[buffalobuffalo]

I mean, that works for you since you're retiring. But for people still working in the industry, you adapt or die. As it's always been.

The fact of the matter is, a person working with a bunch of agents is a lot more productive than just a person. It makes research faster. It makes experimentation faster. It makes output cleaner. And this is true across many disciplines, not just tech.

Also, it is a skill. Yes, anyone can chat with an LLM. But understanding the optimal work flow for what to delegate and what to do yourself is difficult. Understanding the need for precision in the language used, and learning how to elegantly phrase things that were previously just abstract thoughts is absolutely a talent that can be refined.

If i had to guess, I'd say we'll probably see major breakthroughs across multiple disciplines within the next decade, largely because researchers and engineers can cover much more ground individually now, freed from the slow moving coordination mechanisms that team dynamics require. Pretty good for "spicy autocomplete" as you put it.

[LaGrange]

> I mean, that works for you since you're retiring. But for people still working in the industry, you adapt or die. As it's always been.

There are jobs outside of IT. They are harder, they have less benefits, they pay less. It's a whole project to switch your lifestyle so you can even afford them.

I know nobody who regrets making the jump. I hope to make it within this year. I'll be poor, but at least I won't work in IT.

> But understanding the optimal work flow for what to delegate and what to do yourself is difficult.

No it's not, you can learn it in less than a day. I've done it a few times while evaluating how much the agents have progressed (despite what people keep saying, not much).

> Understanding the need for precision in the language used, and learning how to elegantly phrase things that were previously just abstract thoughts is absolutely a talent that can be refined.

Some of us learned technical writing to communicate with _humans_ before, and we're sitting here alternating crying and laughing as y'all scramble to figure it out just to put all that into a hallucination machine.

[eleventen]

> I hope to make it within this year.

What's your plan?

[LaGrange]

Changing flats so it's cheaper (it's hard but still possible here), then go for an entry-level "barista" job.

It's gonna be very broke, but I'm not the first one in my friends circle to make the jump, so I have some support.

Edit: I probably will keep coding. Just... nobody else is ever going to see or use my code again.

[sph]

Respect. I moved countries for lower cost of living, and I’m gonna become a starving artist, so to speak, trying to use my software skills to make myself useful and earn enough to buy food, in a field where human ingenuity still reign supreme.

And if I ever find money under the mattress, I’ll make a solar farm. Something useful for the world, for once.

Better content and poor than living in golden handcuffs.

[raddan]

Why jump now?

If your worry is that you won’t be able to “keep up” and you’ll be laid off, or fired, just wait for that to happen. Keep making a paycheck until then. Then you can start your barista job.

If the problem is that you hate the work, then fine. But why barista? Fine, if that’s what makes you happy. But there are a million jobs out there _if you are willing to relocate_.

[LaGrange]

Bluntly? Because working with y'all is becoming insufferable. Because I don't want to work in IT. Note this isn't "I don't want to program" or whatever. That's cool and fun. But the people in here? Oh gods.

Also I'm sick and tired of working on projects where the best social benefit from my work would be if I stopped. And IT has this talent of doing this to even most superficially useful projects. I worked on solar panel software that got turned into a scam by marketing. That takes a talent, of sort.

The best time to jump out of IT was to never get into it. The second best time is now.

As for why barista? People need food and drink and coffee is great.

[classified]

> working with y'all is becoming insufferable.

It depends on where you land. Not all programmers (and their managers) are brain-amputated zombies. But I do admit that finding that rare pocket of sanity requires a good portion of luck.

[joe_mamba]

Probably goose farmer https://www.linkedin.com/in/dryuan/

[LaGrange]

That sounds quite expensive to start, to be honest. But if you can? Sounds fun.

[cmiles74]

Are they? I remember when heavyweight IDEs where all the rage, there was a similar sentiment that if you weren't using one of them then you would eventually be so much slower that you'd be out of a job. It only took maybe five years until people started asking themselves if the dependency on a big IDE (and cost) was worth it. I don't think anyone would look at someone who prefers a stripped down text editor today and think they are backward or doing it wrong.

