You should write an agent • Hacker News Board

Re: You should write an agent

#251

Post by simonw » Fri, Nov 07, 2025, 6:45 AM UTC

robot-wrangler wrote: post #248

simonw wrote: post #139

Earlier quoted context omitted.

"Agents use Apis that I will need to pay for" Not if you run them against local models, which are free to download and free to run. The Qwen 3 4B models only need a couple of GBs of available RAM and will run happily on CPU as opposed to GPU. Cost isn't a reason not to explore this stuff.

> Not if you run them against local models, which are free to download and free to run .. run happily on CPU .. Cost isn't a reason not to explore this stuff. Let's be realistic and not over-promise. Conversational slop and coding factorial will work. But the local experience for coding agents, tool-calling, and reasoning is still very bad until/unless you have a pretty expensive workstation. CPU and qwen 4b will be…

Sure, you're not going to get anything close to a Claude Code style agent from a local model (unless you shell out $10,000+ for a 512GB Mac Studio or similar).

This post isn't about building Claude Code - it's about hooking up an LLM to one or two tool calls in order to run something like ping. For an educational exercise like that a model like Qwen 4B should still be sufficient.

Re: You should write an agent

#252

Post by Etheryte » Fri, Nov 07, 2025, 6:50 AM UTC

cyberpunk wrote: post #229

crystal_revenge wrote: post #225

Earlier quoted context omitted.

The problem with statements like these is that I work with people who make the same claims, but are slowly building useless, buggy monstrosities that for various reasons nobody can/will call out. Obviously I’m reasonably willing to believe that you are an exception. However every person I’ve interacted with who makes this same claim has presented me with a dumpster fire and expected me to marvel at it.

We have gpt-5 and gemini 2.5 pro at work, and both of them produce huge amounts of basically shit code that doesn’t work. Every time i reach for them recently I end up spending more time refactoring the bad code out or in deep hostage negotiations with the chatbot of the day that I would have been faster writing it myself. That and for some reason they occasionally make me really angry. Oh a bunch of prompts in and t…

On the sometimes getting angry part, I feel you. I don't even understand why it happens, but it's always a weird moment when I notice it. I know I'm talking to a machine and it can't learn from its mistakes, but it's still very frustrating to get back yet another here's the actual no bullshit fix, for real this time, pinky promise.

Re: You should write an agent

#253

Post by baq » Fri, Nov 07, 2025, 6:55 AM UTC

singularity2001 wrote: post #246

dave1010uk wrote: post #80

Two years ago I wrote an agent in 25 lines of PHP [0]. It was surprisingly effective, even back then before tool calling was a thing and you had to coax the LLM into returning structured output. I think it even worked with GPT-3.5 for trivial things. In my mind LLMs are just UNIX strong manipulation tools like `sed` or `awk`: you give them an input and command and they give you an output. This is especially true if y…

what's the point of specialized agents when you just have one universal agent that can do anything e.g. Claude

If you can get a specialized agent to work in its domain at 10% parameters of a foundation model, you can feasibly run locally, which opens up e.g. offline use cases.

Personally I’d absolutely buy an LLM in a box which I could connect to my home assistant via usb.

Re: You should write an agent

#254

Post by baq » Fri, Nov 07, 2025, 6:58 AM UTC

sumedh wrote: post #230

Uehreka wrote: post #218

Earlier quoted context omitted.

The reason a lot of people don’t do this is because Claude Code lets you use a Claude Max subscription to get virtually unlimited tokens. If you’re using this stuff for your job, Claude Max ends up being like 10x the value of paying by the token, it’s basically mandatory. And you can’t use your Claude Max subscription for tools other than Claude Code (for TOS reasons. And they’ll likely catch you eventually if you tr…

> catch you eventually if you try to extract and reuse access tokens What does that mean?

How do they know your requests come from Claude Code?

Re: You should write an agent

#255

Post by p0w3n3d » Fri, Nov 07, 2025, 7:01 AM UTC

Actually tool "ping 8.8.8.8" never quits unless running on windows. This can spawn many processes that kill the server.

