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

How to code Claude Code in 200 lines of code

mihaileric.com

Post reply on HN
Print view View original

161–170 of 249 posts

Re: How to code Claude Code in 200 lines of code

#161

Post by handfuloflight »

joshmlewis wrote: post #116

This is cool but as someone that's built an enterprise grade agentic loop in-house that's processing a billion plus tokens a month, there are so many little things you have to account for that greatly magnify complexity in real world agentic use cases. For loops are an easy way to get your foot in the door and is indeed at the heart of it all, but there are a multitude of a little things that compound complexity rath…

> I should start a blog with my experience from all of this.

Please do.

Re: How to code Claude Code in 200 lines of code

#163

Post by nl »

prodigycorp wrote: post #30
qsort wrote: post #14

Earlier quoted context omitted.

Obviously modern harnesses have better features but I wouldn't say it invalidates the mental model. Simpler agents aren't that far behind in performance if the underlying model is the same, including very minimal ones with basic tools. I'd say it's similar to how a "make your own relational DB" article might feature a basic B-tree with merge-joins. Yeah, obviously real engines have sophisticated planners, multiple jo…

You’re not wrong but I still think that the harness matters a lot when trying to accurately describe Claude Code. Here’s a reframing: If you asked people “what would you rather work with, today’s Claude Code harness with sonnet 3.7, or the 200 line agentic loop in the article with Opus 4.5, which would you choose?” I suspect many people would choose 3.7 with the harness. Moreover, that is true, then I’d say the artic…

This is SO wrong.

I actually wrote my own simple agent (with some twists) in part so I could compare models.

Opus 4.5 is in a completely different league to Sonnet 4.5, and 3.7 isn't even on the same planet.

I happily use my agent with Opus but there is no world in which I'd use a Sonnet 3.7 level model for anything beyond simple code completion.

Re: How to code Claude Code in 200 lines of code

#164

Post by misternugget »

libraryofbabel wrote: post #35

It's a great point and everyone should know it: the core of a coding agent is really simple, it's a loop with tool calling. Having said that, I think if you're going to write an article like this and call it "The Emperor Has No Clothes: How to Code Claude Code in 200 Lines of Code", you should at least include a reference to Thorsten Ball's excellent article from wayyy back in April 2025 entitled "How to Build an Age…

Hey! Thorsten Ball here. Thanks for the shout-out. I was quite confused when someone sent me this article: same "Emperor has no clothes", same "it's only x hundred lines", implements the same tools, it even uses the same ASCII colors when printing you/assistant/tool. Then I saw the "January 2025" in the title and got even more confused.

So, thanks for your comment and answering all the questions I had just now about "wait, did I wake up in a parallel universe where I didn't write the post but someone else did?"

Re: How to code Claude Code in 200 lines of code

#165

Post by nl »

prodigycorp wrote: post #46
rfw300 wrote: post #41

Earlier quoted context omitted.

Any person who would choose 3.7 with a fancy harness has a very poor memory about how dramatically the model capabilities have improved between then and now.

I’d be very interested in the performance of 3.7 decked out with web search, context7, a full suite of skills, and code quality hooks against opus 4.5 with none of those. I suspect it’s closer than you think!

> I suspect it’s closer than you think!

It's not.

I've done this (although not with all these tools).

For a reasonable sized project it's easy to tell the difference in quality between say Grok-4.1-Fast (30 on AA Coding Index) and Sonnet 4.5 (37 on AA).

Sonnet 3.7 scores 27. No way I'm touching that.

Opus 4.5 scores 46 and it's easy to see that difference. Give the models something with high cyclomtric complexity or complex dependency chains and Grok-4.1-Fast falls to bits, Opus 4.5 solves things.

Re: How to code Claude Code in 200 lines of code

#166

Post by fragmede »

__0x01 wrote: post #160

These LLM tools appear to have an unprecedented amount of access to the file systems of their users. Is this correct, and if so do we need to be concerned about user privacy and security?

We should be absolutely terrified about the amount of access these things have to users systems. Of course there is advice to use a sandbox but there are stupid people out there (I'm one of them) who disregard this advice because it's too cumbersome, so Claude is being run in yolo mode, on the same machine that has access access to bank accounts, insurance, password manager and crypto private keys.

Re: How to code Claude Code in 200 lines of code

#167

Post by sams99 »

For those interested, edit is a surprisingly difficult problem, it seems easy on the surface but there is both fine tuning and real world hallucinations you are fighting with. I implemented one this week in:

https://github.com/samsaffron/term-llm

It is about my 10th attempt at the problem so I am aware of a lot of the edge cases, a very interesting bit of research here is:

https://gist.github.com/SamSaffron/5ff5f900645a11ef4ed6c87f2...

Fascinating read.

Re: How to code Claude Code in 200 lines of code

#168

Post by emsign »

> The LLM never actually touches your filesystem.

But that's not correct. You give them write access to files it then compiles and executes. It could include code that then runs with the rights of the executing user to manipulate the system. It already has one foot past the door. And you'd have to set up all kinds of safeguards to make sure it doesn't walk outside completely.

It's a fundamental problem if you give agentic AI rights on your system. Which in contrast kind of is the whole purpose of agentic AI.

Re: How to code Claude Code in 200 lines of code

#169

Post by mickeyp »

rtgfhyuj wrote: post #57
nyellin wrote: post #19

There's a bit more to it! For example, the agent in the post will demonstrate 'early stopping' where it finishes before the task is really done. You'd think you can solve this with reasoning models, but it doesn't actually work on SOTA models. To fix 'early stopping' you need extra features in the agent harness. Claude Code does this with TODOs that are injected back into every prompt to remind the LLM what tasks rem…

why would it early stop? examples?

Models just naturally arrive at a conclusion that they are done. TODO hints can help, but is not infallible: Claude will stop and happily report there's more work to be done and "you just say the word Mister and I'll continue" --- this is a RL problem where you have to balance the chance of an infinite loop (it keeps thinking there's a little bit more to do when there is not) versus the opposite where it stops short of actual completion.

Re: How to code Claude Code in 200 lines of code

#170

Post by armcat »

The new mental model actually is (1) skills based model, i.e. https://agentskills.io/home, and (2) where the LLM agents "see all problems as coding problems". Skills are a bunch of detailed Markdowns and corresponding code libraries and snippets. The mental model thereby loops as follows: read only the top level descriptions in each SKILL.md, use those in-context to decide which skill to pick, after picking the relevant skill read the skill in-depth to choose which code/lib to use, based on the generate new code, execute the code, evaluate, repeat. The problem-as-a-code mental model is also a great way of evaluating, and creating rewards and guarantees.
Post reply on HN