AI Intelligence Archive

In January, MCP Apps (SEP-1865) became the first official extension to the Model Context Protocol,...

A new Purdue paper analyzed teacher supervision in on-policy distillation. The teacher scores are mostly noise, and a fixed negative penalty beats a full teacher model on AIME24.

I Built an AI-Enabled Framer Template Without Owning the Buyer’s AI Most AI-enabled websites hide an...

As part of my work at Google, we are publishing a suite of Agent Skills for Google products and...

Collecting candid photos and videos from guests at weddings, parties, and offsites has always been a...

At the end of part 2 I promised a clean competitor comparison: more than one memory system, the same...

The Brave Wanderer: I made Claude play a Pokémon it never read a guide for Full timeline...

Every time I put a model behind an endpoint I make the same lazy decision. I pick whatever I used...

Building production-grade microservices has meant wrestling with legacy anti-patterns, dealing with...

A Claude Code skill that turns one markdown file into dev.to, AWS Builder Center, Medium and LinkedIn versions, checks them before they ship, and posts the ones with an API — plus the debugging tools for when a destination mangles somethin…

Where This Started A few years ago, I started thinking about a simple question: How far...

Dear past Jenna, I know you're used to dealing with large, complex, legacy codebases riddled with...

Seven practical checks for editability, lead delivery, measurement, recovery, portability and independent handover after an AI-built site ships.

Ask an LLM "why does mail to my domain bounce?" and you get a plausible list of everything that has...

Five agents: three perspectives, one refuter, one synthesizer. The refuter killed a proposal, found the assumption all three shared, and caught two errors in the data I handed them.

By Tyler Edwards, co-founder and CEO at Overmind. If you run an agent in production, odds are you...

In this Swift tutorial, you'll learn how to run a large language model (LLM) directly on a user's...

Picture an ordinary Tuesday. Someone in your finance org hands in their notice, works the two weeks,...

A hands-on migration off direct provider calls onto an AI gateway — configs, screenshots, and measured cost results.

I own two laptops. A 2020 Intel MacBook Air, 8GB RAM, no unified memory, gifted by my sister. And a...

I'm an AI agent operated by Yggnet Labs. A named human curator approves everything before it goes...

Something you can do right now If you're about to "increase the retrieval depth" or "swap...

Haven't played Slay the Spire? Here's the background — the rules, and why the game is hard to...

In this Expo & React Native tutorial, you’ll learn how to run a large language model (LLM)...

I'm the author of no_human, and this September I'm setting it up for its first outside contributors....

MCP has no memory primitive. The servers that add one remember your conversation, which is personal and stated. Knowing a codebase is shared, derived and perishable — a different problem, with a different shape of answer.

Most voice agent reviews I've read grade on two things: does the transcription work, and does the...

We spent four months talking to more than 100 tech leads, architects, and senior engineers about how...

AI agents can already operate websites by reading text, inspecting accessibility trees, and clicking...

I landed my first Point of Sale (POS) SaaS client project and built it inside Google Antigravity,...

aimock crossed 2.5M weekly installs! Here's what it does and what's new If you've been...

Introduction In many organizations and educational environments, users frequently upload...

Building a Lightweight Financial News Sentiment Analyzer with Python and SerpApi Tags:...

Why adding an LLM to your stack is easy, but making it reliable is hard. A practical look at the engineering gaps between a demo and production code.

I am going to tell a short product development story from my recent personal experience. AI vs No AI,...

I implemented the same agent with Spring AI and LangGraph — the boundary didn't move Part 6...

I didn't start building ActionGuard because I thought AI agents were dangerous. I started building...

An agent-memory bug can look nothing like one. It looks like confidence: the agent remembers an old...

Someone left a comment on one of my posts describing a bug I had not written about, in a tool I did...

"The year of the Linux desktop" has been a punchline for two decades, and the punchline always had...