Replied to After two years of vibecoding, I'm back to writing by hand by Mo (Mo Bitar)
Agents write units of changes that look good in isolation. They are consistent with themselves and your prompt. But respect for the whole, there is not.

I’ve been using an LLM for support while I set-up a new Linux environment. It gives me a sounding board and, I hope, some idea of good/best practice.

It also gives me commands, with most of which I am already familiar, so I am happy to copy/paste… BUT, even in a single conversation, I can see it deviating for it’s own suggestions, or making subtle tweaks to commands it already advised me to run and not always explaining why.

It’s clearly not building a holistic “mental” picture of what we’re trying to achieve. It keeps assuring me it is, but it is evidently not actually able to do that. Maybe this is demonstrated by the way it often regenerates ALL the advice it has previously given when asked for clarification on an apparent caveat. This is when the unexplained tilts can creep in.

Knowing a little of how an LLM works, I think I can understand exactly why that is.

With all that in mind, I can completely understand how it can’t reliably develop an actual code base!

It is pretty great at tedious shit like combining and transforming two simple JSON datasets, though!

Replied to https://rubyquartzglasses.me.uk/2026/01/3666/ by Phil Phil
Unless this REALLY picks up in the final two episodes, I’m baffled by this review. I can’t wait to get it over with. The plot is “Spooks” levels of “espionage” nonsense. Thompson’s character, while likeable and against type, is hardly transformational. Whereas, Ruth Wilson playing an e...

It did not pick up. It continued to be mostly ordinary and more than a bit daft.

Replied to Proton Spam and the AI Consent Problem (dbushell.com)
The one where I get very annoyed with my email provider

I had a similar thing from Dominos. They sent me an email that explicitly described itself as a “service message” from survey@feedback.dominosmarketing.co.uk

So, I emailed their DPO and they, obviously, just waved it away. How is anything that directly encourages me to engage with a business for the business’s benefit not direct marketing? 🤷

Where does your customer feedback function sit? Under marketing. So, gathering customer feedback is a marketing activity? No.

Is there maybe space for another ballroom? Or some other sort of redecorating project? Can’t be THAT hard to find something to distract him.

Managers so quick to dimiss complaints about workplace software until they actually have to use it.

“Why do we have to do it that way?”

We have a dedicated Discord server for our little hobby group. It’s been going six years now. It’s a wonderful safe space.

Today, though, this happened:

A warning from Discord advising that an image/gif "May contain sensitive content"

The Online Safety Act has struck. Some of my server buddies are a little outraged but I’m not too fussed. I’m absolutely onboard with the intention. The internet is full of horrible shit that I’d never want my children to see. Or my Dad, for that matter; not unless he REALLY wanted to.

But, as we all know, the implementation is useless. Not least because it’s completely avoidable.

Case in point: I asked the member if he’d been asked to complete the age verification process before he posted the gif. He had not.

So, we can all browse this sensitive content (on Tenor?), via Discord, without verifying our age, just as long as we’re looking at it in the “add a gif” dialogue?

OK. We’ve now established (work intrudes) that it was a gif of the chestburster scene in Alien. I’ve checked and I can, indeed, browse exactly these gifs via the dialogue without having verified my age.

I just… I’m speechless.