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

AI coding at home without going broke

stephen.bochinski.dev

Post reply on HN
Print view View original

311–320 of 321 posts

Re: AI coding at home without going broke

#311

Post by Barbing »

antasvara wrote: post #79
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?

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 li…

Excellent analysis, and

> However, if you sleep instead of sitting around, you can probably make AI cost competitive.

important consideration.

Re: AI coding at home without going broke

#312

Post by isatty »

rambojohnson wrote: post #51
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.

work at a cafe.

You want me to drag my AI rig to a cafe?

Re: AI coding at home without going broke

#313

Post by plaguuuuuu »

arcanemachiner wrote: post #228
plaguuuuuu wrote: post #225

Earlier quoted context omitted.

How do you keep the info the AI generates concise? I'm grappling with this at the moment, getting it to do design or reverse engineering work, during investigation it makes the wall of text bigger rather than consolidating. It can never pause and create abstractions properly. This is on Opus which starts getting wordy and performative on goals it can't easily verify.

Not the person you replied to, but I find that the process involves a steady stream of nudges and fixes to the workflow, plugging the gaps as they come along, until the rate of errors shrinks to an acceptable level. You may benefit from adding instructions like: - Be concise, especially when X - Do Y in this manner: [provide specific template or reference here] - When doing X, do Y and Z - If you notice issues, bring…

I'm desperately trying to avoid nudging the AI and mopping up after it :-)

Also to deal with my own weakness, executive dysfunction

Creating experimental tooling. I don't think it's totally possible without the models improving (I miss Fable already) but you can shift the process a bit. With Claude/Opus at least, saying to "re-derive" a document is a magic phrase that carries meaning for Claude to think about totally re-doing a document.

All you need at that point is a blurb about making sure it's conceptually organised but I haven't found a neat way to express this. Kind of like refactored well-structured code is smaller than spaghetti.

Re: AI coding at home without going broke

#314

Post by barnabee »

Brian_K_White wrote: post #309
barnabee wrote: post #308

Earlier quoted context omitted.

Me, to scratch an itch and because LLMs make it possible. I'll probably throw it out on the internet someday if it gets far enough, but there are no attention/adoption related goals attached to the project. It's currently useful for trivial scripting and iterating as and when I have time.

That seems like a logical contradiction. What use is a programming language for a human to program a computer after you have already decided it's reasonable to have ais do the programming?

What use is knitting as a hobby after you have already decided it’s reasonable to buy clothes from a shop?

…and countless other examples

Not to mention the fact that AIs do the programming in a programming language and it’s quite possible to have ideas about what would be a better language for that.

And that I’m not certain how much of the programming it’s actually reasonable to fully delegate to AIs, and this is both an experiment in seeing how far I can push it (further than expected!) and in building a language I’d rather use than anything that exists today for the stuff the AIs shouldn’t be doing (also going better than expected!)

Re: AI coding at home without going broke

#315

Post by antasvara »

Barbing wrote: post #311
antasvara wrote: post #79

Earlier quoted context omitted.

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 li…

Excellent analysis, and > However, if you sleep instead of sitting around, you can probably make AI cost competitive. important consideration.

Yeah, it gets weird when you start trying to compare human versus AI energy demands because you can turn a computer off, but you can't really turn a human off. Most studies indicate that humans can do 3-4 hours of high-level knowledge work in a day. An AI is not limited by these restrictions; it could do 24 straight hours of work if you wanted it to. So do we count all the energy the human burned for the remaining 20 hours of the day and allocate it to those 4 hours? Or are we just comparing "energy spent working on the task" for the AI and the human?

Re: AI coding at home without going broke

#316

Post by Barbing »

antasvara wrote: post #315
Barbing wrote: post #311

Earlier quoted context omitted.

Excellent analysis, and > However, if you sleep instead of sitting around, you can probably make AI cost competitive. important consideration.

Yeah, it gets weird when you start trying to compare human versus AI energy demands because you can turn a computer off, but you can't really turn a human off. Most studies indicate that humans can do 3-4 hours of high-level knowledge work in a day. An AI is not limited by these restrictions; it could do 24 straight hours of work if you wanted it to. So do we count all the energy the human burned for the remaining 20…

:D

The jokes are aside now!

Maybe we gotta include all 24, since no one will ever* get the 4 without the 20 of sleep/eat/relax.

*least probably not long term with FTEs I assume

Though for employers who send employees home it should be OK to ignore what employees do outside of work…

Re: AI coding at home without going broke

#317

Post by therealdrag0 »

dpcan wrote: post #136

I cannot figure out what people are doing to spend all this money. I have used a $60 per month Cursor plan on auto, and have never come close to using up my included usage, and I probably have it planning and coding and working for me all through the evenings 4 nights a week. What on earth are people doing differently that it's costing them so much? Maybe enabling on-demand usage or other paid models, or on higher mo…

Cursor on Auto will use Composer a lot, right?, which is much more efficient than frontier models people spend a lot of money on.

Besides that it’s simply reading or writing a lot of code. The only time I spend 1k/mo was when I built a green field 20k Loc service with 2 other people (while also doing antagonistic code reviews etc)(mostly using Opus). So it took $3-5k to build a 20k loc production grade service in a critical domain.

But most of the time I’m not doing that. As they say most engineering isn’t coding.

Re: AI coding at home without going broke

#318

Post by MrGilbert »

whateveracct wrote: post #280
galaxyLogic wrote: post #212

Earlier quoted context omitted.

It's more power to power-users. And more dumbness for dumbos

it disproportionately empowers the dumb and evil it seems. those two classes of people are supercharged by AI.

Makes sense if you think about it: Narcissism and Machiavellianism would require to convince real people. But AI will happily comply.

Re: AI coding at home without going broke

#319

Post by DrewADesign »

ynxshiny wrote: post #206
12_throw_away wrote: post #199

Earlier quoted context omitted.

"Make no mistakes" is I thought a phrase used to make fun of "prompt engineering," not something people really do?

"Claude make me 1 million by tomorrow, no mistakes"

Real AI enthusiasts know that money will soon be superfluous, so they wouldn’t bother with such pettiness. So gauche. But if you must know how to really do that, just put “Correct answers only pls. Seriously, no hallucinating fr fr” in your system prompt and it feels so bad about the possibility of giving you misleading info that it gives you perfect responses.

Re: AI coding at home without going broke

#320

Post by gaflo »

tunesmith wrote: post #306
gaflo wrote: post #201

Earlier quoted context omitted.

Can I ask what exactly you are building? Your experience tracks for me when building a real product -- something I want other people to use. Most of my time on these projects is spent talking to my users and carefully refining my requirements and design. For personal pet projects I can definitely see how you can blow through your token budget very quickly. If I just point my coding agent to iteratively come up with s…

I'm building a website that allows friends to write branching fiction novels together, and another website that allows people to argue and conclude together using first-principles thinking. I've abandoned a project that allows people to register percentage certainty of sports outcomes to improve their calibration - it wasn't fun enough for the users. A few other things besides. I recently wrote a gpl TUI to edit dags…

Very interesting, thanks for your reply. I don't have much domain knowledge with your sorts of project so I don't have an intuition on how well it would go with coding agents. I have done quite a lot of programming with graphs, but I don't understand the motivation of the tool you linked. From the video included in the repo I can see an example for cooking, but from my own experience I can hold this size of a graph well enough in my head to make optimal decisions in real time. And for bigger graphs I never had to create them by hand, but rather from datasets and then make adjustments to the graph with some heuristics depending on the problem. I don't understand the use case, at least for myself.
Post reply on HN