Yeah, "We are looking for a developer specialized in Java code following idiomatic COBOL which hasn't been tested in production yet and which nobody is sure about whether the exact behavior matches what's been running in production. You will enjoy meaningful work in an environment which has been considering engaging in environmental matters for decades and which bears the social conditions of fellow human beings as a core value. The pay is good, but remember you are a Java developer, not a COBOL developer. Job starts as soon as possible."
There's a "familiarity with what's already existing" dimension too.
A new developer to the team can research quickly using AI, but experienced folks won't get much over just using their current knowledge.
It shows up as a new team member coming up to speed impressively fast. But since doesn't help the rest of the team it also doesn't contribute much to the overall team's productivity.
I did not say anything about distance. I said cycling enables you to go faster than you could possibly travel without it (ie. faster than you can sprint). What you do with that speed is up to you, but most use it to get to places in less time or get further in the same amount of time. The point is it's not about laziness, it's about unlocking new capabilities.
If cycling were just about laziness then you'd see people cycling at walking speed everywhere, which you never see.
Since we're kinda talking about LLMs too, it's interesting to note that while cycling really does enable you to go faster than you can run, LLMs do not enable you to type at 1000 words per minute. LLMs are more like a teleport that only lets you describe your desired destination, you cannot simply enter a coordinate to get exactly where you want to go.
This is a very good analogy. You have to do way more effort to make sure it's correct than if you have asked it yourself with a controlled context. I generally don't want to feel lucky when I ask questions to coworkers.
I started drinking decaf black instead of coffee for the past several years now, that seems to help the psychological ritual of drinking coffee in the morning to wake you up but not actually have (or have very small amounts of) caffeine.
No. I’m expecting everyone to answer direct questions that they are the only one who can answer by thinking up the answer with their own brain then writing or speaking that.
> every human thought can be written as a sentence.
No they can't. I have things in my brain that I don't have words for, that I'm able to find things other people have done to help me express them. You can attach sentences to music and art, but a picture is worth a thousand words. The thoughts on my head when I saw the latest Banksy, for example. Maybe I'm abberationally ineloquent, but I don't think I'm that exceptional.
I hoped it obvious that I am not comparing being a liar and a bad family man to being a serial rapist (unsurprisingly there is quite few allegations of this exact same behaviour against Polanski). I simply used Polanski and MJ as obvious examples of A) why not separating the art and artist absolutely is not just “immature virtue signaling” B) how people loving the art are able to compartmentalise the evidence and suffering of the victims to keep enjoying the art, meanwhile making any justice very difficult.
There’s artist with whom we can “forget everything else”, then there’s not. Where one draws the line, well, I suppose that up to one’s own discretion, but I would recommend offering a serious thought on where oneself draws the line.
No. There is this persistent belief in the industry that programmers should be good at everything, not just programming itself: communication, product management, design, sysops, UX, coaching, management, testing and so on. The most visible product of this belief was the once hyper hyped role of “full stack” developer.
The really is that you could have experts in each area doing what they’re good, which means letting programmers actually program most of the time, and let business analysts figure out requirements, product owners decide features, designers decide UX and design, QA perform in-depth testing… sure , every programmer will have to manage some of this themselves to not get blocked the whole time waiting for someone to decide something, but that is NOT the same as just having programmers handle everything!
I think that if you only ever hire programmers who are also kind of people person, you definitely have to accept missing out on the antisocial but genius ones who are very likely the only ones capable of tackling the really hard problems! Unpopular view, I know, but it takes a certain type of person to achieve excellence in some areas. Just look at the most successful artists, writers, actors and especially CEOs. Programmers are clearly in that category. I’ve seen “normies” trying to write a little code. They don’t last an hour before they decide it’s bullshit that you need a semicolon precisely placed for the code to not explode, or that they can’t compile on this system until you’ve installed some tool chain that requires a bunch of commands no one knows by heart but you just need to make sure to follow exactly, otherwise hell may break lose.
Without an active harness (eg. Appium) that can end-to-end deterministically verify the changes you make continue to work correctly it is almost impossible to continue to keep the same pace on the app.
Unsupervised LLMs (even fabel) are categorically
incapable of running parallel unsupervised mobile app feature development.
That is my personal, first hand experience working in a team in this space.
What you are (I guess?) experiencing is user-in-the-loop light touch LLM development where you can 80% most tasks quite quickly (much faster than without assistance!) with a small number of human developers working on largely unrelated features and manually verifying they are correct and manually fixing the platform specific issues you encounter.
Maintaining a strong appium end-to-end test suite is still extremely challenging with notifications and maps.
Honestly, it blows my mind you could even being to claim that of all things, native apps using obscure languages like swift are suitable for this, compared to the much much easier path of web + react.
I'm taking a slightly different approach. I've started a project where I intentionally don't use agentic coding. I use LLMs for researcher and to learn, but write all the code by hand.
The goal is to maintain the taste, for lack of a better word, that I've developed over decades of programming.
Claude put me on to the concept "Étude", so I've taken to calling it my Étude project.
I moved into a ghetto in the Netherlands and holy fuck. I'm staying here for a few more years just to earn money and once I have around million euros I'm out of this godforsaken country and then to a place that doesn't look like a gypsy camp. Maybe Czechia?
I don't see why it may fail to integrate. Declare Pin as !Move and... thats all? I mean, there will be issues, edge-cases because it is just how these things happen, but still I don't see any fundamental issues with continuing to use Pin.
We operate Critical National Infrastucture for financial services. We have a lot of regulatory requirements that probably don't apply to most organisations.
