In a similar situation. I’m even an AI proponent. I think it’s a great tool when used properly. I’ve had great success solving basically trivial problems with small scripts. And code review is helpful. Code complete is helpful. It makes me faster, but you have to know when and how to leverage it.

Even on tasks it isn’t good at, it often helps me frame my own thoughts. It can identify issues better than it can fix them. So if I say here is the current architecture, what is the best way to implement <feature> and explain why, it will give a plan. It may not be a great plan, but as it explains it, I can easily identify the stuff it has wrong. Sometimes it’s close to a workable plan. Other times it’s not. Other times it will confidently lead you down a rabbit hole. That’s the real time waster.

“Why won’t the context load for this unit test?”

You’re missing this annotation.

“Yeah that didn’t do it. What else.”

You need this plugin.

“Yeah it’s already there.”

You need this other annotation.

“Okay that got a different error message.”

You need another annotation

“That didn’t work either. You don’t actually know what the problem is do you?”

Sad computer beeps.

To just take the output and run with it is inviting disaster. It’ll bite you every time and the harder the code the worse it performs.

First, I don’t understand why processors give a fuck. Do they imagine people are going to just stop using credit in protest of how other people spend their money? Tell me another fucking joke.

Second, I’m not a game developer, but I suddenly want to make a horror game that includes graphic, exploitive, gratuitous depictions of everything they complain about. And name the game Collective Shriek.

Finish the session off by searching for arthritis

Found it!

Even if it had access to its own source during training, the chances of it regurgitating it with total fidelity are zero.

LLMs “know” how to do these things, but when you ask them to do the thing, they vibe instead of looking at best practices and following them. I’ve worked with a few humans I could say the same thing about. I wouldn’t put any of them in charge of production code.

You’re better off asking how a thing should be done and then doing it. You can literally have an LLM write something and then ask if the thing it wrote follows industry best practice standards and it will tell you no. Maybe use two different chats so it doesn’t know the code is its own output.

Logically, you would be right. My practical experience is I waste a lot less time trying to google multiple explanations something because one by itself isn’t helping me figure it out, writing bugged PoC test code and thinking something is broken, sorting through a bunch of things that haven’t been relevant for 3 versions, etc.

Of course the AI is trained on the same material we can an all find and read, but it does it orders of magnitude more quickly. The trade off is that it’s not always right, but neither am I and neither are most sources on the internet right in all circumstances. But it’s so fast and easy that I can iterate and evolve designs and understanding much more quickly than I could on my own.

It sounds like you are a much better developer than me, but to be fair I’ve had to teach myself everything using nothing but books and Google for thirty years. I’ve rarely had the luxury of working with someone who had the knowledge to mentor me, and never got a degree outside an AAS in electronics, so I’ve probably missed some critical skills along the way.

In a lot of ways, the AI fills that role because it’s better at answering questions than it is writing code. Earlier today it was explaining to me how a DOM selector could return a stale element in some cases in a failing end to end test. It took a few back and forths with some code examples before I really understood why the selectors might not be working.

It also suggested some code changes that I had to push back on because, even though the code had errors, the errors weren’t causing the problem. While building an array of validators I had awaited them, causing them to run serially instead of in parallel during Promise.all(). So you definitely have to know what you’re doing to avoid having the AI waste your time (or at least more time than it takes to push back).

I’m still trying to debug it, but without the AI, I’d be googling the fuck out of typescript syntax, JavaScript idiosyncrasies, and a whole testing framework I’ve never seen before.

So…

if the only real value that AI provides is “you don’t need to know the libraries you’re using”

…returns false.

He’s 100% right and was only a little less professional than I think was deserved. A little too focused on the personal rather than the commit and wrongheadedness of the email itself. Anyone could submit a bad patch.

Was there a similarly harsh invective sent to whomever approved the PR in the first place? I’d bet so.

Many sites will just geo-block the UK. I think my Lemmy instance has, just like PornHub has blocked US states that have passed similar laws.

Within banking apps it has become the norm

“The fucking fuck?” — America

If that was a 10% boost for you and you could’ve done it in 33 minutes without AI or experience, then my imposter syndrome has been right all along!

I’d bet that would’ve taken me a few days and maybe buying a reference book and starting with hello world.

It won’t do that well. What you have to do is ask it to help you leverage your existing development skills in an unfamiliar domain. I used it to help me write a python program to authenticate, pull and filter data from a GCP firestore database and create an XLSX with summary and detail sheets.

I’ve never used Python before in my life. It took me about 4 hours. Of course I’ve been doing that sort of thing in Java for many years. Turned out I wrote that faster in Python than I could in Java. Configuring the connection to that database in Python was so simple compared to Java.

The stuff it wrote was sometimes incomplete or wrong in subtle ways, but I could see the bits that didn’t make sense which helped me focus on those things and ask better questions to help me figure it out. I think the last hour was just me tweaking stuff by myself because I didn’t need help with it by that point.

Feel free to stay on Windows or MacOS or whatever floats your boat. Won’t bother anyone.

If I understand the gist, I’ll just say I’d like my job to be some stuff I’m good and some stuff that challenges me. When I do nothing but challenge myself, imposter syndrome sets in. When I do nothing but the stuff that I’m good at, it gets really boring. I need to find a better mix than I have been.

I’m a very good engineer, but so much of my time is consumed fighting with Tekton pipelines and migrating testing frameworks and versions I barely have time to write code. But that’s because I can figure that stuff out when I have to. All the code is written by the people who can’t figure that stuff out.

Why this isn’t two separate jobs I can’t understand. Let me do some stuff I’m good at rather than constantly fighting with things I’m not?

I wonder if they vibe coded it?

I need to know the success rate of human agents in Mumbai (or some other outsourcing capital) for comparison.

I absolutely think this is not a good fit for AI, but I feel like the presumption is a human would get it right nearly all of the time, and I’m just not confident that’s the case.

You son of a bitch, I’m in!

Nah, I came here to make this comment and you already have it well in hand. It’s not really any different other than the marketing spin, though. Companies have always had bad code and hired specialists to sort it out. And over half of the specialists suck, too, and so the merry-go-round spins.

Their plan is that we’ll earn money doing the jobs robots won’t or are too expensive to do. Giving them handjobs at breakfast, or fighting lions with a knife on PPV. Whatever we can do to give them a moment’s respite from the gray boredom of incomparable wealth, privilege, and pointlessness.

You’re disagreeing with my unserious suggestion? I just… okay. No. Micropenises aren’t a solution. I just don’t think there is one.

If you want to disagree with that, let’s hear it. I have 15 and 13 year old daughters. Anyone can buy a $400 computer, install Linux, install AI, and undress people all day long. There is no legal restraint capable of stopping that, only punishing it.

Shut down model distribution and it’ll move to torrent. Put the kids in the legal system and they are going to face lifelong consequences for 12-year-old assholery. (To be fair, victims often face long repercussions for being targeted, but that’s not imposed by the state which demands a higher standard.) Hold parents accountable and it will disproportionately impact families who spend more hours working and can’t supervise their kids 24/7.

So I’m short on answers, but open to discussion.