Here are all the blog posts I've written, starting with the most recent. If you're looking for something in
particular, you can see all the titles on one page in the site map. If you want to stay
up-to-date with what I'm writing, you can subscribe to the RSS feed in your favourite
feed reader.
In most Star Trek series, the ship or station computer is ever-present in the background, waiting to be called
on by the main characters. It nearly always does exactly the right thing, and there’s little limit to the
functions it can perform. Take this mundane example from DS9:
KIRA: Computer, establish link with the Bajoran Medical Index for the Northwestern District.
COMPUTER: Link established.
KIRA: Access all information on Doctor Surmak Ren.
COMPUTER: There are no records matching that name.
KIRA: Try the Northeastern District, same search.
COMPUTER: Doctor Surmak Ren, currently serving as Chief Administrator of the Ilvian Medical Complex.
KIRA: Computer, open a channel to the Ilvian Medical Complex. Administrator’s office.
The computer is doing some kind of networking to a database only identified by name. It does a search and
summarises the lack of results. It then repeats the process with another database, and succinctly announces
the results. Finally, it opens a communication channel to a specific room in a facility, based only on its
name.
This whole interaction is remarkably boring. Kira doesn’t have to know any URLs or API endpoints, or what
protocol she wants to use. She doesn’t have to open a specific app and then login and then try the query
again. She just says what she wants and the computer does it.
It seems like this should be one of the most easily obtainable bits of sci-fi wizardry with our current
technology. We have multiple massive companies throwing lots of money at digital assistants, LLMs that are
improving at an insane rate, but we’re somehow not even close to the usability or usefulness of the Trek
computers. What gives?
Boring is, well, boring.
Larry Page once said something that might help explain it:
The Star Trek computer doesn’t seem that interesting. They ask it random questions, it thinks for a while. I
think we can do better than that.
This is the same Larry Page that founded Google, whose mission statement is “to organize the world’s
information and make it universally accessible and useful”. Of all people, surely he should find an
omnipresent computer that can answer ‘random questions’ interesting?! It seems like it should be the epitome
of Google’s mission!
I recently encountered a bug in one of my projects that I couldn’t immediately figure out. It was an issue in
Centauri, my reverse proxy. After its config was updated, I
noticed it stopped serving responses. Looking at the logs, I could see it was obtaining new certificates from
Let’s Encrypt for a couple of domains, but I’d designed it so that wouldn’t block requests (or so I thought).
After a few minutes of confusion, everything went back to working.
It felt like an issue with locking, but a quick glance didn’t show me anything obvious. I decided to throw the
problem at Claude Code and see how it did. With some guidance it managed to identify the cause, but it was a
bit of a journey to get there. I’m going to share the prompts and responses, as it was an interesting process.
The initial prompt
I thought the issue might be quite obvious, and I’d just overlooked it. Centauri isn’t that complex a project,
after all. So I gave Claude a fairly minimal prompt to set it off:
> Hello! Please examine this codebase. I have noticed an issue that when a
certificate is being renewed, the application seems to not serve any other
requests. I suspect there is a misplaced lock somewhere.
Can you see what's happening? Think very hard.
Claude Code has
special hardcoded triggers to
engage “thinking” mode, which makes it take more time to think about alternatives. The keywords are: “think”,
“think hard”, “think harder”, and “ultrathink”. I managed to not quite get the right incantation here, and
only enabled the lowest level.
I’ve been using Tailscale for around four years to connect my disparate
devices, servers and apps together. I wanted to talk a bit about how I use it, some cool features you might
not know about, and some stumbling blocks I encountered.
I’m not sure Tailscale needs an introduction for the likely audience of this blog, but I’ll give one anyway.
Tailscale is basically a WireGuard orchestration service, with lots of nice features sprinkled on top. It’s a
subscription product, but it has an insanely generous free tier that covers basically anything you’d ever want
to do as an individual. They also open source all their client software, and there’s a third party control
server implementation called Headscale if you want to
avoid the hosted system entirely.
Basic connectivity
At its core, Tailscale lets you easily connect from one device to another, even if they’re not directly
exposed to the Internet. You install the Tailscale client wherever you like (on your phone, computer, servers,
Raspberry Pi, etc), authenticate the machine with the control server, and it can then talk to all the other
machines on the tailnet using their private Tailscale IP addresses.
That isn’t anything revolutionary: it’s the basic premise behind VPNs. But Tailscale makes it so easy. You
don’t have to bother with any networking configuration. You don’t have to distribute keys. You just install
the client, and login.
I’ve written about LLMs a few times recently, carefully dodging the issue of ethics each time. I didn’t want
to bog down the other posts with it, and I wanted some time to think over the issues. Now I’ve had time to
think, it’s time to remove my head from the sand. There are a lot of different angles to consider, and a lot
of it is more nuanced than is often presented. It’s not all doom and gloom, and it’s also not the most amazing
thing since sliced bread. Who would have thought?
It’s worth noting that I’m just setting out my position here. I’m not trying to convince you to change your
mind. To set the scene a bit, I mainly use Claude Code as a programming tool. I use the Claude chat interface
sometimes to proofread things, do random one-off data analysis, or help organise things. More rarely I’ll try
to use it to brainstorm things, or recommend things, or do more “creative” things, but I don’t trust it enough
in those domains to do it often. I don’t use it for research or as a Google replacement, which I recognise
probably makes me a weird half-in-the-water, half-out-of-it class of user.
Copyright & Corporate Control
One of the key issues, and something that is being prosecuted in several court cases right now, is how LLMs
interact with the copyright system. And by “interact with” I mean “run roughshod all over”. It seems pretty
obvious from my lay perspective that if having 10 seconds of pop music in the background of a YouTube video is
copyright infringement, then
Meta pirating books via BitTorrent
must also be.
This, dear reader, is a hammer. It is almost entirely irrelevant to the article. Enjoy.
I presume everyone is familiar with the idiom “if all you have is a hammer, everything looks like a nail”. If
not, well, there it is. It’s generally used pejoratively about being single-minded, but I think it also gives
a glimpse into something more interesting: mental and perceptual sets.
Before I explain, let me tell you a story about a person who bought a 3D printer. When they were first
thinking about getting one, they weren’t sure if it was worth it. They could print a few board game
accessories, but then what? After they got it, though, a whole new world opened up: everywhere they looked
there were opportunities to improve things by adding 3D printed plastic. Broken appliances were repaired with
3D printed parts, all sorts of shelves, organisers, hooks and other things were made. But when they talked
about this to other people, most often the response was “That’s nice, but I don’t think I’d use one”. How
could they not see the truth in all its glorious layer lines?!
The answer is in the concept of a ‘set’, and instead of trying to explain it, I’m just going to quote
Wikipedia:
In psychology, a set is a group of expectations that shape experience by making people especially sensitive
to specific kinds of information. A perceptual set, also called perceptual expectancy, is a predisposition
to perceive things in a certain way. […] A mental set is a framework for thinking about a problem. It can be
shaped by habit or by desire. Mental sets can make it easy to solve a class of problem, but attachment to
the wrong mental set can inhibit problem-solving and creativity.
This perfectly captures what happened. They’d developed a ‘3D printing mental set’: a predisposition to see
problems that can be solved with their hammer 3D printer. Once I started noticing this pattern, I
started seeing it all over the place.
