Hacker News with Generative AI

Since Chromium 148, Math.tanh is now fingerprintable to link underlying OS (scrapfly.dev)
Cyberpunk Comics, Manga and Graphic Novels (shellzine.net)
Tiny Emulators (floooh.github.io)
Billion Dollar PDFs (billiondollarpdf.com)
So you want to learn physics (second edition, 2021) (susanrigetti.com)
Designing and assembling my first PCB (vilkeliskis.com)
Ask HN: What Are You Working On? (July 2026) (ycombinator.com)
Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper (ploy.ai)
Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k (systima.ai)
Old and new apps, via modern coding agents (wordpress.com)
How we can reduce traffic congestion (research.google)
Kode Dot Programmable pocket device for makers, pentesters and geeks (kode.diy)
Architecture Description Languages [pdf] (ics.uci.edu)
LARP – Revenue infrastructure for serious founders (larp.website)
MacKenzie Scott's Giving, in Quality-Adjusted Life Years (QALYs) (maxghenis.com)
Why write code in 2026 (softwaredoug.com)
Mechanistic interpretability researchers applying causality theory to LLMs (cacm.acm.org)
Profiling the "Abundance" housing bottleneck with real data (laxmena.com)
Circular Obstacle Pathfinding (2017) (redblobgames.github.io)
I Learned to Read Again (magazinenongrata.com)
A Peek Inside Jim Henson's Creature Shop, Where Whimsical Puppets Are Designed (smithsonianmag.com)
Automation Without Understanding (arxiv.org)
Against Usefulness (motivenotes.ai)
A Speed Limit for Computers (caolan.uk)
Why Vanilla JavaScript (guseyn.com)
Deir El-Medina Strikes (wikipedia.org)
I love LLMs, I hate hype (geohot.github.io)
Flash-MSA: Accelerating Million-Token Training with Sparse Attention Kernels (nanduruganesh.github.io)
The One-Step Trap (In AI Research) (incompleteideas.net)
Show HN: Agent Draw: An agent draws while you talk, built on TLDraw (techstackups.com)