Gemini 2.5: The First LLM That Understands PDF Layouts(sergey.fyi)

8 points by serjester 1 year ago | 1 comments

100k TPS over a billion rows: the unreasonable effectiveness of SQLite(andersmurphy.com)

344 points by speckx 10 months ago | 124 comments

Blog post by Anders Murphy benchmarking SQLite at 100k transactions per second over a billion rows, arguing its embedded single-writer design helps it scale.

Small Kafka: Tansu and SQLite on a free t3.micro(blog.tansu.io)

93 points by rmoff 9 months ago | 20 comments

XORShift for Magic Bitboards(strydr.net)

37 points by chilipepperhott 1 year ago | 5 comments

Darwin: A framework for evolving decentralized web apps(evolutionary.arweave.dev)

74 points by k__ 3 years ago | 41 comments

I algorithmically donated $5000 to Open Source(kvinogradov.com)

337 points by lorey 1 year ago | 73 comments

Blog post by Konstantin Vinogradov describing how he used GitHub Sponsors and PyPI data to algorithmically donate over $5000 to open source maintainers.

Three Years from GPT-3 to Gemini 3(oneusefulthing.org)

338 points by JumpCrisscross 11 months ago | 270 comments

Ethan Mollick's One Useful Thing Substack post reviewing Google's Gemini 3 and reflecting on AI progress in the three years since GPT-3 and ChatGPT.

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.

I let an AI run my startup for a week(daily.tinyprojects.dev)

45 points by tinyprojects 12 days ago | 43 comments

A personal blog post describing a week of letting an AI agent team (Grok Bot, similar to OpenClaw) running on a Linux server operate the author's startup.

Making a PDF that's larger than Germany(alexwlchan.net)

649 points by alexwlchan 2 years ago | 140 comments

Blog post by Alex Chan exploring the claimed maximum page size of PDF documents and creating a PDF with pages larger than Germany.

I built a programming language that LLMs can't use(blog.picheta.me)

244 points by dom96 9 days ago | 179 comments

Blog post by Dominik Picheta introducing KillSwitch, a programming language he designed so that large language models cannot use it.

The new skill in AI is not prompting, it's context engineering(philschmid.de)

832 points by robotswantdata 1 year ago | 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.