How AI and podcasts are reviving “ancient heresies” and colliding with American Christianity online

Anthony Levandowski, the engineer at the heart of the Uber/Google lawsuit, is serious about his artificial intelligence religion.

A Coding Implementation on Building Self-Organizing Zettelkasten Knowledge Graphs and Sleep-Consolidation Mechanisms

GitHub Gist: instantly share code, notes, and snippets.

We spent months building a sophisticated text-to-sql agent, but as it turns out, sometimes simpler is better. Giving it the ability to execute arbitrary bash commands outperformed everything we built. We call this a file system agent.

Despite agentic AI boosting content creation speed, human oversight remains critical due to concerns over hallucination, brand consistency.

Yes, this is the umpteenth article about AI and coding that you’ve seen this year. Welcome to 2025. Some people really find LLMs distasteful, and if that’s you, then I would recommend t…

Claude 4.5 Opus Soul Document. GitHub Gist: instantly share code, notes, and snippets.

Answer engine optimization (AEO) is the process of improving a brand's visibility in AI engines like ChatGPT. Learn how to get started with AEO now!

A far more detailed explanation of prompt caching than anyone asked for.

Why Long System Prompts Hurt Context Windows (and How to Fix It) System prompts, context windows, and why bloat hurts A system prompt is the instruction an LLM receives before any user messages …

Artificial intelligence (AI) is often seen as a tool to automate tasks and replace humans, but new research from Swansea University challenges this view, showing that AI can also act as a creative, engaging and inspiring partner.

Code is now as cheap as salt. Meet the three developer archetypes—mixologist, producer, architect—who thrive when AI makes software nearly free.

Blaise Metreweli warns the world is ‘more dangerous and contested now than for decades’ as AI and new technologies emerge

It's been just over two years and two months since ChatGPT launched, and in that time we've seen Large Language Models (LLMs) blossom from a novel concept into one of the most craven cons of the 21st century — a cynical bubble inflated by OpenAI CEO Sam Altman built to sell into an economy run by people that have no concept of labor other than their desperation to exploit or replace it. I realize that Large Language Models like GPT-4o — the model that powers ChatGPT and a bunch of other apps —

How to Design a Fully Local Multi-Agent Orchestration System Using TinyLlama for Intelligent Task Decomposition and Autonomous Collaboration

How engineers and teams use MCP servers: from debugging to working with legacy systems, & giving non-devs more access. Details from 40+ devs – with some surprises

What I use them for and what I don't

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Six months after the hype began, is vibe coding sustainable? We look at the pros and cons, and why blending vibes with structure is key.

A report describing an a highly sophisticated AI-led cyberattack

A brain dump of all the ways I've been using Claude Code.

Patterns for managing agent context.

Frameworks for LLM Agents have been surprisingly disappointing. I want to offer some principles for building agents based on our own trial & error, and explain why some tempting ideas are actually quite bad in practice.

Today, AWS announces the open-source AWS Serverless Model Context Protocol (MCP) Server, a tool that combines the power of AI assistance with serverless expertise to enhance how developers build modern applications. The Serverless MCP Server provides contextual guidance specific to serverless development, helping developers make informed decisions about architecture, implementation, and deployment. This post describes how the Serverless MCP Server works with AI coding assistants to streamline serverless development.

A new paper that we will expand into our next book

Explore the mathematical and cognitive limits that stop large language models from achieving true human-like engineering intelligence