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

Get started with the Agent Client Protocol (ACP)

Our exclusive industry report is out!

Soundtrack: Queens of the Stone Age - First It Giveth Before we go any further: This is, for the third time this year, the longest newsletter I've ever written, weighing in somewhere around 18,500 words. I've written it specifically to be read at your leisure — dip in and out where you'd like — but also in one go.  This is my comprehensive case that yes, we’re in a bubble, one that will inevitably (and violently) collapse in the near future. I'll also be cutting this into a four-part episode

Entry-level jobs are disappearing. In their place: unpaid gigs, cold DMs and self-starters scrambling for a foothold. The ladder’s gone – what’s replacing it, and who’s being left behind?

CreativeMornings is a breakfast lecture series for the creative community. Join us at one of our free monthly events around the world or watch the talks online!

The bitter truth about people preaching taste with AI.

The what, why and how of understanding and building MCP servers

There's this restaurant in Tokyo that doesn't have a kitchen.

Hi, my name is Peter and I'm a Claudoholic. A reflection on AI addiction, extreme work culture, and the blurry line between productivity and obsession in the age of agentic engineering.

Collection of extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini - asgeirtj/system_prompts_leaks

Hello! If you are seeing this you are either early or currently attending my talk at DataEngBytes. Learning how to build an agent is one of the best things you can do for your personal development. Cursor, Windsurf, Claude Code and Ampcode.com are 300 lines of code running in a while true loop. Learn how to build your own agent

Lessons I learned from implementing marimo's MCP client

As AI writes code, developers must become better product thinkers

Contribute to MCP-Manager/MCP-Checklists development by creating an account on GitHub.