I've been programming now for over fifty years. I'll also say that I'm using vibe coding for personal projects. So far, I'm getting good results. Here are some tips:

1. Know what you're doing. Right now, I'm working on an interpreter for a DSL. But I already know the basic structure of interpreters. I can tell when the code the AI is turning out is good or bad. When it's bad, I tell it what's good and ask it to correct the bad code. This usually works.

2. Vibe code in small chunks. I didn't say code the interpreter and here's the syntax. I coded it piece by piece - language primitives, environment structure, control flow primitives, etc. Each step of the way I checked the output to make sure it was what I wanted.

3. Let it write tests. Again, AI's are pretty good at looking at a piece of well-written code and building tests for it. If you point out corner cases you want tested, it will crank those out pretty well.

4. Show it what you want. If you want a particular style in the code, let it know. It will follow that extremely well.

5. Use it for boilerplate. Let's say I have five primitive types in my language. I work with the AI to generate the first one. Then I say "Do the same thing for these other four primitives". AI works well off examples, so give it some.

AI works pretty well if you know what you're doing and how to use it. I think of it as a relatively diligent junior coder. And it works about that well.

I'd be more worried about zero day workweeks brought about by AI.

Why are you trying to get new programmers to write code? Isn't vibe coding supposed to be taking over that niche? I'm not sure if I'm serious or not, but it seems a valid question in this day and she.

... where will you find experienced workers seven years from now? Seems like someone's making a really big bet on AI improving a whole lot soon. And when the next AI winter comes, a lot of people will be paying a lot more for the workforce they need.

Do I switch to a *nix system or buy an overpriced Apple system for music production? REAPER, my DAW of choice, is available on all three systems (or was, I haven't checked since the M-series switchover on the Mac). I've worked with all three systems at various times since the 1970's. However many of my plugins and musical instruments are only supported on Windows or Mac. All I know is that both non-open source systems have screwed their users over in the past and are likely to do so in the future. There's not an easy solution here...

This project will help us to identify and remove mundane tasks that drain your energy so that you can focus on the most engaging and highest value work to make your job better.

Is this the latest corporate euphemism for "Mo metrics, mo better"?

If you, like the Alabama Supreme Court, think that everything short of a perfect live birth for every embryo is grounds for prosecution, what's to keep every pregnancy and behavior of a pregnant woman free of potential scrutiny, litigation, and potential prosecution? Alabama is sending a message loudly and clearly to every woman: If you find yourself pregnant, get the hell out of Alabama before they decide that you aren't giving that lil' ol' baby inside you proper care and decide to send you to prison for a few years. The sad thing is that is the stated viewpoint of a certain political party and soon people stupid enough to vote for this party will find themselves exposed to this sort of stupidity. Poetic justice? Probably. But then, stupidity has always produced it's own reward.

It's another reason why most mainstream languages suck. You can't install a new version of Python without it breaking half your code. Constantly changing versions of widely used libraries because "worse is better" and the developers couldn't be bothered to get the thing right the first time. Oddly enough, there are languages that try to avoid this. Common Lisp hasn't changed since the 1980's. Clojure avoid breaking changes like the plague. There are also languages outside the Lisp family that make stability a priority. My recommendation is that people who value their code avoid non-stable languages. It may be easier for lazy language developers who deliver half-assed features, but it makes life hell for people using the language.

It's a crappy system for sure. Cities have to figure out why it's a losing game and stop doing it. Maybe a Federal law against local bribery of businesses would work.

It's also an indirect argument why MLB needs salary caps (and in the cases of quite a few owners, salary minimums).

To be fair, the guy who suggested this did have a device that gave him useful output.

Most of us just look at our phones to see what time it is.

Get rid of the pesky humans that might form a union or show initiative. in some sub-optimal way. Replace with robotics. Everybody wins. Especially the shareholders. But also the human who no longer has to deal with a boss yelling at them. That thought will comfort them as they starve to death and we're rid of them once and for all.

I've been threatening for years to write a wonderful paper called "Why Agile is (Mostly) Bullshit". However without a replacement methodology to give managers a set of pretty charts and the appearance of control, it would do no good. In fact, having been in the industry as both an individual contributor and/or manager for 40+ years, I could safely broaden the title to "Why Methodologies are (Mostly) Bullshit" without much change. I think as long as IC's understand that their management is for the most a bunch of insecure flunkies and that methodologies are (mostly) security blankets to ease these insecurities up the management chain and provide (usually poor) estimates to allow upper management to budget and make (usually inaccurate) promises to customers, everyone can play the game without too much grief. But whatever the methodology, it simply acts as a multiplier for any behavioral pathologies that are in the organization and so can turn life into a living hell if these are not quashed or managed effectively.