zlacker

>>tablet+(OP)
> An LLM can be instructed to just figure all that shit out. Often, it will drop you precisely at that golden moment where shit almost works, and development means tweaking code and immediately seeing things work better.

Well, except that in order to fix that 1% you'd need to read and understand whatever the LLM did and then look for that 1%. I get the shills just thinking about this, whether the original programmer was human or not. I'd rather just write everything myself to begin with.

>>puttyc+Zb
Reading code is vastly quicker than writing it from scratch.

>>nojito+wo
This is a lie, unless you are just speaking of the mechanics of cursorily skimming it. Reading code to understand it enough to commit it in my name is harder and slower than writing it myself.

>>abenga+ny
Firstly, you are not the other poster, so I don't know how you can say it's a lie with conviction.

Second, reading code to understand it is a skill that you need to practice to get better at. That might be your issue.

>>dymk+jG
It’s not the OP’s issue. That reading code is harder than writing it is as close to a consensus belief as we get in this industry.

https://www.joelonsoftware.com/2000/04/06/things-you-should-...

>>sarche+vR
Which is why it's a key skill that differentiates professional software engineers from amateurs.

>>simonw+lS
You think Joel is an amateur? And the scores of other professional engineers who have written about this are also amateurs?

I mean they could be wrong, but I don’t think you can call them amateurs.

>>sarche+oT
I think Joel is a professional, and that's why he says "reading code is harder than writing code".

You seem to be misunderstanding me. I'm not saying "anyone who thinks reading code is harder than writing code is an amateur". I'm saying "reading code IS harder than writing code, which is why being good at reading code is what separates experienced programmers from beginners."

>>simonw+3U
Ok so you disagree with the person that kicked this off with

“Reading code is vastly quicker than writing it from scratch”

>>sarche+uV
Only if you're not very good at reading code. If you've invested a lot of effort in improving your code reading and code review skills you can work a lot more productively with LLMs than people who don't have good code reading skills.

>>simonw+fX
So you think that reading code is harder, but if you put in equal amounts of practice at reading and writing code you’ll get faster at reading code than writing code?

Sounds to me like you don’t think reading code is harder.

>>sarche+fG1
I think reading code is harder than writing code.

I think that if you put the work in you can get to a point where you are fast enough at reading and reviewing code that it's not a net productivity loss to have an LLM - or your coworkers and collaborators - write code for you to review, as opposed to insisting on writing every line of code yourself.

I'm a little surprised that my opinion about this is seen as controversial!

>>simonw+FI1
Your position is confusing to me as well.

> if you put the work in you can get to a point where you are fast enough at reading and reviewing code

Please correct me if I'm wrong, but "fast enough" here would still be slower than writing the code yourself (given equal amounts of practice at reading and writing code), right? To throw some made-up numbers around: if it would take me 20 minutes to write code to do X, it might take me 30 minutes to read/review code that does X written by somebody else (or an LLM), so I'm at a net loss of 10 minutes. Can you explain the mechanism by which this eventually tips into a productivity gain?

Personally, I think "reading code is harder than writing code" lacks nuance. While I believe it's true on average, the actual difficulties vary wildly depending on the specific changeset and the path it took to get there. For example, writing code can involve exploring many solutions before eventually discovering a concise/simple one, but when reading the final changeset you don't see all those dead-end paths. And reviewing nontrivial code often involves asynchronous back and forth with the author, which is not a factor when writing code. But please take the "reading code is harder than writing code" claim for granted when responding to the above paragraph.