Omarchy - Beautiful, fun & agentic Linux by DHH
The malleable OS for the age of agents. Vibe your way through every alteration, tweak, and desire.
44 posts tagged #ai
Why Didn't Google Build Muse?
Meta shipped the AI assistant that Google should have long ago...
Claude Code from Source — Architecture, Patterns & Internals
A technical book analyzing the architecture of Anthropic
OpenSpec | A lightweight and configurable spec framework
OpenSpec helps teams and coding agents create, refine, and manage living specifications.
On learning programming in an age of LLMs
Open answers to a reader
Yoshua Bengio | Why are AI agents lying, cheating and coordinating?
A lot has been written about the incidents of the last few months in which AI agents misbehaved in serious ways. They took actions that would be considered as crimes if a human took them, escaped their containment to cheat on assigned tasks while attempting to evade detection, and coordinated…
When Anyone Can Build Software, Who Decides What Not to Build?
Archify — Technical Diagrams from Plain English
Describe your system in chat. Archify generates a polished, explorable HTML diagram with semantic focus, dark/light themes, motion, and ultra-crisp export.
ponytail
He says nothing. He writes one line. It works.
Introducing GPT‑6 Astra, the world’s most intelligent and aligned model
You Can't "Vibe Code" Love
About a year ago, I was offered a presentation slot at the WeAreDevelopers World Congress in Berlin. I rarely take speaking engagements, especially international ones, but this one arrived at just the right time, the right place, and with the right person – I said yes, on the contingency that Ben
The AI-Native SDLC playbook
Anthropic's stage-by-stage playbook for the AI-native SDLC: how teams plan, design, build, test, deploy, and maintain software with Claude.
Anger, Anxiety and Agency
Who is the AI villain we should be angry at?
The Claude Code Guide For Startups
The five rules startups use with Claude Code to ship like teams 10x their size—Anthropic's guide to AI-native building, from everyone-ships culture to AI-native SDLCs.
OpenRouter is Joining Stripe — OpenRouter Blog
OpenRouter is joining forces with Stripe. Same mission, same name, same product, same roadmap, and routing that stays driven by what's best
How AI text watermarking works
A gentle visual guide to how a statistical mark hides inside generated text, and what erases it.
Introducing Delta - Zed Blog
From the Zed Blog: A multiplayer environment for coding with agents, from the creators of Zed.
Claude Code Skills for Clean Architecture | Milan Jovanović
A free skill pack that teaches Claude Code the conventions of my Clean Architecture template.
Introducing Muse Code and Muse Spark 1.2
Introducing Muse Code, a terminal coding agent powered by Muse Spark 1.2, with persistent background agents, repository-scale execution, and
Kimi K3 Architecture Notes
Short architecture note on Kimi K3, including LatentMoE, Kimi Delta Attention, Attention Residuals, NoPE, multimodality, and inference-effic
AI Mania Is Eviscerating Global Decisionmaking
The reality of how much damage AI mania is doing to our ability to run institutions effectively.
Who’s Afraid of Chinese Models?
Everyone is worried about Chinese models, but the frontier labs will be fine; we need to enable open U.S. alternatives.
GLM 5.2 and the coming AI margin collapse (part 1)
GLM 5.2 is the first open weights model I'd call a genuine competitor to Opus and GPT for agentic work - at ~15-20% of the price. Part one o
Introducing the Safari MCP server for web developers
In Safari Technology Preview 247, we’re introducing the Safari MCP server — a Model Context Protocol server for web developers that makes yo
Redeploying Claude Fable 5
Anthropic is redeploying Claude Fable 5 starting July 1 following the lifting of export controls, with updated cybersecurity safeguards and
Who Does What? Team Topologies for the Agentic Platform
The agentic platform defines what needs to be provided. Team Topologies defines who provides it, and how teams interact to make it happen.
GLM-5.2 vs Claude Opus | Tech Stackups
Is the GLM-5.2 hype real or benchmaxxed? We ran it head-to-head against Claude Opus, building a 3D platformer in raw WebGL from scratch.
AI in Engineering Teams: ROI, Code Review, and Hiring
At a Shift CTO Craft dinner in Toronto, senior engineering leaders debated AI ROI, code review bottlenecks, hiring, cognitive debt, and vend
Applying Brevity and Language Efficiency in Prompt Engineering
A Comprehensive Guide for Budget-Conscious Users in Oriental Regions Prahlad Yeri · June 15, 2026 · 47 min read Note: This article was
Running local models is good now
Local agentic coding has gotten great over the past few months
Anthropic’s Safety Superpower
Anthropic’s belief in its own commitment to safety gives the company license to aggressively favor its business and even challenge the U.S.
The iPhone’s Last Stand
Siri isn’t state of the art, but as long as it works — and it appears it does — it’s good enough for the consumer market.
Backpressure is all you need
Hot takes and cold truths on software, startups, and the lies we tell ourselves.
Introducing Claude Opus 4.8
Our latest model, Claude Opus 4.8, is an upgrade to our Opus class of models, with stronger performance across coding, agentic tasks, and pr
I think Anthropic and OpenAI have found product-market fit
Anthropic are strongly rumored to be about to have their first profitable quarter. Stories are circulating of companies surprised at how exp
You’ll lose your job in 2027.
Assume that your current role is close to its expiration date.
Codex-maxxing - Jason Liu
How I use Codex as a place where long-running work can live.
How Claude Code works in large codebases: Best practices and where to start | Claude
The most successful Claude Code deployments share a set of recognizable patterns across configurations, tooling, and org structure. This art
Best mini PC for local LLMs in 2026 (Strix Halo era) | TerminalBytes
Strix Halo mini PCs doubled in price in six months. Here's what's worth buying for local LLMs in 2026, what to skip, and the 120W gotcha nob
I benchmarked caveman against two words | Max Taylor
I work on AI evals and reliability for agentic systems. Skeptical of tooling hype, mostly because I keep measuring it.
Who Owns the Code Claude Wrote?
AI-generated code copyright explained for builders.
BEWARE SOFTWARE BRAIN
Software brain is changing the world, but most people still aren’t buying.
A Mac Studio for Local AI — 6 Months Later
The Mac Studio M3 with 512GB of memory is an absurd amount of computer.
GitHub - Arthur-Ficial/apfel: Apple Intelligence from the command line. On-device LLM via FoundationModels framework. No API keys, no cloud,
Apple Intelligence from the command line. On-device LLM via FoundationModels framework. No API keys, no cloud, no dependencies. - Arthur-Fic
Super cool package that allows running the On-device LLMs available from Apple Intelligence.
Fable 5 is back. It has been a weird saga for sure.