But if you just ask them the question and don't tell them what you've found or where you got stuck, you're asking them to stop doing what they're doing and spend all that same time you just spent working on your problem.

It's a reducer of time.

For less experienced developers, it's an immediately reduction at the start of a project. But then they will almost certainly have problems later when their initial decisions come back to haunt them.

For senior devs, it's like having a junior or mid-level dev that will instantly do things within their capability, so long as it's explained to them well enough. This junior dev will do things fairly smartly, but any important decisions left to them will be wholly or subtly wrong. And the subtle ones are the worst ones, because they're so hard to detect.

But if that senior dev sets the guidelines well enough, and notices the problems, development is so, so, so much faster. It's wild.

The only question is where the line is.

His trouble isn't just from the time in jail, though. It's from all the Trump supporters who harass him as well. Previously, and in the future.

If manage is reasonable, you can explain to them that there isn't time to check the work of the AI, and that it frequently makes obscure mistakes that need to be properly checked, and that takes time.

At this point, if they still insist you just give it the AI's work, they've made a decision that is their fault. You've done what you can.

And when the shit hits the fan, we're back to whether they're reasonable or not. If they are, you explained what could happen and it did. If they force responsibility on you, they aren't reasonable and were never going to listen to you. That time bomb was always going to go off.

An outsourced developer isn't a "tool". They're a human being, and responsible for their actions. They're being paid, and they either act responsibly or they get replaced.

A vibe coder is a human using a tool. The human is responsible for code quality, and if it's not good enough, they need to keep using the tool to make it better. That means understanding the tool's output.

If an artist used Photoshop to create a billboard ad that was ugly, they don't get to blame Photoshop. They have to keep using the tool until their output is good.

It's not as good, but it's good enough.

This meant that they were completely unable to actually 'approve' a review, but were only able to reject it. They were juniors, so they'd eventually get to that point, but by then, everyone would be used to just ignoring their approvals.

This provides that middle ground.

Absolutely unconscionable.

Ads need to be truthful. They can't just make things up that aren't actually in the product. It's literally false advertising.

I'm not against AI, but I am against deceiving people. If you can't be bothered to actually check your AI's output, you shouldn't be using it.

If they're doing the same thing as the interrupts that the article is talking about, they are low-level.

If they aren't, then the comparison is by name only.

"Interrupts", for example, are an old concept that is rarely talked about anymore until you get into low-level programming. At a high level, you don't even think about them, let alone talk about them.

It's definitely wrong in that paragraph.

And for small things, like cables you don't often use... You never know when you'll need them. I've been telling myself I'm just going to throw them away after all, but then within a month of deciding that, I end up using a cable that I hadn't even seen in 2 years, and I had to hunt pretty hard for it. And it's a $10+ cable.

The article sounds like it's going to address these issues with the dots, but then just doesn't. I'm actually not even sure what the point of the dots is other than to convince the author that they're doing something about their problem, when they're really just putting stickers on things and buying more bins.