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

How I code with AI on a budget/free

wuu73.org

Post reply on HN
Print view View original

181–190 of 251 posts

Re: How I code with AI on a budget/free

#181

Post by indigodaddy »

ireadmevs wrote: post #104
sumedh wrote: post #89

Earlier quoted context omitted.

What is the catch?

> Beta technology disclaimer > Rovo Dev in the CLI is a beta product under active development. We can only support a certain number of users without affecting the top-notch quality and user experience we are known for providing. Once we reach this limit, we will create a waiting list and continue to onboard users as we increase capacity. This product is available for free while in beta. From https://community.atlassi…

Isn't this only available to a current Jira cloud/service subscription?

Re: How I code with AI on a budget/free

#182

Post by fwystup »

xvv wrote: post #52

As of today, what is the best local model that can be run on a system with 32gb of ram and 24gb of vram?

Qwen3-Coder-30B-A3B-Instruct-FP8 is a good choice ('qwen3-coder:30b' when you use ollama). I have also had good experiences with https://mistral.ai/news/devstral (built under a collaboration between Mistral AI and All Hands AI)

Re: How I code with AI on a budget/free

#186

Post by bongodongobob »

3036e4 wrote: post #132

Maybe optimistic, but reading posts like this makes me hopeful that AI-assisted coding will drive people to design more modular and sanely organized code, to reduce the amount of context required for each task. Sadly pretty much all code I have worked with have been giant messes of everything being connected to everything else, causing the entire project to be potential context for anything.

It's really very good at that. Frequently, I'll have something I've been working on over the years that has turned into an interconnected mess. "Split this code into modules of separated concerns". Bam, done. I used Claude for the first time last week and gave it a 2k line PowerShell script and it neatly pulled it apart into 5 working modules on the first try. Worked exactly the same, and ended up with better comments too.

Re: How I code with AI on a budget/free

#187

Post by bongodongobob »

chiwilliams wrote: post #26
chromaton wrote: post #12

If you're looking for free API access, Google offers access to Gemini for free, including for gemini-2.5-pro with thinking turned on. The limit is... quite high, as I'm running some benchmarking and haven't hit the limit yet. Open weight models like DeepSeek R1 and GPT-OSS are also made available with free API access from various inference providers and hardware manufacturers.

I'm assuming it isn't sensitive for your purposes, but note that Google will train on these interactions, but not if you pay.

I don't care. From what I understand of LLM training, there's basically 0 chance a key or password I might send it will ever be regurgitated. Do you have any examples of an LLM actually doing anything like this?

Re: How I code with AI on a budget/free

#188

Post by DrSiemer »

Ha, I'm working on a similar tool: https://github.com/DrSiemer/codemerger

Glad to see I'm not the only one who prefers to work like that. I don't need many different models though, the free version of Gemini 2.5 Pro is usually enough for me. Especially the 1.000.000 token context length is really useful. I can just keep dumping full code merges in.

I'll have a look at the alternatives mentioned though. Some questions just seem to throw certain models into logic loops.

Re: How I code with AI on a budget/free

#189

Post by saratogacx »

casparvitch wrote: post #137
mathiaspoint wrote: post #134

Earlier quoted context omitted.

LLMs will write code this way if you ask but you have to know to ask.

At that(/what) point does it become harder for a human to grok a project?

It depends if you're willing to drop the $30 for the super version :)

Re: How I code with AI on a budget/free

#190

Post by mattmanser »

bongodongobob wrote: post #186
3036e4 wrote: post #132

Maybe optimistic, but reading posts like this makes me hopeful that AI-assisted coding will drive people to design more modular and sanely organized code, to reduce the amount of context required for each task. Sadly pretty much all code I have worked with have been giant messes of everything being connected to everything else, causing the entire project to be potential context for anything.

It's really very good at that. Frequently, I'll have something I've been working on over the years that has turned into an interconnected mess. "Split this code into modules of separated concerns". Bam, done. I used Claude for the first time last week and gave it a 2k line PowerShell script and it neatly pulled it apart into 5 working modules on the first try. Worked exactly the same, and ended up with better comment…

So I've done that sort of refactoring a lot, albeit on real code in much bigger systems, not a script. Lots of coders won't do this, they'll just keep adding to the crap, crazy big module.

I always end up with a vastly smaller code base. Like 2000 lines turns into 800 lines or something like that.

Did that happen too or did the AI just do a glorified 'extract method', that any decent IDE can already do without AI?

I use AI, I'm not anti it, but on the other hand I keep seeing these gushing posts where I'm like 'but your ide could already do that, just click the quick refactoring button'.

Post reply on HN