We have yet to see hard numbers on time saved by those who use LLM tooling extensively. It could be it doesn't turn out as compelling as we might expect.

Just sayin', I never forced software developers to use NetBeans or Intellij IDEA. I'm certainly not changing my tune and forcing them to use LLM tooling either.

[classified]

Maybe it depends. If what you want to build is one-shot crap anyway, then micromanaging LLMs to make them vomit what you need for that is "productive". I wouldn't know, because I prefer real work over the make-believe and leave the AI coding acolytes to be left behind and die when their ingenious plans explode in their faces.

[znpy]

Keep in mind, we don't do a lot of things that big IDES used to do.

Dumb example: graphical user interfaces. Heavyweight IDEs used to have a GUI designer (Netbeans had a very nice one).

GUI development is niche nowadays.

Also we have much better cross-editor tooling, just think of language servers (https://microsoft.github.io/language-server-protocol/) and build servers (https://build-server-protocol.github.io/). Back in the day each IDE had their own.

Vim and Emacs can do a lot of what IDEs used to offer thanks to language servers and build servers. Before those (lang/build servers) they were largely useless for large scale development (believe me, i tried).

[raxxorraxor]

It can put out code much faster than any software dev. And if you are careful with your prompts and demands, it is good quality code as well.

Especially for visualising data, to just get a quick look at, it can now be done in lightning speed and I am quite familiar with "manual data processing" in a few languages.

AI use me decently outcompetes manual me. Sometimes there are also stupid tasks. Data must be serialised in a certain way for some stupid reason. You prepare the info to be digested and the busywork can be done by agents with little oversight, which otherwise would have taken you a few hours. There simply is a limit in how fast you can read, look up field names, etc... If you outsource these critical paths to AI, you can gain productivity.

I also start way more side projects now and I like manual coding a lot.

[xigoi]

> It can put out code much faster than any software dev.

Judging a programmer by how much code they write is like judging an airplane engineer by how heavy their planes are.

[raxxorraxor]

Of course, it isn't the quantity. It is more about the features you wouldn't implement because manual dev takes a long time and why not let the AI spin up a non-critical site for administration or testing just for you. The cost/benefit calculation shifts a bit.

That said, if you get something quite heavy to lift off, it probably is a decent engineering feet. Not saying it would be the best plane :)

[bergie]

> a person working with a bunch of agents is a lot more productive than just a person

[citation needed]

I try LLMs for something every couple of months, and I have yet to see them produce anything actually correct. Calling non-existing library methods, confabulations, etc.

But sure, they produce a lot of stuff in a short while. The utility of any of that another question.

[jjav]

> I try LLMs for something every couple of months, and I have yet to see them produce anything actually correct. Calling non-existing library methods, confabulations, etc.

That's too pessimistic, the productivity gains are real and substantial.

OTOH, the hype train is out of control. It is nowhere near perfect and requires a lot of handholding and guardrails to avoid going sideways.

You need to adopt it to stay relevant, but don't fall for the excessive hype. At the end of the day the limitations are significant.

[intended]

> That's too pessimistic, the productivity gains are real and substantial.

Source, please.

Even if its self reported, its useful to know.

[jjav]

I ask in honesty, have you used LLMs? Seems to me the productivity gains are obvious.

As for my source, it is my experience at work for both myself, and my direct reports, and my peer teams.

Tiny example: a certain recurring task we need to do to help other teams which requires somewhat tedious analysis but rarely a lot of high level thinking, plus a bit of decision making. A year ago I'd do maybe 2-3 per day because each one took about 30 minutes so I had to find slices of uninterrupted time between other work to complete them.

Just tonight as I was wrapping up the day I did 19 of these in an hour while also catching up on email. I let the bots do all the research in parallel, as each one completed the research I'd either tell it "ok, do it", or if it was asking me for a decision I'd decide and tell it how to proceed.

I count myself as an AI skeptic, in the sense that the hype is way above reality. But that doesn't mean there isn't a huge amount of real gains.