Natural Language Autoencoders: Turning Claude's Thoughts into Text

Coinbase Cuts 700 Jobs and CEO Warns Every Company Will Do the Same

Agents need control flow, not more prompts

AlphaEvolve: Gemini-powered coding agent scaling impact across fields

Agent-harness-kit scaffolding for multi-agent workflows (MCP, provider-agnostic)

The Vatican's Website in Latin

Programming Still Sucks

Appearing Productive in the Workplace

Higher usage limits for Claude and a compute deal with SpaceX

Telus Uses AI to Alter Call-Agent Accents

Computer Use Is 45x More Expensive Than Structured APIs

Pennsylvania sues AI company, saying its chatbots illegally hold themselves out as licensed doctors

Three Inverse Laws of AI

Agents for financial services and insurance

AI didn't delete your database, you did

OpenAI will produce as many as 30 million 'AI agent' phones early next year, says industry analyst

X user tricks Grok into sending them $200,000 in crypto using morse code

Lessons for Agentic Coding: What should we do when code is cheap?

What I'm Hearing About Cognitive Debt (So Far)

Agent Skills

How OpenAI delivers low-latency voice AI at scale

Let's talk about LLMs

Agentic Coding Is a Trap

DeepClaude – Claude Code agent loop with DeepSeek V4 Pro, 17x cheaper

LLMs Are Not a Higher Level of Abstraction

Uncle Bob: It's Over

A desktop made for one

Specsmaxxing – On overcoming AI psychosis, and why I write specs in YAML

AI, Intimacy, and the Data You Never Meant to Share

AI is starting to beat doctors at making correct diagnoses

Voice-AI-for-Beginners – A curated learning path for developers

The agent harness belongs outside the sandbox

Flue is a TypeScript framework for building the next generation of agents

Open Design: Use Your Coding Agent as a Design Engine

Understand Anything

The gay jailbreak technique

Apple accidentally left Claude.md files Apple Support app

Grok 4.3

OpenWarp

Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

I scraped 1.94M Airbnb photos for opium dens, pet cameos, and messy kitchens

Mike: open-source legal AI

I benchmarked Claude Code's caveman plugin against "be brief."

Ramp's Sheets AI Exfiltrates Financials

Mistral Medium 3.5

Letting AI play my game – building an agentic test harness to help play-testing

Snapchat moves ads into chats with AI agents designed to feel like conversation

We decreased our LLM costs with Opus

Regression: malware reminder on every read still causes subagent refusals

How ChatGPT serves ads