This is one of the first production grade errors I've made when I started my programming. I had a widget that would ping the network, but every time someone went on the page, a new ping process would spawn

Re: You should write an agent

#256

Post by robot-wrangler » Fri, Nov 07, 2025, 7:11 AM UTC

simonw wrote: post #251

robot-wrangler wrote: post #248

Earlier quoted context omitted.

> Not if you run them against local models, which are free to download and free to run .. run happily on CPU .. Cost isn't a reason not to explore this stuff. Let's be realistic and not over-promise. Conversational slop and coding factorial will work. But the local experience for coding agents, tool-calling, and reasoning is still very bad until/unless you have a pretty expensive workstation. CPU and qwen 4b will be…

Sure, you're not going to get anything close to a Claude Code style agent from a local model (unless you shell out $10,000+ for a 512GB Mac Studio or similar). This post isn't about building Claude Code - it's about hooking up an LLM to one or two tool calls in order to run something like ping. For an educational exercise like that a model like Qwen 4B should still be sufficient.

The expectation that reasonable people have isn't fully local claude code, that's a strawman. But it's also not ping tools or the simple weather agent that tutorials like to use. It's somewhere in between, isn't that obvious? If you're into evangelism, acknowledging this and actually taking a measured stance would help prevent light skeptics from turning into complete AI-deniers. If you mislead people about one thing, they will assume they are being misled about everything

Re: You should write an agent

#257

Post by sanxiyn » Fri, Nov 07, 2025, 7:12 AM UTC

p0w3n3d wrote: post #255

Actually tool "ping 8.8.8.8" never quits unless running on windows. This can spawn many processes that kill the server. This is one of the first production grade errors I've made when I started my programming. I had a widget that would ping the network, but every time someone went on the page, a new ping process would spawn

If you look at the actual code, it runs ping -c 5. I agree ping without options doesn't terminate.

Re: You should write an agent

#258

Post by DeathArrow » Fri, Nov 07, 2025, 7:23 AM UTC

anonym29 wrote: post #64

ericd wrote: post #41

Absolutely, especially the part about just rolling your own alternative to Claude Code - build your own lightsaber. Having your coding agent improve itself is a pretty magical experience. And then you can trivially swap in whatever model you want (Cerebras is crazy fast, for example, which makes a big difference for these many-turn tool call conversations with big lumps of context, though gpt-oss 120b is obviously no…

Cerebras now has glm 4.6. Still obscenely fast, and now obscenely smart, too.

Aren't there cheaper providers of GLM 4.6 on Openrouter? What are the advantages of using Cerebras? Is it much faster?

Re: You should write an agent

#259

Post by simonw » Fri, Nov 07, 2025, 7:26 AM UTC

robot-wrangler wrote: post #256

simonw wrote: post #251

Earlier quoted context omitted.

Sure, you're not going to get anything close to a Claude Code style agent from a local model (unless you shell out $10,000+ for a 512GB Mac Studio or similar). This post isn't about building Claude Code - it's about hooking up an LLM to one or two tool calls in order to run something like ping. For an educational exercise like that a model like Qwen 4B should still be sufficient.

The expectation that reasonable people have isn't fully local claude code, that's a strawman. But it's also not ping tools or the simple weather agent that tutorials like to use. It's somewhere in between, isn't that obvious? If you're into evangelism, acknowledging this and actually taking a measured stance would help prevent light skeptics from turning into complete AI-deniers. If you mislead people about one thing…

I don't think I was being misleading here.

https://fly.io/blog/everyone-write-an-agent/ is a tutorial about writing a simple "agent" - aka a thing that uses an LLM to call tools in a loop - that can make a simple tool call. The complaint I was responding to here was that there's no point trying this if you don't want to be hooked on expensive APIs. I think this is one of the areas where the existence of tiny but capable local models is relevant - especially for AI skeptics who refuse to engage with this technology at all if it means spending money with companies they don't like.

Re: You should write an agent

#260

Post by DeathArrow » Fri, Nov 07, 2025, 7:27 AM UTC

You should write agents if you want to learn how agents work, if the problem you are trying to solve is not solved yet or if you are convinced that you will do much better job solving the problem again. Otherwise is just reinventing the wheel.