[simonsarris]

> if you’re doing this for your own learning: you will learn better without AI.

This is not the distinction I would want to tell newcomers. AI is extremely good for finding out what the most common practices are for all kinds of situations. That's a powerful learning tool. Besides, learning how to use a tool well (one that we can expect professionals to use) is part of learning.

Now most common practices and best practices are two different things. They are often the same, but not always. That's the major caveat for many fields, but if you can keep it in mind, you're going to do OK.

[nartho]

It is a great learning tool for people who are willing to learn and put in the time and effort. Ask good questions, double check everything, read documentation and make sure they understand everything before they move on. It's a tremendous tool if used correctly. People who just hit tab or past everything Claude generates will get worse. The benefits of "the old way" is that even the people who didn't want to put in the effort where making some improvement if only by friction and time spent.

[jayd16]

You can go to a restaurant to see new dishes (which isn't nothing) but it wont exactly teach you how to cook.

[pegasus]

Unless you happen to meet the unendingly patient and helpful cook who is willing to explain the recipe in any depth one desires.

[avian]

You mean the cook who will in the same unendingly patient and helpful manner sometimes confidently suggest putting glue into your dishes and serving your guests rocks for lunch?

[pegasus]

That's part of the cook being helpful. It's how they check that you're not asleep at the wheel and your critical thinking is awake and engaged ;)

[square_usual]

I'm sure these year-old examples of errors from a bad product are still valid!

[tavavex]

What bad product? I'm not as categorical as OP, but acting like this is a solved problem is weird. LLMs being capable of generating nonsensical stuff isn't a one-off blip on the radar in one product that was quickly patched out, it's nigh unavoidable due to their probabilistic nature, likely until there's another breakthrough in that field. As far as I know, there's no LLM that will universally refuse to try outputting something it doesn't "know" - instead outputting a response that feels correct but is gibberish. Or even one that wouldn't have rare slip-ups even in known territory.

[viraptor]

There's a difference between recent frontier coding LLMs and Google doing quick-and-cheap RAG on web results. It's good to understand it before posting cheap shots like this.

[user432678]

You still need to do the cooking yourself to master it. If that cook will be giving you a readymade dish, can you say you can cook? Although yes, that’s the goal for many…

[throwthrowuknow]

It’s all in how you use it. If you want to learn you can just tell it to walk you through the code or write a tutorial with examples and exercises or give you programming problems to solve or use the socratic method or recommend the best human written tutorials and books or review your code and suggest more idiomatic techniques or help you convert a program from one language or paradigm to another and a million other ways.

I like the AI written tutorial method, both Opus 4.5 and Gemini 3 are good at this. You just have to put the effort in to copytype, make changes, ask questions and put what you’ve learnt into practice. AI code review is also great for discovering alternatives you don’t know about.

[BizarroLand]

This is like telling people to learn how to draw by only looking at the masters' paintings in person instead of tracing and imitating from possibly stolen but otherwise cheap books at home.

I would say to at least just read what the AI does and ask it questions if you don't understand what it did. You can interactively learn software development from AI in a way that you cannot from a human simply because it won't run out of patience even if it will lie to you.

The results depend mostly on how you use it.

[afro88]

It's also extremely good at describing what code is doing, architecture, extrapolating why something is done a certain way etc. Invaluable for me for learning how unfamiliar code works in unfamiliar languages