Neural Networks: Zero to Hero(karpathy.ai)

693 points by suioir 9 months ago | 63 comments

Andrej Karpathy's free video course page on building neural networks from scratch in Python, from backpropagation (micrograd) up to GPT-style language models.

Microgpt explained interactively(growingswe.com)

283 points by growingswe 7 months ago | 41 comments

The Matrix Calculus You Need for Deep Learning(explained.ai)

52 points by Anon84 1 year ago | 1 comments

Neural network training makes beautiful fractals(sohl-dickstein.github.io)

264 points by telotortium 2 years ago | 54 comments

Borgo Programming Language(borgo-lang.github.io)

334 points by MrBuddyCasino 1 year ago | 159 comments

Interactive intro and playground for Borgo, a new statically typed programming language with Rust-like features that compiles to Go.

A technical look at ZeroNet(znano.eu.org)

64 points by znano 3 years ago | 9 comments

Neural Networks: Zero to Hero(karpathy.ai)

693 points by suioir 9 months ago | 63 comments

Andrej Karpathy's free video course page on building neural networks from scratch in Python, from backpropagation (micrograd) up to GPT-style language models.

Deep Learning Is Applied Topology(theahura.substack.com)

473 points by theahura 1 year ago | 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.

AI Made Writing Code Easier. It Made Being an Engineer Harder(ivanturkovic.com)

343 points by saikatsg 7 months ago | 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.

AI models can provably hide arbitrary capabilities(arxiv.org)

252 points by sbulaev 13 days ago | 118 comments

An arXiv paper showing AI models can embed encrypted neural network backdoors that provably hide arbitrary capabilities from elicitation-based safety evaluations.

Neural networks are clean(already-clean.goodfire.com)

768 points by themgt 11 days ago | 300 comments

An informal research essay by Nick Cammarata at Goodfire arguing polysemanticity stems from fixable issues, not superposition, making neurons interpretable at scale.

Generative AI for Beginners(microsoft.github.io)

575 points by Anon84 2 years ago | 86 comments

Microsoft's free 12-lesson course site teaching beginners how to build generative AI applications, covering LLMs, prompt engineering, and app design.