> The problem was clearly this excerpt because we all know which country it was.

Oh yeah? Which?

Did you take down djournal? It returns a 404 now.

I think I want a physical AI device.

I want an AI assistant that I can use truly hands free. I keep my phone in my jacket when I'm riding my motorcycle. I want to be able to start, stop, adjust, and check details in route guidance. I want to be able to ask what the weather is like ahead on my route. I want to be able to ask it to start looking for a sensible place for me to stop for fuel and/or food without making me do a big detour.

Actually I would also quite like better driving directions, since I can't look at the directions on a screen.

None of these demands need an AI in a box.

They need software companies to give a damn and improve apple maps/gmaps/etc.

Or perhaps pull over and adjust your routing like most of us do, or maybe bolt a sacrificial phone with maps on it to a holder. If you don't want to risk your main phone.

> Or perhaps pull over and adjust your routing like most of us do

The entire point is I don't want to have to stop in order to receive new information.

I don't know how to make that clearer, sorry.

Todays pulling over to adjust planning is yesterdays pulling over to make a call, and yesteryears pulling over to throw a map on the hood.

Riding on a motorcycle is already dangerous enough with the average land tank driver on their phone. Talking to your AI assistant while riding at speed sounds like pending split focus disasters waiting to happen.

I think it’s time you hand in your licence.

Earbuds exist.

I use Shure se215 IEMs inside my helmet together with a Cardo Packtalk (which includes a microphone mounted inside my helmet).

The audio setup is not the problem.

The problem is when I say "Hey Siri, cancel route guidance," it will say something like "…You must unlock your iPhone to do that."

The entire point is that I can't take my gloves off, get out my phone, and unlock it, at speed, on a motorcycle.

There are competent CTOs who are not above getting their hands dirty, and there are career politician type CTOs who have no discernible skills beyond projecting an illusion of technical brilliance.

I've seen plenty of both, and I'm sure everything in between exists too.

> career politician type CTOs

Good description; that's been the my majority of companies unfortunately.

How about product only CTOs who quietly hate engineers because they don't know what they do, and they constantly feel threatened

Max Martin, not Martin Max.

Thanks ChatGPT. Really بعيد insightful read.

> Most bugs are logic errors.

Are they? IME most bugs are type errors.

Or rather, IME most bugs are logic errors only because I've excluded the possibility of type errors by using a sophisticated type system.

Most of my bugs are logic errors. I write Java. Your comment seems to imply that moving to Rust or Haskell would make a correct program if it compiles.

I don't think porting your program to Haskell would make your program correct.

I think porting your program to Haskell would make all of your bugs logic errors, rather than only most of them.

Except it isn't the same because the cost is different, which allows discovery that we couldn't afford previously.

Yes, lots of the process and problems and solutions to them are the same but we’ve just massively cut the cost of a part of development. That has huge ramifications about when it makes sense to tackle different things and how tradeoffs work out.

Was it strongdm talking about the dark factories? They were working on some integration software so needed to use google drive and slack and lots of other things. They fully reimplemented those to the level they needed for their tests - outside of the biggest firms this would probably have been an enormous time and money sink. Now it’s reasonable.

On a personal project, with my wife we wanted a tracker for holiday planning. Five minutes given a barely through through request and we had a working prototype, fixed bugs in seconds and then talked through with a model what we needed and how it did or didn’t fit (and we needed that first version to figure that out). It helped drive out actual requirements from us, prioritise them, choose a stack add tickets and then went ahead and implemented it pretty far. Have a mostly working v2 which has highlighted some details about what we really wanted. Total invested cost was one day of a $20 subscription and maybe half an hour of talking to a bot and checking results.

Yes x 1000. I find it amazing.

Lots of Polish people on this website, including me.

What makes you think you're in a position to qualify the morality of the deaths of my not-so-distant relatives at the hands of Nazi invaders?

You'd be surprised at the amounts household name companies spend on broken software. I've personally seen multiple companies spend tens of thousands paying just for the opportunity to evaluate the broken software. And I don't mean the time taken for their own employees to spend doing the evaluation. I mean that plus forking over large piles of cash.