Following a quip on LinkedIn about the introduction of Recall in Copilot+ and Kevin Beaumont’s great piece about why this is a really bad idea from a security point of view, I got thinking: This is dystopian techno-fascism Kevin posited a disconnect in Microsoft that led to the creation of this feature and whether people really wanted it. Personally, I’ve got a brain like a sieve and would not know the command line without ~/.

Many conferences have a hallway track, I loved that Agile Manchester had a jigsaw track. The organisers put out a jigsaw on a big table where attendees could mingle over searching through the 2000 pieces and chat at the same time. Such a great way of breaking the ice. And such a brilliant metaphor. A complex task is achieved through self organisation. Teams self-select and offer assistance all without intervention and imposed coordination or management.

When I stumbled across a post that an encryption library offers a potential backdoor to SSH connectivity on Good Friday, my first thought was: why is it always on a Friday that these things drop? And then my second one: oh bugger, here goes my weekend. Now, I won’t go into the technical details, there are many, many, many, many better resources out there, but I can’t help thinking that this would/should force the software industry to think.

Peter Drucker said “What gets measured, gets managed”. When I turned up at Old Trafford, home of Manchester’s red team (it’s a security conference, geddit) for The Future of Cyber, I certainly was measurably impressed by the setting even though I’m usually found more on the blue spectrum of infosec. But let’s get into the talks! Measure, measure, measure First, Greg Notch talked about the importance of using metrics in communication.

About two months ago I stumbled across a great YouTube video of a talk by Charity Majors called Compliance standards should be modern development practices. Now let’s step back for a minute. Am I seriously suggesting that anything with the word “compliance” is going to be a riveting watch? Why, yes I am. And with good reason. I’m a fan of good security and I like agile. And I think one of the major stumbling blocks about putting Sec into DevOps is to forget the agile origins of DevOps culture.

Last year was exciting, it was my first time going to a DevOps Enterprise Summit and meeting Gene Kim was very cool. The conference didn’t actually start on Tuesday, there was a little session on Monday as people were trickling in from all over the world. And in said session, Gene presented his latest project. He was writing a book with Steven Spears called Wiring the Winning Organisation. If I’m honest, I am not a fan of the title.

After the glimmer of hope on day 3 I was quite optimistic for the day 4 puzzle. I kept going with the phind-codellama model. I continued with keeping the model on a fairly tight leash and just being very specific as to what I wanted it to do. What’s the puzzle? So, for the first part, we had to parse a text file and then match up numbers and winning numbers.

My experimentation with LLMs on day 1 and day 2 of Advent of Code was a bit frustrating. For the day 3 puzzle, I decided to change model. Previously I had been using the codellama:13b model but wasn’t really happy. I kept arguing with it and it just frustrated me. So let’s try some others. codellama:34b So I thought maybe the model just wasn’t big enough, so off we went

After day 1 of Advent of Code was only partially successful, I thought I would change my approach. Yesterday I tried to get the LLM to develop the whole solution in one go. But that was more like argumentative programming rather than conversational programming, so for the day 2 puzzle I start with small problems and hope to put it all together at the end. Let’s get started The problem looked quite straightforward, parse something like the following

So it is that time of the year again. Advent of Code is back. Yey! This means I get to try to look at a new language again. This time, why not Kotlin? But as an extra challenge, I thought why not see how the vaunted LLMs would help. Is AI really the accelerator that would elevate a mere developer to a rockstar ninja (whatever that is)? I have to add that I am a bit of an AI sceptic and keep saying that