architecture involves pseudo-code to some degree

Clue: you can vibe-code pseudo-code. Hell, I vibe-coded a season of screen-plays for a TV series. Once you’re comfortable with the architecture and requirements, then have your agent do a “readiness review” to ensure it thinks you’ve specified everything well enough to code it, then have it plan implementation and execute the plan, and review the output to ensure it’s all consistent with all that documentation, and iterate on the reviews until you’re happy that the only “problems” it’s finding are inconsequential.

Then hand it over to an independent human test team. Like you always should have been doing without LLMs anyway.

I actively sought out automation back then

So did I, it was called C compilers so I didn’t have to do hand coded assembly. They turned out O.K. after the first few buggy generations.

Like the article says they are just focused on MOAR

Then they’re doing it wrong.

It is only when I write the first test and the first function that I start noticing the structure and the limitations

To an extent, you can do this with “the vibe” as well, you just have to stay engaged, do lots of reviews (by which I mean, have the LLM review for you and explain what it finds) and when you decide the architecture needs to be revised, do it - in writing. Your requirements and architecture should be “living documents” developed at least a little bit ahead of the code implementation, and if the current implementation is too far removed from your current vision of how things should fit, throw it out and re-implement from the requirements and revised architecture documents. That’s one huge benefit of a tool that writes code so quickly, it’s much less costly to throw it all out and start over.

Still, eight to ten productive hours a day in any sustained fashion is bullshit, more like 3-4 with a bunch of meetings, learning, deciphering etc. filling out the day.

That’s the norm for cube-farmed drones. As Work From Home I have more opportunity for focused development time and I can actually pull off a couple of 4 hour productive sessions in a day, but those distraction items still pile up.

Something interesting about vibe coding, lately, is that the LLMs are doing bigger and bigger chunks of work, and even when they come back with a prompt, frequently all you have to say is “continue” to keep them chewing away on a big development plan. This means, after you have got decent requirements and implementation plan in place, your minions do the work with minimal direction - freeing you for the important tasks like corporate documented training sessions, skimming through the inbox - I don’t like to simultaneously participate in a conference call and vibe code, but if it’s a passive “listen only” experience that’s usually multi-taskable with the periodic “continue” prompt.

Just like human written code, if you spend extra iterations vibe coding you can shake out more bugs, identiy DRY (Don’t Repeat Yourself) and SSOT (Single Source Of Truth) opportunities that make your LOC count leaner and your code easier to maintain.

If you just ship the first thing that seems to work… yeah, that’s going to look horrible when you revisit it after a few years.

I’d be pulling my hair out too if I had to vibe code all that.

Spoiler alert: the teams have been pulling their hair out doing all that for decades without vibe coding it.

You find yourself signing off on an overwhelming amount of raw code just to keep up with the output that’s expected these days.

Then you’re doing it wrong, very very wrong. And any management that expects you to “just read faster” is management you should be distancing yourself from at maximum possible speed.

No, you can’t review the volume of code that LLMs output, one engineer driving an LLM code generator can create code faster than 10 engineers can review it. However, one engineer driving an LLM code generator, then driving the same and other LLMs to review that code for correctness can.

You can, and also should, be developing documented requirements for EVERYTHING the code is doing - LLMs help accelerate that process too.

You can, and also should, be developing unit and integration tests which ensure that your implementation doesn’t regress as new features are added. LLMs help accelerate that process too.

You can, and also should, be using LLMs to review the requirements, implementation and tests to ensure they are all synchronized, aligned, saying what they do and doing what they say. LLMs help accelerate that process too.

You can, and also should, be doing all of the above for software developed without LLMs, but in my experience the vast majority of teams don’t do good implementation of all the pieces. LLMs are an opportunity to start.

Asymmetric power is where it’s at.

It’s no fun when both sides have full access to all the toys.

Well, there’s the whole “let them eat cake” narrative to go along with that - generations of uber-power and wealth don’t teach much in the way of street smarts. The French aristocracy had no personal concept or grasp or even inkling of what desperation felt like, what desperate starving people would be capable of - and there’s the true logic of it as well: after they revolted conditions did actually get worse - as everyone predicted - but that didn’t matter: as you say, there’s no point in hanging on to a pitiful existence through obesiance just because it might be more pitiful for a generation if you revolt.

Oh, but that won’t happen this time, the elite control all the cannon, most of the muskets, the army is overwhelming, the peasants are weak from malnutrition, they’ll never succeed in a revolt, they’d be fools to try.

Sadly, Bernie is - and always has been - just a politician. One of the few good ones, but still out there playing the popular angles. AI taking everyone’s job is the popular angle of the moment.

The “ultimate question” is: do they really just want a whole lot of people to die? They bluster around the topic like that’s a question that you just don’t ask, but when you boil away all the BS, what’s left is: are you saying that you’re going to lock people out of any possible way to feed themselves and their children and just “let them figure it out for themselves”?

Work is good.

Forced work is slavery - and I think most of the world figured out how bad that was about 150+ years ago.

Just to repeat it for the obtuse: UBI doesn’t mean “permanently sit around on your ass doing nothing” either, because that’s a horrible existence (as proven in the generational welfare state…) UBI is about a safety net, negotiating power, and ending the nanny state rectal probes over every penny they “hand out.”

Given a choice, the vast majority of people will seek out social validation - and in today’s world that’s most commonly found through work - occasionally volunteering - but more often the real feelings of self-worth come from knowing that the people you hang out with all day aren’t just tolerating you, they actually want you there, appreciate you as a person or for what you do or more often both. And that’s what the paycheck does: reaffirm your personal value.

On the other side of things, with (sufficient) UBI they really can end minimum wage and many other “employment guarantees” that de-value that validation of knowing you get to keep your job because your job wants you, not because they’re forced to take you.

Who here enjoys working in a situation where your employer / coworkers don’t want you around?

Who here enjoys interacting with people who are only doing their job because they have no other choice?

Who here thinks the world would be a better place for everyone if we reduced and eventually eliminated those situations?

Where’s my “No Autotune” label?

Hundreds of millions of users paying $50 a month.

That’s a hell of a lot better than .com had back in the day: hundreds of millions of “hits” on their websites, with no proof if there was even a human connected to the request.

turn 1 prompt into 12 and bill the user

I think there’s a whole lot of variability of user experience out there still, and that’s some of what is getting shaken out of the systems - new models are better for some, worse for others. Overall, I think they are still improving, quite dramatically for software creation in the past 12 months, but as they grow in their specialty skills, some of the users who were getting better results for other things do get hurt in the process.

If there ever is such a thing as GenAI, I suspect it will follow the medical model of your General Practitioner referring you to specialists as warranted.

I don’t think the current phase is about sensible business models, it’s about jockeying for position to control the power of the new thing. The people doing the core investment have more money than they will ever need - this is a play to turn that money into more power than it currently represents for them - get in on the ground floor - shape the landscape - help form the regulations and relationships that will propel them up the next rung of the ladder.

It’s a bit like spending $44B for a social media platform then running it into the ground financially - it’s not about the money, it’s about the things you get in exchange for that “waste” of money.