AI coding at home without going broke • Hacker News Board

Re: AI coding at home without going broke

#71

Post by CamperBob2 » Sat, Jun 13, 2026, 5:55 PM UTC

theossuary wrote: post #49

Catloafdev wrote: post #27

Earlier quoted context omitted.

If you want frontier-level, the economically reasonable option is OpenRouter or a direct sub to frontier-of-your-choice. The reality is that they do not offer configurations that would allow a consumer to run that much VRAM on a single setup to protect datacenter margins. Apple used to, and they stopped, those devices are going for ~$20k+ each on ebay now. You can get very, very capable models on a 3090/4090/5090/600…

I truly think by 2028 we'll have integrated chip systems that'll be able to run opus 4.8 level models at ~500 watts at acceptable performance. Honestly I think now is the worst time to invest in AI hardware. Get your harness ready and processes perfected with hosted models, and wait a few years to buy hardware to transition to running models locally

Honestly I think now is the worst time to invest in AI hardware.

That position is not without its own risks, though. Maybe Opus 4.8 will run on a single chip by 2028... and maybe you won't be allowed to touch it.

And what if Xi makes a play for Taiwan? That would be stupid, but so was invading Ukraine with tanks from Temu, and it still happened.

Re: AI coding at home without going broke

#72

Post by jrm4 » Sat, Jun 13, 2026, 5:56 PM UTC

pianopatrick wrote: post #41

petra wrote: post #28

Earlier quoted context omitted.

Maybe one possible path(to make weaker models highly capable) is making the job of the llm as easy as possible. I wonder if part of the solution is building/finding the right libraries, with the right documentation/language/API(one that plays well with LLM's) and maybe creating some synthetic data around them - to make it very easy for the llm. And maybe there could be a business model around creating those libraries…

I think as well there might be "algorithms" that can work with local LLMs. With local LLMs there is a small context window, but not that much cost per token. So perhaps there is a way to do lots of small prompts that work in a sequence to produce a result. Like perhaps you could produce 5 versions of a piece of code, and then compare them to choose the best. Also if the local LLMs can call tools, maybe you can use st…

Yes. LITERALLY THIS. I do this! Not hypothetical.

I'll write a detailed prompt for a function, hand it off to 5 or so models (all of which are on my local machine), wait about 5 min and then compare.

Re: AI coding at home without going broke

#73

Post by jacobgold » Sat, Jun 13, 2026, 5:56 PM UTC

simonw wrote: post #55

jacobgold wrote: post #35

"Around $400 a month of plans buys roughly $2800 of API usage at list prices, which is a real bargain right up until you hit the ceiling." I realize this text is just slop but it never stops being a "real bargain" at any point. And it's more like $200/mo for $4000+/mo in tokens. You can also buy additional subscriptions. There's no sense in running local models or doing anything else as long as VCs (and soon the publ…

SemiAnalysis pushed this to the limit and managed to get $8,000 of tokens from a $200/month Anthropic plan and $14,000 of tokens from a $200/month OpenAI plan: https://twitter.com/SemiAnalysis_/status/2064815044085318040

Yeah, although that is pushing every rate limit and no one knows what happens if you do that consistently? I think $4,000/mo is probably a good estimate for an individual dev doing synchronous coding agent work.

Re: AI coding at home without going broke

#74

Post by manfre » Sat, Jun 13, 2026, 5:56 PM UTC

OutOfHere wrote: post #5

Fixed-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.

With access to view usage for my org and conversations with developers, I think much of the high token usage is a result of people not knowing how to right size the model for the given task. The trend seems to be to pick the most powerful model and use it for everything. Based upon git metrics, I'm one of the top performing engineers at my org and I've yet to run into any overage or throttling on the $200/mo anthropic sub.

Re: AI coding at home without going broke

#75

Post by Yoric » Sat, Jun 13, 2026, 5:57 PM UTC

enraged_camel wrote: post #6

isatty wrote: post #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.

>> 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?

I'm assuming that you need to feed the human being (i.e. you) regardless of whether you use that human being for writing code or not. So, by this metric, there is simply no breaking even point. The cost of human + AI is always going to be higher than the cost of human.

