I like these efforts to neatly categorise the extent of AI usage in a project. I do think they need some kind of neutrally worded classification but this and the original post are fine attempts at this emerging niche. It's important to some of us and I look forward to what ends being adopted.

... aaaand now it's JATS.

> LLMs still can't write Gleam/Janet/CommonLisp/etc

hoho - I did a 20/80 human/claude project over the long weekend using Janet: https://git.sr.ht/~lsh-0/pj/tree (dead simple Lerna replacement)

... but I otherwise agree with the sentiment. Go code is so simple it scrubs any creative fingerprints anyway. The Clojure/Janet/scheme code I've seen it writing isn't _great_ but it gets the job done quickly and correct enough for me to return to it later and golf it some.

> This architecture was subjected to a definitive stress test at 100,000 years using a single-file artifact.

what does this even mean?

Yup, I also couldn't figure out after scrolling and skimming two or three pages.

Some understandable short sentence or paragraph early on needs to answer the main question the title raises.

See also `gdu` for an `ncdu` more suited to SSDs: https://github.com/dundee/gdu

Session resets at 2:30am

fwiw, I'm finding claude2 released a few days ago to be a lot less infuriating

I had stopped using the sonnet model for anything important after some very big goof ups. 4.5 is definitely significantly better.

I've been totally blown away by opus except on a project I'm working on I discovered a few unexpected weaknesses that have cost quite a bit of time.

Not at all. I can't stand it either. It's definitely patronising and infantile. I tolerate the silliness, grit my teeth and move on but it wears away at my patience.

This is why I add anime catgirls to nearly everything I build. I'm glad the effort isn't in vain!

I think I'd be down for anime catgirls in my builds. Something particularly anti-corporate about that I could get behind.

Hey, good luck with the interview!

The Vero 4 and Vero V by the OSMC team are amazing: https://osmc.tv

They do a terrible job of marketing themselves though, so quite underrated.

Don't all the XBMC/Kodi-likes suffer from having poor support for mainstream content providers. I've looked a few times over the years, and add-ons for Netflix, YouTube, iPlayer, etc. were slow and terrible for discovery. If you knew the exact name of what you wanted to watch they were just about ok, but beyond that they just didn't fit the paradigm of something that was designed for browsing static libraries of content.

Isn't the whole premise of Roku that it does this well with cheap hardware?