811
Teaching LLMs how to solid model
It turns out that LLMs can make CAD models for simple 3D mechanical parts. And, I think they’ll be extremely good at it soon.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 3,091 posts.
812
Neglected machine learning ideas
This post is inspired by the “metacademy” suggestions for “leveling up your machine learning.” They make some halfway decent suggestions for beginners. The problem is, thes…
813
814
My trick for getting consistent classification from LLMs
A technique for deterministic labeling from stochastic models, with benchmarked Golang implementation.
815
Hard problems that reduce to document ranking
There are two claims I’d like to make: LLMs can be used effectively1 for listwise document ranking. Some complex problems can (surprisingly) be solved by transforming them into document ranking problems. I’ve primarily explored both of these claims in the context of using patch diffing to locate N-day…
816
Top data mining algorithms in plain English
Today, I'm going to explain in plain English the top 10 most influential data mining algorithms as voted on by 3 separate panels in this survey paper. Once you know what they are, how they work, what they do and where you ... Read More
817
AI’s big rift is like a religious schism
The cult-like battles between e/acc and doomers
818
All AI Videos Are Harmful (2025)
When OpenAI released the first version of Sora, I was excited. For years, I'd had this short story sitting on my hard drive, something I'd written long ago and always dreamed of bringing to life as a
819
The AI Trust Crisis
Dropbox added some new AI features. In the past couple of days these have attracted a firestorm of criticism. Benj Edwards rounds it up in Dropbox spooks users with new …
820
Deep Learning Enables You to Hide Screen When Your Boss Is Approaching
Discover how advanced deep learning technologies offer revolutionary screen privacy solutions in the workplace. Learn to safeguard your digital space with ease.
821
822
Neural network training makes beautiful fractals
This blog is intended to be a place to share ideas and results that are too weird, incomplete, or off-topic to turn into an academic paper, but that I think may be important. Let me know what you think! Contact links to the left.
823
824
Principal Component Analysis Explained Visually (2015)
Principal component analysis (PCA) is a technique used to emphasize variation and bring out strong patterns in a dataset. It's often used to make data easy to explore and visualize.
825
Gemini 3 Pro vs. 2.5 Pro in Pokemon Crystal
From 2.5 Pro's lighthouse loop to 3 Pro's "Zombie Phoenix" strategy against Red: a full breakdown of why Gemini 3 Pro is a superior long-horizon agent.
826
Diffusion Models
I spent 2022 learning to draw and was blindsided by the rise of AI art There is lots to say about this, whether it has been or will be a good thing for artists and society in the long run. I hope to write about it in another post. models like Stable Diffusion. Suddenly, the computer was a better artist than I could…
827
Why AI hasn't replaced software engineers, and won't
Coding agents as normal technology
828
829
Deep Learning for Guitar Effect Emulation
Since the 1940s, electric guitarists, keyboardists, and other instrumentalists have been using effects pedals, devices that modify the sound of the original audio source. Typical effects include distortion, compression, chorus, reverb, and delay. Early effects pedals consisted of basic analog circuits, often along…
830
I caught Google Gemini using my data and then covering it up
I asked Google Gemini a pretty basic developer question. The answer was unremarkable, apart from it mentioning in conclusion that it knows I previously used ...
831
What is protein folding? A brief explanation
AlphaFold from Google DeepMind is said to solve the protein folding problem. What is that, and why is it hard?
832
Compiling LLMs into a MegaKernel: A path to low-latency inference
TL;DR: We developed a compiler that automatically transforms LLM inference into a single megakernel — a fused GPU kernel that performs…
833
Audio Decomposition – open-source seperation of music to constituent instruments
Matthew Bird Portfolio
834
On Chomsky and the Two Cultures of Statistical Learning
Chomsky's remarks were in response to Steven Pinker's question about the success of probabilistic models trained with statistical methods. This essay is a response to Pinker and Chomsky, and will address these questions:
835
Tools: Code Is All You Need
The solution to agentic flows was code all along.
836
The tech market is fundamentally fucked up and AI is just a scapegoat
The Tech Market is Fundamentally Fucked Up - AI is Just a Scapegoat
837
ChatGPT and Code Interpreter = Magic
tl;dr: OpenAI is testing the ability to run code and use third-party plugins in ChatGPT. OpenAI has announced that we’re developing plugins for ChatGPT that will extend its capabilities. [Link] Plu…
838
This AI is bad at drawing but will try anyways
There was a paper recently where a research team trained a machine learning algorithm (a GAN they called AttnGAN) to generate pictures based on written descriptions. It’s like Visual Chatbot in reverse. When it was just trained to generate pictures of birds, it did pretty well, actually.
839
PyTorch for WebGPU
TL;DR I’ve been working on a WebGPU optimized inference and autograd library called webgpu-torch with an API that matches PyTorch. The goal is to run neural networks in the browser at speeds comparable to a Linux workstation. Many kernels have been implemented and its design is easily extensible. It’s available on NPM…
840