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

You should write an agent

fly.io

Post reply on HN
Print view View original

71–80 of 409 posts

Re: You should write an agent

#71

Post by zahlman »

tptacek wrote: post #56
zahlman wrote: post #53

Earlier quoted context omitted.

> They know all the flags and are generally better at interpreting tool output than I am. In the toy example, you explicitly restrict the agent to supply just a `host`, and hard-code the rest of the command. Is the idea that you'd instead give a `description` something like "invoke the UNIX `ping` command", and a parameter described as constituting all the arguments to `ping`?

Honestly, I didn't think very hard about how to make `ping` do something interesting here, and in serious code I'd give it all the `ping` options (and also run it in a Fly Machine or Sprite where I don't have to bother checking to make sure none of those options gives code exec). It's possible the post would have been better had I done that; it might have come up with an even better test. I was telling a friend onlin…

Also to be clear: are the schemas for the JSON data sent and parsed here specific to the model used? Or is there a standard? (Is that the P in MCP?)

Re: You should write an agent

#73

Post by nowittyusername »

8note wrote: post #69
nowittyusername wrote: post #35

I agree with the sentiment but I also recommend you build a local only agent. Something that runs on llama.cpp or vllm, whatever... This way you can better grasp the more fundamental nature of what LLM's really are and how they work under the hood. That experience will also make you realize how much control you are giving up when using cloud based api providers like OpenAI and why so mane engineers feel that LLM's ar…

ive been trying this for a few week, but i dont at all currently own hardware good enough to be useful for local inference. ill be trying again once i have written my own agent, but i dont expect to get any useful results compared to using some claude or gemini tokens

My man, we now have llms that are anywhere between 130 million to 1 trillion parameters available for us to run locally, I can guarantee there is a model for you there that even your toaster can run. I have a RTX 4090 but for most of my fiddling i use small models like Qwen 3 4b and they work amazing so there's no excuse :P.

Re: You should write an agent

#74

Post by 8note »

tptacek wrote: post #34
robot-wrangler wrote: post #29

> Another thing to notice: we didn’t need MCP at all. That’s because MCP isn’t a fundamental enabling technology. The amount of coverage it gets is frustrating. It’s barely a technology at all. MCP is just a plugin interface for Claude Code and Cursor, a way of getting your own tools into code you don’t control. Write your own agent. Be a programmer. Deal in APIs, not plugins. Hold up. These are all the right concern…

I think my thing about MCP, besides the outsized press coverage it gets, is the implicit presumption it smuggles in that agents will be built around the context architecture of Claude Code --- that is to say, a single context window (maybe with sub-agents) with a single set of tools. That straitjacket is really most of the subtext of this post. I get that you can use MCP with any agent architecture. I debated whether…

i treat MCP as a shorthand for "schema + documentation, passed to the LLM as context"

you dont need the MCP implementation, but the idea is useful and you can consider the tradeoffs to your context window, vs passing in the manual as fine tuning or something.

Re: You should write an agent

#75

Post by mrkurt »

threecheese wrote: post #57

Does anyone have an understanding - or intuition - of what the agentic loop looks like in the popular coding agents? Is it purely a “while 1: call_llm(system, assistant)”, or is there complex orchestration? I’m trying to understand if the value for Claude Code (for example) is purely in Sonnet/Haiku + the tool system prompt, or if there’s more secret sauce - beyond the “sugar” of instruction file inclusion via comman…

Claude Code is an obfuscated javascript app. You can point Claude Code at it's own package and it will pretty reliably tell you how it works.

I think Claude Code's magic is that Anthropic is happy to burn tokens. The loop itself is not all that interesting.

What is interesting is how they manage the context window over a long chat. And I think a fair amount of that is serverside.

Re: You should write an agent

#76

Post by dannyobrien »

tptacek wrote: post #49
jacquesm wrote: post #47

Earlier quoted context omitted.

Interesting. You have to wonder if all the tools that is based on would have been written in the first place if that kind of thing had been possible all along. Who needs 'grep' when you can write a prompt?

My long running joke is that the actual good `jq` is just the LLM interface that generates `jq` queries; 'simonw actually went and built that.

https://github.com/simonw/llm-jq for those following along at home

https://github.com/simonw/llm-cmd is what i use as the "actually good ffmpeg etc front end"

and just to toot my own horn, I hand Simon's `llm` command lone tool access to its own todo list and read/write access to the cwd with my own tools, https://github.com/dannyob/llm-tools-todo and https://github.com/dannyob/llm-tools-patch

Even with just these and no shell access it can get a lot done, because these tools encode the fundamental tricks of Claude Code ( I have `llmw` aliased to `llm --tool Patch --tool Todo --cl 0` so it will have access to these tools and can act in a loop, as Simon defines an agent. )

Re: You should write an agent

#77

Post by SatvikBeri »

chemotaxis wrote: post #13
riskable wrote: post #11

It's interesting how much this makes you want to write Unix-style tools that do one thing and only one thing really well. Not just because it makes coding an agent simpler, but because it's much more secure!

You could even imagine a world in which we create an entire suite of deterministic, limited-purpose tools and then expose it directly to humans!

Half my use of LLM tools is just to remember the options for command line tools, including ones I wrote but only use every few months.

Re: You should write an agent

#78

Post by Zak »

> You only think you understand how a bicycle works, until you learn to ride one.

I bet a majority of people who can ride a bicycle don't know how they steer, and would describe the physical movements they use to initiate and terminate a turn inaccurately.

https://en.wikipedia.org/wiki/Countersteering

Re: You should write an agent

#79

Post by rbren »

Spoiler: it's not actually that easy. Compaction, security, sandboxing, planning, custom tools--all this is really hard to get right.

We're about to launch an SDK that gives devs all these building blocks, specifically oriented around software agents. Would love feedback if anyone wants to look: https://github.com/OpenHands/software-agent-sdk

Re: You should write an agent

#80

Post by dave1010uk »

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 you use something like `llm` [1].

It then seems logical that you can compose calls to LLMs, loop and branch and combine them with other functions.

[0] https://github.com/dave1010/hubcap

[1] https://github.com/simonw/llm

Post reply on HN