Hacker News Reader

Comment by tfandango | Hacker News Reader

We get to check a box on what AI we use when we close a ticket. I used to select "none" because most of the time that was the case, sometimes I would pick one if I used it to build some scaffolding or explore some performance issue.

But then we started having AI demos with the CTO where the presenters would say things like "I don't know how to code in python but now I don't need to! yay!" and the C level people would be very excited about this. That's when I realized that these poor developers who just want to brown nose and show off to big cheese are instead making an argument for their own demise.

Meanwhile I asked AI to make me a test and it mocked out everything I wanted to test, testing nothing, but passing. I wonder how much of these kinds of tests we have now...

View on HN

> Meanwhile I asked AI to make me a test and it mocked out everything I wanted to test, testing nothing, but passing. I wonder how much of these kinds of tests we have now

This sort of thing is what I'm most worried about with programmers who are very bullish on AI.

I don't think it's too controversial to say that most developers are much worse at reviewing code than they are at writing code

AI generated code is a code review exercise. If you accept my premise that most devs are worse at reviewing code than writing it, this should ring some alarm bells

You're spot on about developers being worse at reviewing code. With generated code, you still need to understand it if you want to maintain it.

I had another person send me some AI generated code that was close to 90% working. It was missing something simple (something like appending to an array instead of overwriting it...) The original developer could not understand or debug it. I'm afraid of the crap we're going to see over the next few years.

This is a great point. This mocked test, easy to literally click a button, look like you did something good, but potentially add massive negative value when the code fails but the tests all pass. It can be a very helpful tool, but you need to understand the code it produces, and it seems like people are missing that point.

It is the "we copied this snippet from stack overflow without understanding it" problem, except turned up to incredibly high volumes

There are multiple factors exacerbating this even further:

1) AI generated code is "soulless". Reviewing code can be engaging if you are trying to understand your colleagues thought process. Sometimes you learn something new, sometimes you can feel superior, or politely disagree. AI ain't worth the hassle.

2) You unlearn how to write code by relying heavily on LLMs. On some level, it is similar to an IDE giving you context clues and definitions. On another, it can replace the hard work of thinking things through with mediocre yet usually workable solutions. And that's the big trap.

> Sometimes you learn something new, sometimes you can feel superior, or politely disagree. AI ain't worth the hassle.

Often I am looking for opportunities to mentor a less experienced developer

Why bother if they are just offloading their thinking to AI

> Why bother if they are just offloading their thinking to AI

Because you get to make them cry when you show them the error of their AI ways.

Consider it a teaching moment if you can show them why the AI-generated code is insufficient for production.

You could make an analogy to the engineer babysitting a self-driving car during testing: you'd need to be a better driver than most to recognize when the machine is about to make a mistake and intervene.

Pff we will just use another AI to do the review /s

I think I'm somewhat decent at code reviewing, what I'm seeing currently is though that the PRs become larger and larger. Because AI just rewrites everything, even if you tell it to fix things. This leads to devs pushing more and bigger code changes. I'm convinced no company has enough senior developers to review these vast amounts of sloppy code.

Reply on news.ycombinator.com