News for hackers. Stuff that matters.
Re:AI in software engineering at Google: Progress and the pa... by WalterSear on Friday June 07, 2024 @02:31AM (#40605863)
IMHO, review is a misnomer for where software engineering is going. I'm not sure where we are going, but review implies less responsibility for the outcome.

But I do think that we will have less depth of knowledge of the underlying processes. That's the point of having a machine do it. I expect this, however, to be a good trend: the systems will need to be up to a task before it makes sense to rely on them.

Re:AI in software engineering at Google: Progress and the pa... by reacharavindh on Friday June 07, 2024 @03:06AM (#40606041)
This is how progress (in developer productivity) has always been made. We coded in assembler, then used macros, then a language like C, Fortran, then more of Java/Go/Puthon/Rust/Ruby et al. A developer writing a for loop over a list in Python need to necessarily know about linked lists and memory patterns because Python takes care of it. This frees up that developer from abstracted details and think one level closer to the problem at a higher speed.

LLMs _can_ be a good tool under the right hands. They certainly have some ways to become a reliable assistant. I suppose in the way of LLMs, they need better training before they can get there.

Re:AI in software engineering at Google: Progress and the pa... by discreteevent on Friday June 07, 2024 @06:07AM (#40607078)
> We coded in assembler, then used macros, then a language like C, Fortran, then more of Java/Go/Puthon/Rust/Ruby et al.

The difference is that:

1) All of those things are deterministic [1]

2) In all of those cases I can debug at the level of the abstraction.

[1] Meaning: Do exactly what I say. Don't make it up.

Re:AI in software engineering at Google: Progress and the pa... by CoastalCoder on Friday June 07, 2024 @07:22AM (#40607506)
I agree with your overall point.

In a certain sense I'd say optimizing compilers aren't deterministic:

The same source code can produce different object code, depending on data and algorithms into which a typical programmer has little insight.

Re:AI in software engineering at Google: Progress and the pa... by vitiral on Friday June 07, 2024 @08:52AM (#40608252)
Being a bit pedantic. Globally but not locally deterministic
Re:AI in software engineering at Google: Progress and the pa... by shrimp_emoji on Friday June 07, 2024 @09:20AM (#40608461)
Your brain's not deterministic.
Re:AI in software engineering at Google: Progress and the pa... by kibwen on Friday June 07, 2024 @09:22AM (#40608472)
Crucially, optimizers are supposed to be semantics-preserving, and if they aren't that's considered a major problem.