19 February 2026
The Gemini AI will make some pretty good guesses about how a 3rd-party API may work. It is good at searching the internet, but when APIs have changed across versions, the old and new docs and examples it’ll find can confuse it. In a dynamic language and environment you’ll not spot these errors until runtime.
To combat the ambiguity and to give the AI agent more power to solve its own problems, ask it to add some tests around the code that uses the API. (In my case, the API is the XTDB client API.) Once it has a way to execute the code through tests, it’ll quickly start figuring out where it’s made mistakes and start running its own experiments to observe errors, search for fixes, and applying those fixes around the codebase. I exhibit the same pattern when I’m doing it by hand.
The tests also give you, the human, an easier entry point to evaluate the code the AI generated. If the tests look gnarly, you know to suggest refactorings to improve the architecture and make it easier to test. When the AI has the tests passing, and the test code is easy enough to read, then you can have a closer look at the application code to refine and keep that maintainable too.
31 December 2025
I’ve had Gemini CLI installed on my workstation since August 2025.
Originally,
it would default
to use the gemini-2.5-pro model
and your "access" to that
would run out for the day,
and it would switch to using gemini-2.5-flash.
I found the flash model to be adequate
for the way I’d use it to do Clojure and ClojureScript,
so most the time I’d override
it to just use flash from the beginning.
I thought I could kick over to pro
if I found a problem for which I’d need more power.
Eventually,
Gemini CLI started switching back and forth
between models more intelligently,
so it didn’t burn through your limited access
to pro,
so I no longer override it with 3.0 models.
The AI agent by itself has read lots of documentation, and it’s pretty good at Googling the answers to questions and picking something to try. (I often get a bit of analysis paralysis when trying to choose a library.) It can be surprisingly good at translating sample usage of some JavaScript library it finds into a simple bit of ClojureScript.
In my experience, it’s sometimes bad at matching parentheses, so I just fix them myself. Recently, it may be getting better, and some Clojure MCP projects can cleanup parentheses automatically.
I only ask it to do small tasks,
and I closely review and test
the code it generates.
When it looks good,
I commit and push the code,
but I know I can always
easily go back to a previous working version
when the AI goes off the rails.
I don’t have to worry too much
about it getting too confused
or destroying something.
I tell it to forget what we were doing,
/clear the context,
or just restart the agent completely,
and recover my known good state from git.
(Update 2026-02-17:
/rewind may be better these days
for clearing some context.)
I find that even if it fails to complete a task, I at least learn a little from what it did, and often have an initial direction or two to explore.
It’s pretty good at keeping my momentum when working and keeping me from spinning my wheels, like pairing with another programmer.
28 January 2022
My Google Assistant on my phone has been refusing to turn on and off the 2 devices I have on smart plugs: "Can’t reach SmartThings."
I found an article about the Google Home doing the same thing. Fortunately, the advice there worked: go into Assistant’s settings → Devices → Add Devices. Upon clicking on the SmartThings entry that was already there, it gave me the option to re-link. Once I authorized access, I could again ask Google to control those devices.
21 September 2019
Google Calendar makes the world go 'round, especially for kids who travel between households and have lots of school events. There are a couple things you can do to get the most out of your calendar.
Calendar events obviously come with times and fixed reminders so many minutes before the event. It doesn’t matter where you are or where the event takes place: that notification is coming at the same time.
With a location set on each calendar event, other software, like Waze GPS, can continuously watch your current location and offer you a more useful notification giving you time to travel based on distance and current driving conditions along the way.
Most my calendar events have just one start time, but my kids' events aren’t that simple. A marching band performance may be at 7pm, but the bus to the stadium leaves at 4pm. Since we live by notifications, it’s important to get those notifications at the earliest time at which we need to act. The other times are likely just extra details that can go into the event title or event details. I can get a notification for 4pm and realize I don’t need to be there until 7pm, but I can’t tolerate a 7pm notification if I was supposed to be dropping a kid at the practice at 4pm.
If I find it’s important to see notifications for all the potential times of an event, then it’s probably best to break that event into more than one event: drop-off, performance, and pick-up.
This is the first and most useful collaboration feature of Google Calendar. A personal calendar benefits one person, but invite the other participants (the kids), and then they can start adding and maintaining events and following these rules as well.