopefully by then the open source models will have caught up? How brutal will the enshittification phase of these products be? Will the 10x cost or whatever be something that future employers will have to pay, or will it be a more visible impact for…

Is it proven that they serve the models at cost? Amodei has said that Anthropic's models make back their training cost - the reason they're so deep in the red is because they're investing substantially more in subsequent runs, and R&D dwarfs inference cost[1]. If the tech plateaus I would expect to see a lot of that R&D spend move into just powering inference.

[1] https://epoch.ai/data-insights/openai-compute-spend

Re: Building for an audience of one: starting and finishing side projects with AI

#40

Post by lsp »

theteapot wrote: post #36

Right now I'm trying to get an AI (actually two ChatGPT and Grok) to write me a simple HomeAssistant integration that blinks a virtual light on and off driven by a random boolean virtual sensor. I just started using HomeAssistant and don't know it well. +2H and a few iterations in, still doesn't work. Winning.

HomeAssistant is probably doing too much for what you need. Imo it's not a good piece of software. https://nodered.org/ is maybe a better fit. Or just some plain old scripts.
Post reply on HN