LLMs make it easier to write code, but understanding, reviewing, and maintaining it still takes time, trust, and good judgment.

FAQ from our course on AI Evals.

The solution to agentic flows was code all along.

Neural networks surround us, in the form of large language models, speech transcription systems, molecular discovery algorithms, robotics, and much more. Stripped of anything else, neural networks...

Carson Gross explores the Locality of Behaviour (LoB) principle, which emphasizes making the behavior of code units obvious on inspection to enhance maintainability. He discusses the tradeoffs between LoB and other software design principles like DRY and…

A Rust port of tmux

"Unlock the mystery of the 'Peasant Railgun' – a legendary D&D phenomenon explained! Delve into the tale where DMs debated and players plead.

On making use of large thinking models.

Brew your morning HN

Poor man's Backend-as-a-Service (BaaS), similar to Firebase/Supabase/Pocketbase - zserge/pennybase

In 1962. There — that answers the clickbaity title right away.

Unleashing Film Grain Synthesis on Netflix and Enhancing Visuals for Millions

Today, we open sourced our Zero-Knowledge Proof (ZKP) libraries, fulfilling a promise and building on our partnership with Sparkasse to support EU age assurance.

Recent advancements in artificial intelligence (AI), particularly in large language models (LLMs) such as OpenAI-o1 and DeepSeek-R1, have demonstrated remarkable capabilities in complex domains...

Run LLM batch jobs in hours, not days, at a fraction of the cost.

Scientists have dubbed the tar-like substance ShipGoo001.

I've always been told that caching is a tool to make software faster. That, given some careful considerations to consistency, caching makes it so that when...

Kevin Kelly on a different way to do great work

Self-host a personal website + newsletter