schaefer

Joined 14 years ago

Karma
1,693
Submissions
614
Member since
Dec 16
Hi friends,

I enjoy Rock Climbing, Go, Software Engineering, and Buddhism.

dilapidated homepage: https://slow.camp

View on Hacker News

Recent submissions

Comment · 6 days ago
Correct. I am only working on building my own harnesses.
Comment · 6 days ago
I don't know if you'll be interested, but there is an excellent book on the topic: Build an AI Agent (From Scratch), by Jungjun Hur and Younghee Song (Manning Publication).

By chapter four you have a minimal working codebase in python. Later chapters add out features like tool calling, planning, and reflection.

Comment · 6 days ago
Thanks for the suggestion, but that’s not a fit for me.

I’m writing my own harness to learn. And I’m writing it in zig.

But, I’ll absolutely add maki.sh to my reading list. So, that’s a win.

Comment · 6 days ago
> "What kind of hardware... "

At home, I mostly use openrouter.

A few bucks will realistically last you forever. I also bought a DGX Spark at launch. I've learned a ton. but it's not usually my daily driver. I do run overnight tasks on it, like "read this book and write up notes on each chapter..."

In retrospect, given the dirt cheap prices of apis and or renting hardware, buying hardware for inference was likely a mistake (but not enough of a mistake to sell it now).

Comment · 6 days ago
Pi.dev at home.

And I’m slowly writing my own. But it’s garbage at the moment.

Comment · 10 days ago
I just looked up a video for this game, and looks like a really interesting take on user interface in VR. Thanks for the head's up!
Comment · 12 days ago
>> Not sure there's a strong use case…

The author’s discussion of their personal use case starts on the seventh sentence in TFA. And frankly, it sounds like a pretty solid use case:

“Being able to run things locally and mess around with RL, quantisation and fine-tuning on a laptop would be sick. I already publish my own GGUF quants on Hugging Face, with over 160,000 downloads in the past month.”

Comment · 12 days ago
I agree with your skepticism.

3.8k is less than the preorder cost of the DGX Spark over a year ago (Oct 14th, 2025).

Comment · 15 days ago
Comment · 16 days ago
this is not what *decision models* do.
Comment · 19 days ago
I would like to start seeing bar graphs for benchmark results to add a second y axis to show token spend or cost in dollars.

I guess what I'm saying is performance is fine... but what I really want to see is performance/dollar.

Comment · 22 days ago
In my state, early voting in the US midterm elections start on October 17. That's just eight days from now.

Thank goodness.

Comment · 24 days ago
This is a great recommendation. And considering the code base is in assembly, I'll gladly welcome a walkthrough.
Comment · 24 days ago
thank you!
Comment · 24 days ago
Is any of the original Apollo code available to read?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton