Somebody should make a tea cosy but to fit a cafetiere.
That sounds like a great idea.
Somebody should make a tea cosy but to fit a cafetiere.
That sounds like a great idea.
My current temporary home – and, necessarily, office – is directly next door to some kind of “horse gym”: a contraption a little like a huge revolving door to encourage one or more horses to exercise by walking around it:
Every now and then my peripheral vision registers that there’s a horse outside the window and, for the dozenth time, I look up from my work and glance around to barely catch it vanishing off on yet another lap.
Non-exhaustive list of things I’m doing when I’m writing code, that don’t look like “writing code”:
For all its faults, an AI agent might “write code” faster than me.
But that’s only a part of the process.
My typing speed is not the bottleneck.
Nineteen days after my house flooded, causing extensive damage on the ground floor, the insurance company has finally accepted the claim and is willing to pay for our temporary accommodation in the meantime (a few days in a hotel, a few days with friends although that’s not paid-for, four weeks in two different holiday lets), although we’re still waiting for their thumbs-up on a proposal for a ~6-month let of a house to live in while our floors are replaced and our kitchen rebuilt and whatnot.
Meanwhile, yesterday a surveyor came around and looked at all of our walls. Everything still feels like it’s taking a very long time. I appreciate that insurance companies are a maze of bureaucracy and procedure, but from “this side” of the table – living and working out of strange places, never really feeling “unpacked” but without it being a holiday – it’s all a bit of a drag!
Today, an AI review tool used by my workplace reviewed some code that I wrote, and incorrectly claimed that it would introduce a bug because a global variable I created could “be available to multiple browser tabs” (that’s not how browser JavaScript works).
Just in case I was mistaken, I explained to the AI why I thought it was wrong, and asked it to explain itself.
To do so, the LLM wrote a PR to propose adding some code to use our application’s save mechanism to pass the data back, via the server, and to any other browser tab, thereby creating the problem that it claimed existed.
This isn’t even the most-efficient way to create this problem. localStorage would have been better.
So in other words, today I watched an AI:
(a) claim to have discovered a problem (that doesn’t exist),
(b) when challenged, attempt to create the problem (that wasn’t needed), and
(c) do so in a way that was suboptimal.
Humans aren’t perfect. A human could easily make one of these mistakes. Under some circumstances, a human might even have made two of these mistakes. But to make all three? That took an AI.
What’s the old saying? “To err is human, but to really foul things up you need a computer.”
While cleaning up/assessing damage following our house flood, I finally found a lost digital stylus I’ve been looking for for a couple of months.
Unfortunately it’s been sat under the water line so I don’t know yet if it survived. But it’s FOUND, at least!
(Look at me, finding ways to stay positive!)
I want normal life back now, please.
I appreciate that it’s only 40-ish hours since my house flooded and we had to move out. But with all the stress and activity that’s necessarily followed, it feels like it’s been so much longer.
Unrelated note: why has the person in the room above me at this hotel been using a pogo stick since around 05:30?
James van der Beek died this week of bowel cancer; he was only a couple of years older than I am. I guess I’m at that point of my life where unexpectedly-early celebrity deaths might start being “around my age”.
I’m neither young nor angsty enough to enjoy a re-watch of Dawson’s Creek, but I especially loved him in Don’t Trust the B—- in Apartment 23 so maybe I’ll re-watch that.