Re: AI coding at home without going broke

#76

Post by Yoric » Sat, Jun 13, 2026, 5:57 PM UTC

mwcampbell wrote: post #33

I invested about $4,000 in an NVIDIA DGX Spark several months ago. 128 GB of unified RAM, and the NVIDIA GB10 chip. With the RAM, the several CPU cores, and the 4 TB NVMe SSD, it's a very capable ARM64 Linux computer even without the GPU, and so far I've mostly been using it as such. But I wonder, what's the most capable model, specifically for coding, that can run well on that hardware?

https://www.canirun.ai/?status=tight might answer that question

Re: AI coding at home without going broke

#77

Post by sheremetyev » Sat, Jun 13, 2026, 5:58 PM UTC

tunesmith wrote: post #47

I feel like I must have plateued and don't know what to do next to level up. I'm currently on the $100/month codex plan and it seems fine using 5.5-xhigh all the time. I think of what to do next, have a chat session to determine exactly what to ask for up to the point of being ready to implement, and then codex churns on a commit-sized task whereupon I briefly check it on my local dev server. If necessary I ask for a…

> I don't want to give it "dangerous" access to my entire mac

I'm running Claude/Codex inside native macOS sandbox, configured with a simple script - https://github.com/sheremetyev/sandfence

always in "bypass permissions" mode - it works until task is solved, sometime 1 hour or more (which includes running tests etc)

Re: AI coding at home without going broke

#78

Post by Yoric » Sat, Jun 13, 2026, 5:58 PM UTC

atreids wrote: post #2

I 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.

Directly at DeepSeek? It was my understanding (but I didn't check) that some other AI operators were providing (some of?) DeepSeek's model for cheaper prices.

Still, that's interesting. What do you get for that price? Only coding, or also e.g. image generation?

Re: AI coding at home without going broke

#79

Post by antasvara » Sat, Jun 13, 2026, 5:59 PM UTC

enraged_camel wrote: post #6

isatty wrote: post #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.

>> 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?

Studies on grandmaster chess players indicate that at most you burn 10% more calories when engaged in deep thought than when you're at rest. So the energy "attributable" to an hour of knowledge work is like 10 calories (average sedentary calorie burn is like 80-100 per hour; add a max of 10% for the thinking gets you 8-10 calories). A pound of potatoes is like a buck and is about 320 calories. So you're looking at like 3 cents an hour at most to cover that energy burn. It's definitely even less; I certainly don't think as hard as a grandmaster chess player.

Then, assume power costs 20 cents per kilowatt hour (US avwrage) To match the human 3 cents per hour, you need an average of 150 watts of power drawn per hour. That's in the range of a budget graphics card, but not much past there.

However, if you sleep instead of sitting around, you can probably make AI cost competitive. Sleeping drops your metabolic rate by more, and lying down in bed (as opposed to sitting) also reduces calorie burn. Combined, you can reduce your burn by like 30 calories an hour. At the new 9 cents per hour human cost, you can afford to run a higher end graphics card at ~450 watts per hour. That puts you in RTX 3090 range.

Re: AI coding at home without going broke

#80

Post by evrydayhustling » Sat, Jun 13, 2026, 6:02 PM UTC

dofm wrote: post #17

enraged_camel wrote: post #6

Earlier quoted context omitted.

>> 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?

If an identical task takes a day on both sides, then the human route uses less energy, surely. Brains are thousands or maybe even millions of times more fuel-efficient than computers and you are alive for the whole day either way, right? You probably eat about the same even. The reason executives think AI is more efficient is that it more space efficient than a human and doesn't demand to be paid or work only a set n…

Brains are efficient, but civilized humans aren't. In the USA, adults consume at a rate of about 10kW -- only 1-2% of that being the human's metabolism, the rest being HVAC, electrical devices, etc.

For comparison, a modern frontier model like Gemini 3.5 Pro consumes about 15kW -- so only about 1.5x the fully loaded human. In an 8h workday, that model would crank through ~80M tokens (~$5k at API prices). That's ~4 major refactors of a 10k LOC codebase, so probably not a very realistic comparison to a single human dev.

I think a more useful comparison, based on my experience, is that an engineer with AI support can get one 8h day's worth of unassisted work done in 1h. So, the 25 kWh consumed during collaboration (conservatively assuming I keep the GPU hot for the whole hour) frees up the remaining 70 kWh I'll draw down for the day to be spent in some other way.