I’m the opposite. Tabbing through boilerplate increases my flow.
The hidden cost of AI coding
321–330 of 475 posts
Re: The hidden cost of AI coding
#322Most comments here surprise me: I am using Githubs Copilot / ChatGPT 4.0 at work with a code base which is mostly implements a basic CRUD service... and outside of small/trivial example (where the generated code is mostly okay), prompting is more often than not a total waste of time. Now, I wonder if I am just totally unable to write/refine good prompts for the LLM (as it works for smaller samples, I hope I am not to…
Copilot is just plain bad. The result is day and night compare with cursor + gemini 2.5 (of course with good prompting)
Re: The hidden cost of AI coding
#323Some people love programming, for the sake of programming itself. They love the CS theory, they love the tooling, they love most everything about it. Other people see all that as an means to an end - and find no joy from the technical aspect of creating something. They're more interested in the end result / product, rather than the process itself. I think that if you're in group A, it can be difficult to understand g…
I think a closer analogy is:
- A singer might learn to play guitar to sing along to it. Guitar is a means to an end; it is simply a tool to them.
- A guitarist learns to play guitar due to love of the instrument.
Re: The hidden cost of AI coding
#324Earlier quoted context omitted.
Plenty of incorrect code compiles. It is a very bad sign that people are making comments like "Then the code won't compile". As for my editor saying it is invalid..? That is just as untrustworthy as an LLM. >I "trust" LLM's more than tutorials, there's so much garbage out there. Yes, rubbish generated by AI. That is the rubbish out there. The stuff written by people is largely good.
> Plenty of incorrect code compiles. It is a very bad sign that people are making comments like "Then the code won't compile". I interpreted the "hallucination" part as the AI using functions that don't exist. I don't consider that a problem because it's immediately obvious. Yes, AI can suggest syntactically valid code that does the wrong thing. If it obviously does the wrong thing, then that's not really an issue ei…
> Yes, AI can suggest syntactically valid code that does the wrong thing
To be fair, I as a dev with ten or fifteen years experience I do that too. That's why I always have to through test the results of new code before pushing to production. People act as if using AI should remove that step, or alternatively, as if it suddenly got much more burdensome. But honestly it's the part that has changed least for me since adopting an AI in the loop workflow. At least the AIncan help with writing automated tests now which helps a bit.
Re: The hidden cost of AI coding
#325I found myself recently making decent superficial progress only to introduce a bug and had a system crash (unusual bc it’s python) bc I didn’t really understand how the package worked (bc I bypassed the docs for the AI examples). It did end up working out ok - I then went into the weeds and realised the AI has given me two examples that worked in isolation but not together - inconsistent API calls essentially. I do like understanding what I’m doing as much or more than getting it done, bc it always comes back to you, sooner or later.
Re: The hidden cost of AI coding
#326Some people love programming, for the sake of programming itself. They love the CS theory, they love the tooling, they love most everything about it. Other people see all that as an means to an end - and find no joy from the technical aspect of creating something. They're more interested in the end result / product, rather than the process itself. I think that if you're in group A, it can be difficult to understand g…
I've always distilled this down to people who like the "craft" and those who like the "result". Of course, everything is on a scale so it's not either/or. But, like you, how I get there matters to me, not just the destination. Outside the context of music, a project could be super successful but if the journey was littered with unnecessary stress due to preventable reasons, it will still leave a bad taste in my mouth…
> I've always distilled this down to people who like the "craft" and those who like the "result".
I find it very unlikely anyone who only likes the results will ever pick up the craft in the first place
It takes a very specific sort of person to push through learning a craft they dislike (or don't care about) just because they want a result badly enough
Re: The hidden cost of AI coding
#327Earlier quoted context omitted.
Those of us who write software professionally are literally in a field premised on automating other people's jobs away. There is no profession with less claim to the moral high ground of worker rights than ours.
[flagged]
> Automating jobs away is good for workers. Not bad.
Sure, if you completely disregard the past 200 years or so of history.
Re: The hidden cost of AI coding
#328Earlier quoted context omitted.
Picasso (if he really said that) had a machine painting for him?
Picasso explicitly wanted his designs (for cutlery, plates, household items he designed) to be mass-produced, so your question is not as straightforward as you make it to be.
What is the connection to machine generated code? He designed the items manually and mass produced them.
No one objects to a human writing code and selling copies.
Apart from that, this is the commercial Picasso who loved money. His early pre-expressionist paintings are godlike in execution, even if someone else has painted a Pierrot before him.
Re: The hidden cost of AI coding
#329Would you be happier and feel more flow if you were typing in assembly? What about hand-punching cards? To me this reads more as nostalgia than a genuine concern. Tools are always increasing in abstraction, but there’s no reason you can’t achieve flow with new tools. Learning to prompt is the new learning to type.
Re: The hidden cost of AI coding
#330Most comments here surprise me: I am using Githubs Copilot / ChatGPT 4.0 at work with a code base which is mostly implements a basic CRUD service... and outside of small/trivial example (where the generated code is mostly okay), prompting is more often than not a total waste of time. Now, I wonder if I am just totally unable to write/refine good prompts for the LLM (as it works for smaller samples, I hope I am not to…
Play with Cursor or Claude Code a bit and then make a decision. I am not on the this is going to replace Devs boat, but this has changed the way I code and approach things.