AI

I’ve spent the last few weeks building across a few different AI coding tools, and I stopped paying much attention to the model underneath. You spend enough time around AI and you start to believe the model is the part that matters, since it’s what everyone talks about and all the benchmarking is against. But build across enough tools in a short stretch and a different picture shows up. The model is closer to an interchangeable component, and the setup wrapped around it is what decides success. ...

The first time I used Kiro was at the AWS Summit in London earlier this year. It was a hands-on workshop, so on the rails run through to show what the tool could do. Everyone was converging on the same idea at that point, that the spec was what mattered, and it all felt a bit contrived from Kiro just formalising it. The first time I used Kiro was in a guided workshop at AWS Summit London. ...

Something appeared on my screen while I was in Codex the other day and I didn’t know what it was. A little animated creature, off to the side, and I don’t know which keys I pressed to bring it up. I clicked it, which made it change to voice mode and so now I couldn’t get rid of it and it was listening to me. In the end I opened ChatGPT in another window and asked how to get rid of the pet that OpenAI’s coding tool had just put on my desktop. ...

I was on site during a Windows 10 migration about eight years ago, and the group I’d cut over the previous day started coming to me with the same problem. They were opening files they’d opened the day before, and now some threw an error about a missing font and refused to open at all. Others opened with chunks of text gone, or the formatting pushed out of shape. The characters in those files were never damaged. Every letter was sitting there in the PDF and the file itself was fine, which is why the same documents opened without complaint on a machine that hadn’t been touched yet. What was missing was what turns those characters into shapes on a screen. ...

I got off the Marker waitlist on a Saturday and planned to poke at it for an hour. It’s a writing tool built by a small team in London that deliberately won’t write for you, which sounds like a limitation until you use it, and what it does instead is read what you’ve written and ask you questions about it. I’ve spent a number of sessions with it now across about two weeks. ...

I was listening to the Era Vulgaris album before a Queens of the Stone Age gig, and it put me back in Birmingham between finishing secondary school and starting university. The technology I had then was a 17-inch gaming laptop running Vista, and I chose it over a desktop because I wanted something I could take with me. (A possible error given how heavy it was) It came to the US with me for my second year of university in 2008, and once I’d bought some cheap speakers it was the entire setup for the year, because the screen was big enough that I didn’t need anything else. Before that I’d never had my own machine at all, I shared a PC with my brother. ...

I ran out of usage in Claude on an afternoon and wanted to carry on working in ChatGPT, which I already use most days for Codex, but I quickly realised the two aren’t set up the same way. The surface comparison is easy. The harder part is what actually survives the move from one tool to another. ...

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. ...