←back to thread

Some thoughts on LLMs and software development

(martinfowler.com)
416 points floverfelt | 9 comments | 28 Aug 25 18:52 UTC | HN request time: 0.618s | source | bottom
Show context
ares623 ◴[28 Aug 25 19:56 UTC] No.45056350[source]▶
> Other forms of engineering have to take into account the variability of the world.

> Maybe LLMs mark the point where we join our engineering peers in a world on non-determinism.

Those other forms of engineering have no choice due to the nature of what they are engineering.

Software engineers already have a way to introduce determinism into the systems they build! We’re going backwards!

replies(6): >>45056412 #>>45056449 #>>45056511 #>>45056669 #>>45056797 #>>45059375 #
1. didericis ◴[28 Aug 25 20:09 UTC] No.45056511[source]▶
Part of what got me into software was this: no matter how complex or impressive the operation, with enough time and determination, you could trace each step and learn how a tap on a joystick lead to the specific pixels on a screen changing.

There’s a beautiful invitation to learn and contribute baked into a world where each command is fully deterministic and spec-ed out.

Yes, there have always been poorly documented black boxes, but I thought the goal was to minimize those.

People don’t understand how much is going to be lost if that goal is abandoned.

replies(3): >>45056889 #>>45057390 #>>45057729 #
2. pton_xd ◴[28 Aug 25 20:50 UTC] No.45056889[source]▶
Agreed. The beauty of programming is that you're creating a "mathematical artifact." You can always drill down and figure out exactly what is going on and what is going to happen with a given set of inputs. Now with things like concurrency that's not exactly true, but, I think the sentiment still holds.

The more practical question is though, does that matter? Maybe not.

replies(2): >>45057031 #>>45057133 #
3. DSingularity ◴[28 Aug 25 21:05 UTC] No.45057031[source]▶
In a way this is also a mathematical artifact — after all tokens are selected through beam searching or some random sampling of likely successor tokens.
4. didericis ◴[28 Aug 25 21:16 UTC] No.45057133[source]▶
> The more practical question is though, does that matter?

I think it matters quite a lot.

Specifically for knowledge preservation and education.

replies(2): >>45057407 #>>45058329 #
5. girvo ◴[28 Aug 25 21:42 UTC] No.45057390[source]▶
> People don’t understand how much is going to be lost if that goal is abandoned.

Ah but you see, imagine the shareholder value we can generate for a quarter or two in the meanwhile!

Editors note: please read that as absolutely dripping with disdain and sarcasm.

6. bathtub365 ◴[28 Aug 25 21:45 UTC] No.45057407{3}[source]▶
Yep, LLM’s still run on hardware with the same fundamental architecture we’ve had for years, sitting under a standard operating system. The software is written in the same languages we’ve been using for a long time. Unless there’s some seismic shift where all of these layers go away we’ll be maintaining these systems for a while.
7. whartung ◴[28 Aug 25 22:24 UTC] No.45057729[source]▶
"Computers are deterministic!"

If I wanted to plumb together badly documented black boxes, I'd have become an EE.

replies(1): >>45058085 #
8. _mu ◴[28 Aug 25 23:13 UTC] No.45058085[source]▶
Underrated comment - computers can be decidedly non-deterministic.

https://en.wikipedia.org/wiki/Metastability_(electronics)

9. beefnugs ◴[28 Aug 25 23:49 UTC] No.45058329{3}[source]▶
Yes, but : not in all cases really. There are plenty of throw away, one off, experimental, trial and error, low stakes, spammy, interactions with dumb-assery, manager replacing instances that are acceptable as being quickly created and forgotten black boxes of temporary barely working trash. (not that people will limit to the proper uses)