AI Intelligence Archive

A response to Marina Wyss's How I'd Learn Machine Learning in 2026, from someone who arrived at the...

Most memory demos ask whether a later fact can be retrieved. That is a useful start, but it leaves...

Flash on 27 August, the flagship on 28 August. Real quant sizes, why the bigger model has better tooling support than the smaller one, and the default that silently makes it feel slow.

As of 09/02/2026, the ActorTemplate object no longer exists. It was created, as the name suggests, to...

When an agent regression judge says “accept,” the interesting question is often not the score. It is...

Retries are comforting until the process dies at the worst possible moment: after an external action...

Earlier this week, an engineer at Spotify published numbers that should make everyone running an AI...

I started collecting ancient and world coins this year. It got out of hand fast, the way these...

This is a submission for the Weekend Challenge: Generosity Edition. Have you ever thought: “I...

Previously: 9 Bugs That All Looked Like a Working System · I Built an AI That Rewrites Its Own...

I don’t just want to train a model in a Jupyter notebook and call it an ML project. I want to...

“Let’s split it into agents” has become the AI equivalent of “let’s make it a...

A familiar production failure looks like this: an AI support agent reads a ticket, decides the...

Your team decides to add an AI agent to your Laravel application. The initial plan seems...

The agent did not fail because the model was stupid. It failed because a CRM tool returned a 502,...

Remote MCP servers are shipping fast, and a lot of them are generated straight out of an OpenAPI spec...

Your team ships an internal AI assistant grounded on company documents. The demo is excellent: ask...

An AI can recall a fact when asked and miss it when it matters. InMind separates retrieval from application—and suggests a better way to test agent memory.

Everyone's OpenClaw runs on a cloud VM they rent from someone else's computer. Read that sentence...

Ask a guardrails library how often it is wrong and you will usually get silence, or a benchmark of...

RAG Over YouTube Playlists: From Video URLs to Cited Answers in 60 Lines In the previous...

I run seven agents over the same domain. They have never once sent each other a message. That was...

There is a problem with most benchmarks for coding agents: they are not software development. They...

This is a submission for Weekend Challenge: Generosity Edition What I Built VeriAid is a...

Last week a colleague shared a project with me as a zip file. I did what most of us do now: I dropped...

ProofGive: a donation tracker that protects the people it's helping Submission for the DEV...

A colleague recently asked me how he would run financial analysis with AI over the books of an...

The European Parliament has adopted a resolution calling for targeted criminal provisions and more...

I've built enough animated portfolio sites and agency landing pages at this point that I can usually...

My AI agent audited 25 projects by reading four lines of each README. Every kill verdict was...

AgentPostmortem is a moderated, searchable database of real incidents where AI agents caused harm in production, with a permanent case number for each one.

AI is no longer just a helper in development — it’s becoming a core collaborator. With this shift,...

OpenAI is signaling that it wants clearer standards for disclosing AI misalignment incidents,...

Apple's Vision framework read the image in 0.27 seconds. A local 27B vision model took 82.8 seconds. Vision made four times as many character errors — but that wasn't what decided it. Vision shredded the table into columns, and a shredded …

Three frontier models shipped in one week. The benchmark tables disagree about the winner. Here is what each number measures and which model fits which work.

The first time an AI assistant triggers a real workflow, the interesting question is not “Can it do...

A reliable AI agent is not the one that never fails. It is the one whose failures are boring: logged,...

The dangerous version of an AI agent is not the one that gives a bad answer. It is the one that...

Give a coding agent a failing test and it fixes itself. Give it a stack trace, a type error, a red CI...

The demo is flawless. The agent reads the support ticket, categorizes it, looks up the customer,...