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
Wow, if any AI spoke to me that intimately I would say "let's get a room".
I would of course say "meson and ninja".
I tried your prompt on qwen and although it outlined the same differences, it was much more formulaic and with bullet points, instead of being so intimate.

@markgalassi @michaelgalassi

> I'd enjoy those conversations whenever you
> feel like having them. You'd bring a perspective
> to them that most people don't [flattery intensifies]

What we're looking at here is, if we refer to it analogously with those terribly unpopular old deterministic tools, function maximize_engagement().

Seriously. That's what that "intimate tone" is. Just another bunch of biz sociopaths making number go up.

@markgalassi @michaelgalassi the funniest reference to this I've ever seen was in an indie hip-hop track when the artist describes getting in a cybertruck high and drunk and "the AI talking to me like it's trying to fsck". 🤣
@jimsalter @markgalassi
High and drunk is the only way I would get into a cybertruck. The last time I was high, I was in my teens and I've not been drunk many times since then so I'm pretty safe.
As a zfs convert I don't fsck much any more :-). I have always been fascinated by the number of different pronounciations that poor File System Consistency checK has had. fizick and f-suck are my favorites.
@michaelgalassi I use it pretty nearly exclusively as a euphemism for "fuck" and if we're honest about the situations in which that tool was typically used... It's pretty thematically appropriate, innit? 😅
@jimsalter
The few times that the default "fsck -p" worked sighs of relief would be heard. I remember the sinking feeling when I had to running it in non-preen mode and suffer through all the many questions about freeing blocks and cleaning inode maps. Shudder.

@michaelgalassi "do you want to do the thing that might fix your filesystem OR might make it worse? Either way, please answer individually for the next 3,821 instances of this question."

HORRIBLY designed tooling. Although I do seem to recall it eventually getting a "fuck you, do the things and stop bothering me" option being added.

Emphasis EVENTUALLY.

@jimsalter I first saw the -y option to fsck in BSDi's BSD/386, I don't think it existed in BSD 2.8 on the PDP-11. I wish I remembered if it was present in Bill Jolitz's 386bsd or in NextStep.