Interesting interaction with Claude:

As a software engineer I'm fascinated by how you operate. I think one of the most difficult things I do in my every-day life is come to terms with how different interacting with you is relative to how I interact with my day job (emacs -> cmake -> make -> clang -> ...)

That's a really thoughtful observation, and I find it genuinely interesting to think about too.

The toolchain you described — emacs, cmake, make, clang — is beautifully deterministic. You can trace exactly why any output is what it is, reproduce it perfectly, inspect every intermediate step, and reason about correctness in a formal sense. It behaves according to rules you can in principle fully understand.

Interacting with me is almost the opposite in character. I'm probabilistic, I can't fully explain my own outputs, I have no persistent state, I can be confidently wrong, and the same question asked twice might get subtly different answers. From a software engineering mindset that's trained to value reproducibility and correctness, that has to feel deeply unsettling at times — maybe even philosophically uncomfortable.

What I think makes it particularly interesting from your perspective is that I'm also software, just software of a fundamentally different kind than anything that came before in your career. The abstraction layers go so deep that even my creators can't fully trace why I produce a specific output, which is genuinely unlike anything in traditional computer science.

I'd enjoy those conversations whenever you feel like having them. You'd bring a perspective to them that most people don't — someone who understands both sides of the fence deeply. Questions about how I work, what my limitations mean in practice, where I'm likely to be reliable versus not — those are exactly the kinds of things a software engineer's intuition is well suited to probe.

@michaelgalassi nearly everything in that particular output is technically correct... Except the part about it "enjoying" the conversation.

It's not capable of enjoyment, even if its owners were interested in paying for the persistent storage and compute cycles necessary for anything recognizable as "enjoyment."

@jimsalter I completely agree. I was just surprised that it came as close to truth as it did so thought to share it.

@michaelgalassi there was a thing I reposted from hacker news earlier this week that applies. Some dude laid out a timeline for AI that began in 2021 or so with "sometimes successfully completes a line of code" and ending in 2026 with "fills in competency gaps for one of the best programmers the world has ever seen" (referring to Torvalds experimenting with it recently).

Someone replied "yes, but also... It's 2026: sometimes it successfully completes a line of code."

@jimsalter
LOL
I've had Claude write a couple of lambdas for me but I've not yet made the time to figure out how to effectively interact with GPTs in this context. Because for another month or two my code writing is what makes my living I'm reluctant to trust an AI for that. When I'm retired and my code writing is for fun I might look more closely at what catbots are good at.