First screen, captured . Open the video.
Full page
Captured . Click for the whole screenshot.
Looks similar
Neural Networks: Zero to Hero(karpathy.ai)
546 points by whereistimbo | 64 comments
Course page for Andrej Karpathy's Neural Networks: Zero to Hero, a video series building neural networks from scratch in code up to GPT-style language models.
E-means: Outperforming k-means in one-tenth the epochs(e-means.github.io)
484 points by porridgeraisin | 71 comments
Project blog post introducing e-means, an open-source mini-batch k-means algorithm from Meta FAIR using exponential moving averages, claiming ~10x speedup over Lloyd's algorithm.
Quadrillion-parameter transformers and how to train them(qlabs.sh)
60 points by frozenseven | 48 comments
Q Labs research post presenting a data-constrained scaling law with ensembling that prescribes far larger transformer models, up to quadrillion parameters, for fixed datasets.
A Minsky machine in ncurses terminfo(seriot.ch)
29 points by beefburger | 9 comments
Nicolas Seriot's article showing ncurses terminfo parameter expansion can simulate a two-counter Minsky machine, making it computationally universal, with a Fibonacci demo.
JIT bitmap text rendering for microcontrollers(linebender.org)
102 points by dmit | 22 comments
Raph Levien's Linebender blog post describing a JIT technique for fast proportional bitmap text rendering on the RP2350 microcontroller in his vic-2350 project.
Related stories
Show HN: Building a web search engine from scratch with 3B neural embeddings(blog.wilsonl.in)
578 points by wilsonzlin | 97 comments
Wilson Lin's blog post describing how he built a web search engine from scratch in two months using 3 billion neural embeddings.
Deep Learning Is Applied Topology(theahura.substack.com)
473 points by theahura | 176 comments
A Substack essay from 12 Grams of Carbon arguing that deep learning is applied topology, explaining how neural networks transform data lying on manifolds.
Deep learning gets the glory, deep fact checking gets ignored(rachel.fast.ai)
549 points by chmaynard | 134 comments
Rachel Thomas blog post on how a high-profile Nature paper using a Transformer to predict enzyme functions contained many errors that received far less attention than the original result.
AI models can provably hide arbitrary capabilities(arxiv.org)
252 points by sbulaev | 118 comments
An arXiv paper showing AI models can embed encrypted neural network backdoors that provably hide arbitrary capabilities from elicitation-based safety evaluations.
AI Made Writing Code Easier. It Made Being an Engineer Harder(ivanturkovic.com)
343 points by saikatsg | 242 comments
Blog post by Ivan Turkovic arguing that AI tools make producing code easier while making the broader job of being a software engineer harder.
The new skill in AI is not prompting, it's context engineering(philschmid.de)
832 points by robotswantdata | 467 comments
Blog post by Philipp Schmid arguing that context engineering, supplying LLMs with the right information and tools, matters more than prompting for AI agents.