AI coding at home without going broke
stephen.bochinski.dev
AI coding at home without going broke
1–10 of 321 posts
Re: AI coding at home without going broke
#2I find just going via Deepseek's platform API directly, using their V4 flash model, and hooking into a harness like Opencode more than acceptable. Think I've spent maybe $10 over a couple of weeks.
I did explore self-hosting models but hardware right now is just too expensive.
Re: AI coding at home without going broke
#3> The first is to self host. You buy the machine, run open source models locally, and pay nothing per token after that.
Power is not free.
What I’ve found is that you’re basically paying a premium for privacy, and that’s worth it for me.
Re: AI coding at home without going broke
#4> The first is to self host. You buy the machine, run open source models locally, and pay nothing per token after that. Power is not free. What I’ve found is that you’re basically paying a premium for privacy, and that’s worth it for me.
[dead]
Re: AI coding at home without going broke
#5Fixed-price monthly plans ought to be sufficient for most people who actually review their spec and code, for building production-grade software that stand the test of time. A careful spec+review+iteration takes time, resetting the usage quota. Granted, security audits uses tokens too.
If you still need more tokens, odds that you're vibecoding unmaintainable throwaway trash.
Re: AI coding at home without going broke
#6> The first is to self host. You buy the machine, run open source models locally, and pay nothing per token after that. Power is not free. What I’ve found is that you’re basically paying a premium for privacy, and that’s worth it for me.
>> Power is not free.
There's actually an interesting thought experiment here: if it takes you a full day to build something that AI would otherwise build in a day, do you end up using more power, or less? What is the break-even point, purely from a power consumption perspective?
Re: AI coding at home without going broke
#7> The first is to self host. You buy the machine, run open source models locally, and pay nothing per token after that. Power is not free. What I’ve found is that you’re basically paying a premium for privacy, and that’s worth it for me.
Actually if you have solar, it kind of is.. so prIvAt AI compute gets defacto cheaper during the day?
Re: AI coding at home without going broke
#8Ha just wrote a post[1] about a sort of 4th option - max out cheap compute to create more tangible things that can be used/run locally.
Re: AI coding at home without going broke
#9> The first is to self host. You buy the machine, run open source models locally, and pay nothing per token after that. Power is not free. What I’ve found is that you’re basically paying a premium for privacy, and that’s worth it for me.
>> Power is not free. There's actually an interesting thought experiment here: if it takes you a full day to build something that AI would otherwise build in a day, do you end up using more power, or less? What is the break-even point, purely from a power consumption perspective?
What would you do for the rest of the day, power off your devices and go for a long bike ride?
Re: AI coding at home without going broke
#10> The first is to self host. You buy the machine, run open source models locally, and pay nothing per token after that.
In the good ol' days, we bought machines not only to run stuff, but to experiment.
I understand today experiments are limited. Inference is reasonable, fine-tuning is either niche or a stretch, and base training is impossible.
*That is bound to change*, and when it does, there will be an avalanche of hobbysts and amateurs poking at base training. They'll find optimizations no one found before, synthetize data no one ever imagined to synthetize, and when that happens we'll start getting libre models.
So, yeah. Right now, buying the machine doesn't pay off that well, unless you want to pioneer this stuff in severe adverse conditions (hardware prices inflated, etc). Eventually, it will.