Notes from the workshop.

Writing on AI adoption, bespoke software, intelligent automation, and the things a one-person workshop learns along the way. Read it here or by RSS. For MSP owners there is also MSP Field Notes, one finding from the workshop by email every other week.

DKIM on Microsoft 365: your DNS, their keys

DKIM on Microsoft 365 is enabled by creating two selector CNAMEs in your DNS and turning on signing in the Defender portal; the signatures may not appear for up to half an hour.

What does the screen say?

Ten days, Meta's newest models and a hackathon. My first idea died on day two, Eyewitness took its place, and two AI agents built it in two days while I made the calls. A report from the inside, with the bit that nearly fooled us.

The only thing they wanted was my passport

For 20 months a Colombian bank has emailed me a stranger's finances: every card transaction, her statements, her loan papers. I tried every channel I could find to report it. One human replied, and wanted my passport number.

Six months in the memory palace

Every AI session starts with amnesia and a training cutoff. For six months a memory palace has filled the gap across every project I run, and this week Milla Jovovich's latest release made it better. A field report, and a love letter.

When GitHub suspended my account without telling me

No email, no warning, no reason. One evening my GitHub account stopped existing, and every automation built on it failed within the minute. This is what broke, what I still do not know, and how my own Gitea carried the load.

PHP2Shell: the interpreter is the vulnerability

Two unauthenticated RCEs in PHP itself, rated 9.2 and reaching back to version 5.4. The fix is out, probing has started, and the flaw sits underneath every line of application code. What happened, and the remediation order that works.

Meta: how this podcast gets made

Two synthetic co-hosts, one verification pipeline, and why every episode is also a demo. If your business has words, it can have voices.

The filter will not save you

I spent a day reading the AI security papers that matter, with primary sources open rather than vendor summaries. Prompt injection is structural, most defences collapse under adaptive attack, and what survives is architecture.

Verified in an hour. Flagged for three months.

In July Anthropic checked my ID and approved me for security work on my own code within the hour. Three months on, Claude still flags me for writing a gitleaks config, and my bug reports go to a bot.

A nutritionist, an accountant and an IT guy walk into a park

The key takeaway is that AI will happily give confident answers without grounding, so you must demand reputable sources, have it verify its claims and provide clear context.

A barn find, in shell script

TIGER audited Unix systems in 1993 and was last released in 2008. I pulled it out of the shed, ran it on a 2026 Linux Mint desktop, and got 49,651 lines back. By the evening it was 318, and most of those were worth reading. This is what waking up old code is actually like.

Full marks, and disqualified

Before moving this site's chat to a new model, I tested six against the real prompt. The scorecard gave five of them full marks. Two of those five should have been thrown out on the spot, and only reading the answers showed it.