Ai

Back in May I wrote about asking ChatGPT and Claude where to put my circulator fan in my study. Last week the question was less relaxed and burning. The UK broke its June temperature record three days running, my study is a small room with the sun aimed straight at it, and I went back to both models to see if they could help. What came back read well and annoyingly didn’t work. Both kept telling me to aim the air just above my head, which puts the column over you, and when I said it wasn’t working they’d tell me to nudge it up a little more and that I was nearly there, pointing me the whole time at a placement that wasn’t going to achieve what they calculated. ...

A website serving Windows Server 2019 was returning the correct pages to every human who visited, to Bing, and to Yandex, and Thai casino spam to Googlebot alone. The admin who posted about it had spent days inside the box looking for the cause. They checked web.config, the URL rewrite rules, the HTTP redirects, the custom error pages, the IIS handlers and modules and ISAPI filters, robots.txt, the sitemap, and then ran findstr across every drive for the spam domain and the casino keywords. All of it came back clean. The same behaviour showed up on multiple unrelated sites on the same server, which ruled out a single compromised application and pointed at something sitting underneath all of them. ...

Three apps can still mean one underlying answer. I was heading to the ExCeL the morning after a tube strike, when the tubes were meant to be running again, and I had a session I wanted to catch. The boards outside the station said the trains were running soon, so I waited, switching between Citymapper and Google Maps to work out which one to believe. A woman walking past told me not to bother. She’d been standing at another station where the boards said the same thing and nothing had come, so she’d given up and was getting the bus. I ended up on a bus that didn’t go all the way, then the Elizabeth line, and the whole thing took far longer than I’d planned for a journey that was meant to be simple. ...

The system can keep running long after the reasoning behind it has left. You can’t test it, because the only place it runs is production, so you read the logs and you sit with someone while they do their job with it and build up a picture of what it does from the outside. The customer said it pulls from the billing platform on a schedule, but the logs say it pushes on a trigger, the connection string points at a host that isn’t on the network diagram, and the job everyone calls the nightly sync runs four times a day. At one point the worker does a step that makes no sense, and when you ask why, the answer is that’s just how it’s always done. It takes time and the picture you end up with is nothing like the description, but you get there. ...

The biggest change in chat models over the last two years is not the one most articles focus on. It is that they can now actually look at things. Image input went from a feature you would test once and forget about to something I use weekly without thinking about it, and the gap between describing a problem in words and just showing the model what you are looking at turns out to be much bigger than I expected. The first time it really landed for me was a few years ago when I started feeding ChatGPT photos of error screens and bits of hardware I could not be bothered to describe. By the time photo-based questions felt routine I had built up enough trust in ChatGPT specifically that vision tasks became one of the things I would default to it for, even as Claude took over for almost everything else I do. ...

The biggest change I made for this AWS recert isn’t which AI I’m using, it’s that I moved my study notes out of OneNote and into Notion. Back in March I wrote about studying with custom GPTs for the AI Practitioner. The note-creation GPT had grown a system prompt that read like a software spec, the coaching one had stayed simple and useful, and the post ended with me saying I’d try Claude as a study partner for the SA Pro and figure out whether to move my notes out of OneNote. ...

The Register reported that UK entry-level tech roles fell 46 percent in 2024, with projections hitting 53 percent by the end of 2026, based on figures from the Institute of Student Employers. Most of the commentary points at AI as the cause, and AI is doing something, but the ladder into architecture has been eroding for over a decade and the AI piece is just the wave you can see right now. The earlier waves were quieter and they did most of the damage well before agents showed up. ...

The AI Builders Breakfast Before the main programme opened there was a smaller invite-only session called the AI Builders Breakfast, which I hadn’t known about when I wrote the pre-Summit piece and only found out about after. It ended up being the part of the day I got the most out of. The room was smaller than anything else I sat in all day and the conversations were about what’s actually hard rather than what’s being announced. ...

I’ve been to plenty of vendor events and briefings over the years but never an AWS Summit, so heading to London on Wednesday for the first time I genuinely don’t know what to expect. I’m planning to get there when doors open at 8am partly to beat the keynote crowds and partly because I’ve already had to make some hard choices about how the day runs. Picking the Sessions I had four sessions I wanted to attend: the keynote on agentic AI, a workshop on rapid prototyping with Kiro, a zero trust for AI security session, and a fast-track VMware migration workshop. Some run 2–3 hours, the zero trust session clashes directly with Kiro, and doing all of them would mean spending the entire day in rooms with no time to actually see any of it, so I’ve cut two. I’m skipping the keynote, which at my first AWS Summit feels like it should be a bigger deal than it is, and dropping the AI security session because it runs at the same time as Kiro and that’s not a close call. The keynote will be streamed and I’ll catch it later. The VMware workshop and Kiro are what I’m actually there for. ...

I came across AI Warehouse while studying for the AWS AI Practitioner cert through the Stephanie Maarek course. I lost a few hours on their YouTube channel watching reinforcement learning agents figure out games from scratch, and when I found they had a downloadable Windows simulator I wanted to try it myself. Their Red Light, Green Light scenario, the one from Squid Games, lets you run different shaped agents through the course and adjust the training parameters to see what changes. ...