Nixiesearch: Running Lucene over S3, and why we're building a new search engine(nixiesearch.substack.com)

102 points by shutty 2 years ago | 65 comments

Ladybird Web Browser becomes a non-profit with $1M from GitHub Founder(lunduke.locals.com)

944 points by mapper32 2 years ago | 668 comments

Lunduke article reporting that the from-scratch Ladybird web browser is becoming a non-profit backed by $1 million from GitHub co-founder Chris Wanstrath.

The Smallest Brain You Can Build: A Perceptron in Python(ranpara.net)

286 points by DevarshRanpara 4 months ago | 64 comments

Build a search engine, not a vector DB(blog.elicit.com)

195 points by stuhlmueller 2 years ago | 62 comments

I built a large language model "from scratch"(brettgfitzgerald.com)

66 points by controversy187 1 year ago | 4 comments

Building a Simple Search Engine That Works(karboosx.net)

240 points by freediver 11 months ago | 68 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.

Show HN: Training a model to identify AI web content from structure alone(arxiv.org)

57 points by jochenmadler 1 month ago | 14 comments

arXiv paper "SlopShape" presenting a classifier that detects AI-generated commercial blog posts and attributes their source model using structural features rather than wording.

A search engine in 80 lines of Python(alexmolas.com)

564 points by alexmolas 2 years ago | 88 comments

Blog post walking through building a simple search engine from scratch in about 80 lines of Python, motivated by small website discoverability.

Show HN: RawLink – Building a VPN protocol from scratch(github.com)

11 points by znano 7 days ago | 0 comments

GitHub repository for RawLink, an experimental VPN protocol built from scratch, with an accompanying blog post explaining its design.

Show HN: Building an LLM from Scratch in TypeScript(book.humanexperiences.io)

27 points by baraa_ 12 days ago | 2 comments

An online book guiding readers through building a large language model from scratch in NodeJS and TypeScript, covering dataloaders, embeddings, and attention.

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.