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

151–160 of 251 posts

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

#151

Post by stillsut »

statenjason wrote: post #29
andai wrote: post #9

My experience lines up with the article. The agentic stuff only works with the biggest models. (Well, "works"... OpenAI Codex took 200 requests with o4-mini to change like 3 lines of code...) For simple changes I actually found smaller models better because they're so much faster. So I shifted my focus from "best model" to "stupidest I can get away with". I've been pushing that idea even further. If you give up on ag…

Aider as a non-agentic coding tool strikes a nice balance on the efficiency vs effectiveness front. Using tree-sitter to create a repo map of the repository means less filesystem digging. No MCP, but shell commands mean it can use utilities I myself am familiar with. Combined with Cerebras as a provider, the turnaround on prompts is instant; I can stay involved rather than waiting on multiple rounds of tool calls. It…

Just added a fork of aider that does do agentic commands: https://github.com/sutt/agent-aider

In testing I've found it to be underwhelming at being an agent compared to claude code, wrote up some case-studies on it here: https://github.com/sutt/agro/blob/master/docs/case-studies/a...

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

#152

Post by simonw »

ta1243 wrote: post #139
bahmboo wrote: post #72

Earlier quoted context omitted.

I was going to downvote you but you are adding to the discussion. In this context this is free from having to spend money. Many of us don't have the option to pay for models. We have to find some way to get the state of the art without spending our food money.

I don't trust any AI company not to use and monetise my data, regardless how much I pay or regardless what their terms of service say. I know full well that large companies ignore laws with impunity and no accountability.

I would encourage you to rethink this position just a little bit. Going through life not trusting any company isn't a fun way to live.

If it helps, think about those company's own selfish motivations. They like money, so they like paying customers. If they promise those paying customers (in legally binding agreements, no less) that they won't train on their data... and are then found to have trained on their data anyway, they wont just lose that customer - they'll lose thousands of others too.

Which hurts their bottom line. It's in their interest not to break those promises.

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

#153

Post by simonw »

pyman wrote: post #88
PeterStuer wrote: post #62

Earlier quoted context omitted.

Very nice article and thx for the update. I would be very interested in an in dept of your experiences of differences between Roo Code and Cline if you feel you can share that. I've only tried Roo Code (with interesting but mixed results) thus far.

Just use lmstudio.ai, it's what everyone is using nowadays

LM Studio is great, but it's a very different product from an AI-enabled IDE or a Claude Code style coding agent.

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

#154

Post by simonw »

ya3r wrote: post #74
radio879 wrote: post #16

I am the person that wrote that. Sorry about the font. This is a bit outdated, AI stuff goes at high speed. More models so I will try to update that. Every month so many new models come out. My new fav is GLM-4.5... Kimi K2 is also good, and Qwen3-Coder 480b, or 2507 instruct.. very good as well. All of those work really well in any agentic environment/in agent tools. I made a context helper app ( https://wuu73.org/a…

Have you seen Microsoft's copilot? It is essentially free openai models

Which of their many Copilot products do you mean?

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

#155

Post by simonw »

hgarg wrote: post #51
radio879 wrote: post #16

I am the person that wrote that. Sorry about the font. This is a bit outdated, AI stuff goes at high speed. More models so I will try to update that. Every month so many new models come out. My new fav is GLM-4.5... Kimi K2 is also good, and Qwen3-Coder 480b, or 2507 instruct.. very good as well. All of those work really well in any agentic environment/in agent tools. I made a context helper app ( https://wuu73.org/a…

Qwen is totally useless any serious dev work.

Which Qwen? They have over a dozen models now.

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

#156

Post by hpincket »

radio879 wrote: post #98
hpincket wrote: post #69

Earlier quoted context omitted.

I am developing the same opinion. I want something fast and dependable. Getting into a flow state is important to me, and I just can't do that when I'm waiting for an agentic coding assistant to terminate. I'm also interested in smaller models for their speed. That, or a provider like Cerebras. Then, if you narrow the problem domain you can increase the dependability. I am curious to hear more about your "surgical" t…

well, most of the time, I just dump the entire codebase in if the context window is big and its a good model. But there are plenty of times when I need to block one folder in a repo or disable a few files because the files might "nudge" it in a wrong direction. The surgical context tool (aicodeprep-gui) - there are at least 30 similar tools but most (if not all) are CLI only/no UI. I like UIs, I work faster with them…

aicodeprep-gui looks great. I will try it out

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

#157

Post by alpaca128 »

simonw wrote: post #152
ta1243 wrote: post #139

Earlier quoted context omitted.

I don't trust any AI company not to use and monetise my data, regardless how much I pay or regardless what their terms of service say. I know full well that large companies ignore laws with impunity and no accountability.

I would encourage you to rethink this position just a little bit. Going through life not trusting any company isn't a fun way to live. If it helps, think about those company's own selfish motivations. They like money, so they like paying customers. If they promise those paying customers (in legally binding agreements, no less) that they won't train on their data... and are then found to have trained on their data any…

> they wont just lose that customer - they'll lose thousands of others too

No, they won't. And that's the problem in your argument. Google landed in court for tracking users in incognito mode. They also were fined for not complying with the rules for cookie popups. Facebook lost in court for illegally using data for advertising. Did it lose them any paying customer? Maybe, but not nearly enough for them to even notice a difference. The larger outcome was that people are now more pissed at the EU for cookie popups that make the greed for data more transparent. Also in the case of Google most money comes from different people than the ones that have their privacy violated, so the incentives are not working as you suggest.

> Going through life not trusting any company isn't a fun way to live

Ignoring existing problems isn't a recipe for a happy life either.

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

#158

Post by ghxst »

mathiaspoint wrote: post #135
andai wrote: post #9

My experience lines up with the article. The agentic stuff only works with the biggest models. (Well, "works"... OpenAI Codex took 200 requests with o4-mini to change like 3 lines of code...) For simple changes I actually found smaller models better because they're so much faster. So I shifted my focus from "best model" to "stupidest I can get away with". I've been pushing that idea even further. If you give up on ag…

I use a 500 million parameter model for editor completions because I want those to nearly instantaneous and the plugin makes 50+ completion requests every session.

What editor do you use, and how did you set it up? I've been thinking about trying this with some local models and also with super low-latency ones like Gemini 2.5 Flash Lite. Would love to read more about this.

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

#159

Post by stuart73547373 »

radio879 wrote: post #16

I am the person that wrote that. Sorry about the font. This is a bit outdated, AI stuff goes at high speed. More models so I will try to update that. Every month so many new models come out. My new fav is GLM-4.5... Kimi K2 is also good, and Qwen3-Coder 480b, or 2507 instruct.. very good as well. All of those work really well in any agentic environment/in agent tools. I made a context helper app ( https://wuu73.org/a…

(relevant self promotion) i wrote a cli tool called slupe that lets web based llm dictate fs changes to your computer to make it easier to do ai coding from web llms https://news.ycombinator.com/item?id=44776250

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

#160

Post by badlogic »

mathiaspoint wrote: post #135
andai wrote: post #9

My experience lines up with the article. The agentic stuff only works with the biggest models. (Well, "works"... OpenAI Codex took 200 requests with o4-mini to change like 3 lines of code...) For simple changes I actually found smaller models better because they're so much faster. So I shifted my focus from "best model" to "stupidest I can get away with". I've been pushing that idea even further. If you give up on ag…

I use a 500 million parameter model for editor completions because I want those to nearly instantaneous and the plugin makes 50+ completion requests every session.

Can you share which model you are using?
Post reply on HN