[ctippett]

Yeesh, is "never reading the code" really the modus operandi we want from AI?

Microsoft, for all their warts, at least had the compassion to call their AI product "Copilot", suggesting we have some residual agency in whatever it is that it produces.

[quantumleaper]

Copilot is a legacy brand from 2021 (anyone remembers it's free beta? good times) when it was just a rudimentary autocomplete powered by GPT-3. I don't think it aligns with Microsoft's views and priorities now.

[modriano]

It's clearly not the MO that capable engineers want, but it's the MO that is getting funded right now.

Reading code carefully is harder than writing code unless the code is written consistently and clearly in a way that is idiomatic to the reader. And there's way more code to review now, but companies aren't scaling up the number of skilled engineers on staff. So in practice, never reading all of the diffs is the MO that will be built into code we depend on.

[lelanthran]

> It's clearly not the MO that capable engineers want, but it's the MO that is getting funded right now.

Quite a few capable engineers really are that short-sighted!

The bigger question for the AI-techbro questioning "If AI writes your code, why use Python?" is "If AI writes your code, what use do we have for you?"

After all, there's dozens of people in the same business that have better domain knowledge but are unable to program - as a programmer the only value you added over random analysts and clerks was that you could automate shit.

Now you can't, so good luck competing with people who were already making half your salary when your largest value-prop is now gone.

[simonkagedal]

There are lots of good use cases for vibe coding (”never reading the code”), prototypes, various explorations and one-offs. I’ve done various kinds of migrations where I didn’t bother to review the code much, just the output.

Possibly also some user-facing tools with a limited task and runtime environment.

Incidentally, these are all use cases where performance isn’t critical, typically, so you might as well write them in Python or Typescript or whatever makes most sense for the task.

Real production code? Yeah, you still need to be able to read it and understand it.

[tedggh]

You don’t need to read the code if you have a robust test suit to validate the output. The article implies testing is the new “reading”. If I spend 10 minutes reading code to find an edge case bug, I have lost the benefit of using AI. AI code is legacy code the moment is generated because I can’t tell why some lines were chosen, so the only way for me to add more features or refactor legacy code is by being very rigorous with testing.

[theshrike79]

Let's say you get access to a microservice from another team in the company. Do you read through and audit every line of code?

What if it's from an external vendor? A 3rd party SaaS?

At which point do you stop caring about reading every line of code you run?

[ctippett]

This is perhaps where our perspectives differ, because I see the usage of LLMs not as an external third-party (another team per your example), but instead as an extension of one's self. Given that lens, I'm highly sensitive to the quality and function of its output, because ultimately its contribution is my responsibility.

I appreciate not everyone feels this way, but that's why I personally would be anathema not to read its code.

[theshrike79]

My philosophy is just to Duck-type the program: "If it walks like a duck and it quacks like a duck, then it must be a duck"

I don't care if the duck is wet spaghetti inside, it does what I need it to do within the parameters I can measure.

If it fails to quack or walk later on, I have production alerts for that and I'll deal with it then.