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

261–270 of 321 posts

Re: AI coding at home without going broke

#261

Post by Brian_K_White »

barnabee wrote: post #258
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…

Yeah I agree. I’m “vibe engineering” an entire (non-trivial) programming language, toolchain, and standard library, as well as some smaller side projects. I leave OpenCode implementing entire milestones unattended for long periods regularly. I feel like I’d need to not have a job or a life if I wanted to exhaust the OpenAI $100 plan using GPT 5.5 xhigh, and I’ve found it insanely capable. That said, while I don’t rea…

Who is the consumer of the new language?

Re: AI coding at home without going broke

#262

Post by alecco »

ryeguy wrote: post #203
alecco wrote: post #181

Earlier quoted context omitted.

DeepSeek API gave 6x to 8x better caching rate for inputs over OpenRouter (even chosing DeepSeek as provider). And some of the cheaper providers are using FP4 quantizations. https://openrouter.ai/deepseek/deepseek-v4-flash-20260423#pr... After complaints the cached read is not listed anymore in that page, you have to click one by one. All providers for DeepSeek V4 Flash charge ~$0.02 while DeepSeek provider is $0.002…

Openrouter's pricing via the deepseek provider is the same as the official deepseek api for both flash and pro and for cached and uncached tokens. It's literally the same api. And no, cache rates are not different if you're going through the official deepseek provider. The only way caching rates can drop is if you let openrouter fully control routing by preferring uptime or something, and then it might bounce you bet…

Last month I had this issue. Others confirmed. On X people say OpenRouter messes with headers or something (this I can't confirm).

Re: AI coding at home without going broke

#263

Post by novia »

I want to be able to experiment with tweaking model weights and seeing the outcomes and i want to be able to finetune open source models. What's the best way to experiment with that without breaking the bank?

Re: AI coding at home without going broke

#264

Post by anon373839 »

novia wrote: post #263

I want to be able to experiment with tweaking model weights and seeing the outcomes and i want to be able to finetune open source models. What's the best way to experiment with that without breaking the bank?

If you want to experiment with fine tuning small models, you can actually do that with free Google Colab instances. Unsloth.ai has written a bunch of guides on this.

Re: AI coding at home without going broke

#265

Post by sermakarevich »

I started using brain -> workers approach for coding.

-- Brain is expensive smart model from claude subscription, Fable 5 when it was available, Opus now.

-- Worker is a local model (qwen3.6:46B), deployed in 36GB GPU, Opencode + Ollama.

Brain is responsible for analysis/design and task creation. Task should be made simple and clear so the worker can handle it. Worker does the coding. Brain validates and create a fix task when required. Atm fix to task ration is ~ 1:20.

If no available GPU at home - qwen3.6 is quite cheap on clouds.

Its rather experimental setup, out of curiosity, but it works better than I would expect it to. This allows me running 3 coding agents non stop for the 4-th day atm. Here I explain how I got there: https://news.ycombinator.com/item?id=48520757

Re: AI coding at home without going broke

#266

Post by lee_ars »

mappu wrote: post #222
lee_ars wrote: post #205

Earlier quoted context omitted.

I'm currently working through research and testing for an article on Ars about the Spark and what things one might do with it, and I've kind of stumbled into a two-LLM agentic setup with Qwen3.6-35B-A3B (via nvidia/Qwen3.6-35B-A3B-NVFP4) as the planning agent and the FP8 version of Qwen3-Coder-30B-A3B-Instruct (Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8) as the coding agent that the planner delegates tasks down to. I'm st…

Long time Ars reader, looking forward to your article (and have a few DOS games to reverse in mind already)! Is this with a Ghidra MCP or some other technique? And why two models - did you try using Qwen3.6-35B-A3B for everything? (Or 27B or a bigger model since you have the RAM for it)

I haven't paired it with Ghidra MCP; because the games are relatively tiny (I'm starting with one of my personal favorites, Karl Buiter's Sentinel Worlds I: Future Magic, which is like I went with a pair of models primarily just to see if I could make it work. It's been fine, but I'm going to rip out the smaller coder model today and try it with just the bigger thinking Qwen model wearing both planner & coder hats in the same loop, just with only the bigger model running.

I'm learning a lot, and primarily what I'm learning is that I'm not a developer and this stuff gets real complex real fast, especially in chasing down all the details needed to make sure I'm taking advantage of the spark hardware!

Re: AI coding at home without going broke

#267

Post by Eridrus »

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…

Codex is much more subscription-efficient than Claude.

Having said that, I think there is a question of how far we can push this and not collapse under the weight of tech debt created, e.g. https://openai.com/index/open-source-codex-orchestration-sym...

I think the dream is basically that you go and file a bunch of Linear tickets, and then you come back a day later to evidence of the tickets being resolved and the code merged. I don't think we're super there yet (See: Anthropic's regular bugs in everything), but this is the future that people are trying to get to and to some extent the question is: is there anywhere we can apply this to now sanely? How does this frontier evolve?

Re: AI coding at home without going broke

#268

Post by toilet »

dofm wrote: post #48
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.

Luckily I needed a new laptop and I bought an M1 Max secondhand from a friend quite cheaply because it was fast enough to recompile something else I am interested in. So for me, there is no additional hardware cost; it was acquired in replacement. I run the AI models at home on this kit because I want to; I'll use openrouter if I need to. I accept the economics of this article are right. But I feel so incredibly sad…

This was very touching to read, thank you for writing this dofm. I feel the same in a lot of ways. -toilet

Re: AI coding at home without going broke

#269

Post by vitally3643 »

giardini wrote: post #230
vitally3643 wrote: post #141

Earlier quoted context omitted.

That's because you're treating the problem as an engineer instead of an "influencer" or "10xer" or whatever. You're treating it as a problem to be solved with engineering and AI is merely a tool to do so. It is, in my experience, vanishingly rare for an engineer to have a problem that needs to be solved with multiple hours of unattended AI code generation. I've only found one single application where it makes even th…

I thought most products had legal provisions that prohibit reverse engineering?

Yes, and most have the same legal power as the statement: By reading this comment you accept my terms and conditions and agree to pay me ten thousand dollars per word read.

Re: AI coding at home without going broke

#270

Post by Schiendelman »

frizlab wrote: post #152
rbalicki wrote: post #149

Earlier quoted context omitted.

I'll add another use case for letting an AI go ham: many small, atomic refactors where the name of the game is never breaking anything. My personal OSS projects don't have the scale to necessarily make this worth it, but at work I run three pipelines using Barnum ( https://barnum-circus.github.io/ ). First, one that ingests files, identifies refactors (from a pre-approved list), and places a precise description of th…

I recently in $COMPANY had a coworker try fable to do a refactor where not breaking anything was the game. It broke something at the first PR. I think we’re not there yet.

One of the best things you can do is start by having it do unit test coverage for existing behavior. A refactor with no tests breaks things pretty much no matter who does it, because they don't know what the right behavior is.
Post reply on HN