Elizabeth :therian: :cascadia:

@Elizafox@social.treehouse.systems

I sometimes post about sports. Mostly about tech.

In a sane society I would not need these but techbros seem to believe consent is implied now sooo:
#nobot #noindex #noarchive #nosearch #nobridge

Age
Mid 30’s
Location
Read the bio
Queer
Yeah
Pronouns
They/them or she/her
Sexuality
Don't worry about that, I don't

Replying to @Elizafox@social.treehouse.systems

LLMs are worthless for software architectural work unless you're extremely dilligent and know where to poke. No manager is going to replace a senior dev with this. No manager would know what to ask, what to say, what to push back on, just silently say yes. The thing is LLMs can get 90% of things right, it's that last 10% that matters, and that 10% is not "obscure things a normal programmer would miss", it's "very obvious glaring holes it just ignored."

Replying to @Elizafox@social.treehouse.systems

I dunno. I don't get why companies want to mandate this crap on their workers when it produces obvious slop and can't do any kind of reasoning beyond basic applications, and to make LLMs scalable to the point of "reliably make a kernel" would take an astronomical amount of tokens and models with probably quadrillions of parameters. Which sounds fake, but no, that's about what it'd take.

Replying to @Elizafox@social.treehouse.systems

Also unlike @ariadne's bunix which it made in a day because it was C and probably extremely well-trodden ground (could just steal shit from Linux + BSD), this has been a slog, comparatively speaking. It is like only 40% of the way to spawning anything in userspace for me. It took two days to even spawn a kernel thread, and it's still not done (returns aren't quite implemented).

Which admittedly is faster than I could have done it, but it has done this kind of incompetently and needs tons and tons of babysitting.

Because I was bored and wanted to see how close this thing was to taking my career from me, I decided to have Claude vibecode a kernel in Rust.

It did not suggest adding an allocator until it had gotten most of the way through creating kernel threads and context-switching.

Did I say "it did not suggest?" I had to tell it to because it was making statically-sized tables everywhere silently.

*golf clap*

I still like n-gate's treatment of Daniel Stenberg and curl:

"The author of curl, Daniel Stenberg, who wrote curl, is so excited to find a country he's allowed into that he takes a break from being the author of curl to tell us about a new version of HTTP, which addresses HTTP/2's "TCP over TCP" problem by migrating to a "TCP over TCP over UDP" model. By formalizing layer violations directly into the protocol, Google can remove any opportunity to interfere with advertising and surveillance, since the application (specified in the standards as Chrome) communicates directly to AdSense without leaking signs of important personal information exfiltration to hostile third parties, such as the user. Daniel Stenberg, author of curl, is the author of curl, which is written and maintained by Daniel Stenberg."

This sentence basically perfectly sums up curl and the author of curl, Daniel Stenberg, who wrote curl :p.