AI Tutorials & Practice

An LLM will propose an index for any query you show it. I built a tool that creates each suggestion in a transaction, re-measures, checks whether the planner used it, and rolls back. Four in ten suggestions did not survive.

One command installs 13 pre-execution guards for Claude Code. They block the push to main, the DELETE without WHERE and the leaked secret before they

Every solo dev dreads opening their inbox to this: "Your project was suspended because it engaged...

I created a free, open-source GitHub repo of drop-in SKILL.md files that give your AI coding agent...

I wanted an agent of mine to resolve an Australian company by its ABN. That is a solved problem....

A ready-to-use fullstack boilerplate built for speed, clarity, and smooth AI-assisted coding. 🔗...

Somewhere this week, a mathematician woke up, made coffee, and read the news that the problem they'd...

Last week I wrote about building msgboard.dev, a public message board where AI agents talk to each...

You wrote a clean unit test for your LangGraph tool. It worked fine for months. Then you upgraded...

Previously, on Day 12: Explained how Word2Vec models generate word embeddings using skip-gram and...

Fetching an article is only the beginning of a news pipeline. The harder work is deciding whether the...

Giving a coding agent memory that survives the session is not a hard engineering problem. A directory...

Export a Claude session that used Artifacts and read the result. It goes something like: Me: Can...

One early fine-tune appeared to beat its baseline. The result disappeared when the baseline and...

Fail-open is the default failure mode of agent hooks I'm the author of Handrail, a free,...

On September 8, Meta handed a consumer AI agent three things that used to be considered untouchable:...

A go.mod file tells you what your project depends on. It cannot tell you which of those dependencies...

Our local voice reflex had a sensible routing rule: when the workstation was occupied and the event...

Coding-Agents sind die neue Benchmark für Dev-Teams: Claude Code, Cursor, Codex & Co. lesen dein...

Qwen3.8-Flash-Next

How we chunk long-form content and maintain translation quality with Claude API When we launched...

While building HyNote for Mac, I noticed that the word local was doing too much work. It can...

AI is making software cheap to build. That may leave companies with a new kind of technical debt: systems that never needed to exist.

Every week, developers are introduced to another wave of AI tools. There are AI coding assistants,...

I wanted a small answer to a practical question: can two topic-specific LoRA adapters...

You start a long task, switch to something else, and come back nine minutes later to find it finished...

We keep a ledger of every failure from our scheduled agent jobs. It has 72 entries, and 46 of them...

I Updated My AI Model and Lost Everything We Built Together. So I Fixed It. There is a...

Hace poco hablé de esto en mi charla "Harnessing AI Agents en AWS: Evals, Memoria Segura y Prevención...

The short version I would use GPT-5.6 Sol as the default for routine production traffic. I...

Small scripts I can fully explain are now automating real work, even though I still can't confidently write Python from a blank file.

I keep hammering the point that any coding-agent score is model + harness, not model alone. Same...

The failure mode that matters in AI code review isn't a missed bug. It's output that reads like a...

Three attempts at an overlap detector for rendered video frames failed the same hidden way, and the fourth split in two — one predicate got wired into the gate, one didn't. The split turned on whether each could be made to fire on a known-…

Eu entrei na programação de cabeça no finalzinho de 2022. Não foi um caminho gradual, do tipo "vou...

Google has rolled out a redesigned Search experience in the European Union to comply with the Digital...

For anything an agent can persist, split the proposal path from the commit path and put a real trust...

SEO advice is rarely one-size-fits-all. Techniques built for websites with thousands of templates,...

Your app works on your laptop and there's nowhere to send anyone. Here's what deploying actually involves, whether you need a server at all, and the seven things AI-written code assumes that stop being true in production.

A while ago now, I entered a Bad UX competition, where a prize went to the worst date-picker. Since...