Topics /
The most popular blog posts about ai & machine learning on Hacker News. 80 posts.
I do not agree with GitHub's unauthorized and unlicensed use of copyrighted source code as training data for their ML-powered GitHub Copilot product. This product injects source code derived from copyrighted sources into the software of their customers without informing them of the license of the original source code…
Why this is the first rule, some baseline heuristics, and when to move on to machine learning.
How simple structured data trumps clever machine learning
The bureaucrats are running the asylum
I have to tell you about the Kalman filter, because what it does is pretty damn amazing.
Geoffrey Hinton is a legendary computer scientist . . . Naturally, people paid attention when Hinton declared in 2016, “We should stop training radiologists now, it’s just completely obvious within five years deep learning is going to do better than radiologists.” The US Food and Drug Administration (FDA) approved the…
This post delves into the implementation of my procedural earth simulation, written entirely in GLSL fragment shaders. It simulates the complete history of an earth-like planet in a few minutes, with the simulation updating at 60 frames per second.
Last time, we briefly mentioned the high-level differences between Stockfish and Leela Chess. To recap, Stockfish evaluates about 100 million positions per second using rudimentary heuristics, wher…
It is not the fault of Turing, though.
His famous 1931 paper identified the fundamental limits of math, logics, theorem proving, computing, AI.
There are upsides to working with a neural net that trained on a huge collection of internet images and text. One is that, instead of ominous grey geometric blobs [https://aiweirdness.com/post/177091486527/this-ai-is-bad-at-drawing-but-will-try-anyways] when it doesn't understand your
Reflections from my time at Google Brain, and why I left for a PhD.
This article is an adaptation of a Lightning Talk I gave at CppCon2021. Link here : https://www.youtube.com/watch?v=RtqTGSOdmBo
Guess the movie based on an AI’s visual interpretation of the plot.
This class is a general introduction to computer vision. It covers standard techniques in image processing like filtering, edge detection, stereo, flow, etc. (old-school vision), as well as newer, machine-learning based computer vision. It was originally offered in the spring of 2018 at the University of Washington .
A bug that plagues thousands of open-source ML projects.
How I (almost) replicated OpenAI’s GPT-2 (124M version)
Most of the lectures, labs, and notebooks are similar to the previous edition, nevertheless, some are brand new. I will try to make clear which is which.
So it’s borderline useless for all but the simplest use cases, and even there it does a very subpar job. I’d like to have an inline image every now and then, or organize things in some multi-column layouts or the like, or a table. 19th century newspapers could do this, and if your technology can’t emulate typography…
Training the car to do self-parking using a genetic algorithm
To understand the differences between automatic differentiation libraries, let’s talk about the engineering trade-offs that were made. I would personally say that none of these libraries are “better” than another, they simply all make engineering trade-offs based on the domains and use cases they were aiming to…
I spent 24 days digging into the code of {Shan, Shui}* Chinese painting generator and lived to tell the story.
In some previous blog posts we described in details how one can generalize automatic differentiation to give automatically stability enhancements and all sorts of other niceties by incorporating graph transformations into code generation. However, one of the things which we didn’t go into too much is the limitation of…
Once upon a time I decided to train a neural net to generate pickup lines. Once I started collecting the training data I began to regret it when I saw how awful the existing lines were. Turns out I needn’t have worried. The neural net I used was so small and clueless that
<meta http-equiv=
Technological debt is insidious, a kind of socio-infrastructural subprime crisis that's unfolding around us in slow motion. Our digital infrastructure is built atop layers and layers and layers of code that's insecure due to a combination of bad practices and bad frameworks.
