A Calculator won't increase your creativity directly but it will free resources that you can allocate to creativity!
Coding assistants are solving the wrong problem
91–100 of 151 posts
Re: Coding assistants are solving the wrong problem
#92"Experienced developers were 19% slower when using AI coding assistants—yet believed they were faster (METR, 2025)" Anecdotally I see this _all the time_...
This is actually amazing, isn't it? we are just 21% away from becoming faster then?
Also I don't even care about speed, since I've managed to get soooo much work done which I would not even have wanted to start working on manually.
Re: Coding assistants are solving the wrong problem
#93Earlier quoted context omitted.
Because bugs are bad. Fixing one bug but accidentally introducing three more is such a pattern it should have a name.
They are. And we have processes to minimize them - tests, code review, staging/preprod envs - but they are nowhere close to being 100% sure that code is bug free - that's just way too high bar for both AI and purely human workflows outside of few pretty niche fields.
When you use AI to 'fix' something you don't actually understand the chances of this happening go up tremendously.
Re: Coding assistants are solving the wrong problem
#94"Experienced developers were 19% slower when using AI coding assistants—yet believed they were faster (METR, 2025)" Anecdotally I see this _all the time_...
The article they are referring to is 404, but based on the URL was published bit more than year ago. That's quite long time in a field that is evolving so rapidly and which even the pioneers are still figuring out.
Re: Coding assistants are solving the wrong problem
#95Earlier quoted context omitted.
Why would you ever, outside flight and medical software, care about being 100% sure that the change did not introduce any bugs?
Because bugs are bad. Fixing one bug but accidentally introducing three more is such a pattern it should have a name.
I propose "the whack-a-hydra" pattern
Re: Coding assistants are solving the wrong problem
#96Some of the conclusions remind of the "ha ha only serious" joke that most people (obviously not the Monks themselves) had about Perl; "write only code". Maybe some of the lessons learnt about how to maintain Perl code might be applicable in this space?
Re: Coding assistants are solving the wrong problem
#97> There’s a name for misalignment between business intent and codebase implementation: technical debt.
I wish we'd stop redefining this term. Technical debt is a shortcut agreed upon with the business to get something out now and fix later, and the fix will cost more than the original. It is entirely in line with business intent.
Re: Coding assistants are solving the wrong problem
#98Re: Coding assistants are solving the wrong problem
#99Earlier quoted context omitted.
It's not just about elegance. I'm going to give an example of a software with multiple processes. Humans can imagine scenarios where a process can break. Claude can also do it, but only when the breakage happens from inside the process and if you specify it. It can not identify future issues from a separate process unless you specifically describe that external process, the fact that it could interact with our origin…
So, your point is that programmers identify the unexpected edge cases through the act of taking their time writing the code by hand. From my experience, it takes a proficient developer to actually plan their code around future issues from separate processes. I think that it's mistaken to think that reasoning while writing the code is at all a good way to truly understand what your code is doing. (Without implying tha…
> From my experience, it takes a proficient developer to actually plan their code around future issues from separate processes.
And it takes even more experience to know when not to spend time on that.
Way too many codebases are optimised to 1M DAU and see like 100 users for the first year. All that time optimising and handling edge cases could've been spent on delivering features that bring in more users and thus more money.
Re: Coding assistants are solving the wrong problem
#100> Experienced developers were 19% slower when using AI coding assistants—yet believed they were faster
One paper is sure doing a lot of leg work these days...