Author: Ross Wintle

IT issues…

I've been having really odd issues with laptops lately. My work laptop running MacOS Tahoe refuses to recognise any sound-input device connected by USB, relegating me to Bluetooth-connected or built-in mic’s.

And yesterday I plugged my laptop in by USB-C/Thunderbolt cable to my monitor (which has a built in USB hub and basically works as a dock) and nothing connected. After about 40 mins of swapping things around I decided the Thunderbolt cable was dead.

ARGH!!!

Finally for today, and I've said this before: I'm REALLY curious about this technology. I WANT it to be good. I am trying it (in work context only). I see others saying it's good, but it's just not. If it was good, it might justify the many, many bad things about it. But it's just not. And I don't understand what I'm missing. I really hope it just goes away soon so I can stop thinking about it.

3) I find the process of using a coding agent so mentally taxing. Mental processes to do something are:
– Convert what I want to do into English
– Add context that the LLM will need to do it well
– Wait (and get distracted by something else)
– Get results (context-switch back)
– Figure out what the code output does
– Figure out if that was what we wanted it to do
– Iterate bugs and style

Manual coding is:
– Convert what I want to do into code
– Iterate bugs and style

2) So much of what I hear about AI is caveated.
– Yeah, sometimes it gets things wrong
– Sure, token prices are going up
– Reading code to verify it is so boring
– I had to keep telling it to do better
– It will be better soon

And yet… and yet… people default to using it. "Oh we can just chuck a load of stuff at this and it will work it out.”

But… you just told me that a) it often can’t and b) it's really expensive to do so!! It's INFURIATING!!!

It's hard not to have thoughts about LLMs every single day.

1) I tried "vibe coding" a small internal tool yesterday. It worked, but the code was terrible. It make no useful suggestions about architecture, didn't question anything, didn't ask for extra information that might have helped, use lots of short and meaningless variable names, left no comments or explanations of how anything worked.

Sure I didn't ask it for these things. But it was BAD code by default.

I just watched King Charles's speech to Congress. Wow!

He basically just went "No one is going to turn this thing off, so I'm going to very British-Politely educate you on your own history and faith and have multiple digs at the current administration while I'm here.”

Great job, Charlie!

RE: https://infosec.exchange/@tinker/116494136372314588

Oh wow – I need to read this about 8 times, and then think hard about who seems to like using AI and who doesn’t.

This could be a thing.

I’m in a mood. Just as well my main co-worker is in the US and gets me in a few hours time!!

Yo! Frickin, B-Corps and “healthy” food companies. Please please please make recycling instructions for you weird might-be-paper-might-be-compostable-might-not-be-recyclable-at-all packaging REALLY CLEAR. Because the people eating this stuff also want to do the right thing. And you’re not helping them.

B-CORPS!!!

😩

A prediction: After plugins that use skills that use MCP servers backed by APIs finally let people take actions by chat, people will decide they don’t actually like typing potentially-ambiguous commands in human language, and will ask if some visual interface can be built on top of the chat bot to allow them to issue it more precise commands.

I’m one idiot who’s often wrong. But I believe people only want chatboxes because UIs suck.

We should just build better UIs!

From BlueSky: "The Child, aged 17, witheringly asks "where did you hear that? ChatGPT?" when I've said something she thinks is stupid."

I don't understand why it isn't more telling that we can detect AI by looking for low quality. I do it at work. Kids are doing it everywhere.

Low quality images. Rambling, incorrect text. Poorly structured code and software that breaks.

🤷‍♂️

After completing a popular, daily, online, letter-based puzzle with two moves to spare, I have suggested to my son that “Wördlinfor” would be a good D&D character name.

He is totally running with this idea.

I mean… Relatively we're doing well. We are in a very fortunate position. But I'm looking at state pension ages going up and lower birth rates meaning the old outnumber the young, and increasing life expectancy and kids being at Uni (maybe) when I'm in my mid-to-late-50's. There's a lot of life to come! And I can't be working for all of it.

I was talking to someone about money today.

I'd love for us to talk more about money. Like… in detail. But it's such a taboo.

I’d love a way for people to be able to anonymously share their financial situations so I can compare because I have no idea if our future is good or bad or what.

Does this exist?

I wanted to get a re-worked Turbo Admin command palette using native HTML dialog in the next release, but it's really fiddly (not because of dialog, but because I need two different implementation of it now).

I really want some of the new features I've built. So I might have to do an interim release without <dialog>.

Hmm…

Ugh. Customer support for my merchant-of-record eCommerce system seems really broken. Haven't heard from them in a week. Only social channel seems to be Twitter.

Not acceptable for such a critical SaaS.

I'm on a pay-as-you-go plan, but even so.

Does anyone know if Lemon Squeezy is alive?

RE: https://crikey.social/@ross/116432820645230306

Do I know any camping/caravan/RV folks who can take questions on a portable solar panel + battery set up. Wondering if I can use something like this for my some power for my south-facing garden office (which is very much like a static caravan!)

It pays for itself in a couple of years. Assuming good use in winter. But that's a lot of daily hassle.

Probably not worth it.

But something in me wants to try, even while I wait for plug-in solar!