3571
A visual exploration of vector embeddings
For Pycon 2025, I created a poster exploring vector embedding models, which you can download at full-size . In this post, I'll translate ...
Topics /
AI & Machine Learning
The most popular blog posts about ai & machine learning on Hacker News. 6,326 posts.
3572
NanoGPT Slowrun: Language Modeling with Limited Data, Infinite Compute
NanoGPT Slowrun is an open effort to implement data-efficient learning algorithms; 5.5x data efficiency in the first week and improving.
3573
How to scale your model: A systems view of LLMs on TPUs
Training LLMs often feels like alchemy, but understanding and optimizing the performance of your models doesn't have to. This book aims to demystify the science of scaling language models: how TPUs (and GPUs) work and how they communicate with each other, how LLMs run on real hardware, and how to parallelize your…
3574
Graph Neural Networks – An Overview
How Neural Networks can be used in graph data
3575
Emergent Features in 6.7B+ Param Transformers
When I attended NAACL, I wanted to do a little test. I had two pitches for my LLM.int8() paper. One pitch is about how I use advanced quantization methods to achieve no performance degradation transformer inference at scale that makes large models more accessible. The other pitch talks about emergent outliers in…
3576
3577
AI Responses May Include Mistakes
The other day I wanted to look up a specific IBM PS/2 model, a circa 1992 PS/2 Server system. So I punched the model into Google, and got this:
3578
AI and the Ship of Theseus
Slopforks: what happens when a library gets rewritten with AI?
3579
Softmax forever, or why I like softmax
[UPDATE: Feb 8 2025] my amazing colleague Max Shen noticed a sign mistake in my derivation of the partial derivative of the log-harmonic function below.
3580
3581
Hacker News, Sans AI
I like HackerNews, but I don't love that so much of it has turned into discussion of a single topic: AI. This is a version of HackerNews, filtered to remove any article focusing on __AI__. Refreshes about every ten minutes.
3582
Why Bayesian Stats Needs Monte-Carlo Methods
Bayesian statistics rely heavily on Monte-Carlo methods. A common question that arises is “isn’t there an easier, analytical solution?” This post explores a bit more why this is by breaking down the analysis of a Bayesian A/B test and showing how tricky the analytical path is and exploring more of t
3583
The skill of the future is not 'AI', but 'Focus'
Don't let AI erode your focus.
3584
We compete with GitHub. Bing does not show our website
A genuine question on why we are not getting indexed by Bing.
3585
Google ML Compiler Inlining Achieves 3-7% Reduction in Size
Posted by Yundi Qian, Software Engineer, Google Research and Mircea Trofin, Software Engineer, Google Core The question of how to compile faster an...
3586
Coping with dumb LLMs using classic ML
Taking the output of many dumb LLM search relevance judges and feeding the output to a decision tree to improve precision
3587
Structured outputs on the Claude Developer Platform
Structured outputs on the Claude Developer Platform guarantee API responses match your JSON schemas and tool definitions. Now in public beta for Sonnet 4.5 and Opus 4.1, this feature eliminates parsing errors and failed tool calls for production applications.
3588
3589
RoboCat – A Self-Improving Robotic Agent
Robots are quickly becoming part of our everyday lives, but they’re often only programmed to perform specific tasks well. While harnessing recent advances in AI could lead to robots that could help in many more ways, progress in building general-purpose robots is slower in part because of the time needed to collect…
3590
ML Beyond Curve Fitting: An Intro to Causal Inference and Do-Calculus
Since writing this post back in 2018, I have extended this to a 4-part series on causal inference: * ➡️️ Part 1: Intro to causal inference and do-calculus [https://www.inference.vc/untitled] * Part 2: Illustrating Interventions with a Toy Example…
3591
New bioinspired robot flies, rolls, walks, and more
Developed at Caltech's Center for Autonomous Systems and Technologies, a new robot can autonomously choose from a variety of motions to move through a complex environment.
3592
Cloud GPU Resources and Pricing
Detailed comparison table of cloud GPU providers for deep learning.
3593
LoRA Without Regret
How LoRA matches full training performance more broadly than expected.
3594
Frank Rosenblatt's perceptron paved the way for AI 60 years too soon (2019)
As the Faculty of Computing and Information Science celebrates its 20th year, Frank Rosenblatt’s prescient research into artificial intelligence underscores Cornell’s pivotal role in computing history.
3595
Researchers use AI to turn sound recordings into street images
AUSTIN, Texas — Using generative artificial intelligence, a team of researchers at The University of Texas at Austin has converted sounds from audio
3596
The RWKV language model: An RNN with the advantages of a transformer
I explain what is so unique about the RWKV language model.
3597
Hopfield Networks Is All You Need
Blog post
3598
Logistic Regression from Bayes’ Theorem
In this post we’ll explore how we can derive logistic regression from Bayes’ Theorem. Starting with Bayes’ Theorem we’ll work our way to computing the log odds of our problem and the arrive at the inverse logit function. After reading this post you’ll have a much stronger intuition for how logistic
3599
How to build a diffusion language model
An introduction to diffusion language models and the research advances that underlie today's diffusion LLMs. We describe the building blocks of recent open-source models, starting from simple masking diffusion, and including techniques for iterative refinement, post-training, and variable-length generation. Material…
3600