advanced-context-engineering-for-coding-agents/wsff.md at main · humanlayer/advanced-context-engineering-for-coding-agents
Contribute to humanlayer/advanced-context-engineering-for-coding-agents development by creating an account on GitHub.
There continue to be reasons for software to be slow
A discussion on the various reasons why performance is slow, and which ones are unlikely to be affected by LLMs. Originally written as a counter-point to Dan Luu
Grace (@gracekind.net)
For my part, seeing AI catch up to my abilities in several domains has been painful. I feel a sense of loss. And I’m in a position where I have (a tiny bit of) leverage and control over the process. I can only imagine how painful it would be if I felt like it were completely out of my hands
advanced-context-engineering-for-coding-agents/wsff.md at f2bc7aec4575418d2d2e83fec078266cc56d3e6a · humanlayer/advanced-context-engineering-for-coding-agents
Contribute to humanlayer/advanced-context-engineering-for-coding-agents development by creating an account on GitHub.
What Even Is An OS Now?
Computers now work the way I thought they did when I was 8. What does computing look like when most applications have an audience of 1-2 people? I'm leaving Fly.io to build a phone for that world.

Sung Kim (@sungkim.bsky.social)
I like this quote on code review: "The idea that humans will reliably look through code to find the increasingly rare issues that automated tools miss seems like a fantasy." By Marc Brooker, AWS.
If coding is solved, what now?: Measuring the sloppiness of code | EARENDIL
Exploring how to measure code sloppiness, why correct code can still erode a codebase, and why human intuition and taste still matter.

There's no reason for software to be slow anymore
The other day, I saw a viral tweet saying that people talking about how LLMs are causing slow, bloated, code are going to eat crow once they re-write everything in super-optimized assembly. We're not quite at the point where we want to write everything in assembly, but some variant of what Nolan Lawson said about testing, you can choose how many bugs you want now, which I less eloquently noted here, is becoming more true for performance.
2027: My jailbroken robot vacuum cleans my apartment. It sends lidar and imaging data to my homelab. My GPU begins updating the gaussian splat model of my apartment. Astra then refines and updates the blender version of it. The model is then made available to my microduck which it uses to run