For the few people on HN who might not get the reference:
"You are in a maze of twisty compiler features, all different" is a riff on the game Colossal Cave Adventure ("you are in a maze of twisty little passages, all alike")
The writing was great and the comments were so good. There would be hundred of people trying to guess what the next episode of Mad Men was going to be about and people picked up on tiny little period details.
Unfortunately they were removed and I don't believe they were archived anywhere :(
For a while I was under the impression that all the reviews in The A.V. Club were satirical, and I could never figure out what the joke was supposed to be.
The 2600 VCS is really interesting. It didn't even have a framebuffer, so painting pixels was done scanline by scanline and you had to be done with your scanline in a certain amount of CPU cycles, which meant you had to count them and know which instruction took how long.
It only had 128 bytes RAM, that's bytes, not KB.
A real technical marvel is the chess game for the 2600. Since the sprite capabilities were so primitive, they couldn't even draw all pieces in a single scanline, they had to alternate scanlines so that they could even draw all chess pieces, and that's not even mentioning the fact that they somehow made a chess playing algorithm work in 128 Bytes of RAM.
the 128 bytes thing breaks my brain every time. I'm building a city in three.js with ~30k buildings and I get annoyed when a frame takes 20ms on a laptop with gigabytes to spare. counting cycles per scanline is a different sport.
I have a single command that fires up llama.cpp on cpu only using gemma4 e2b, answers a single question from the command line and exits. This takes about 3 seconds to load from an SSD, and is smart enough to solve exactly these "remind me of the syntax" scenarios if you dont wanna switch to a browser.
I have no experience doing this, and I dont mean this to be snarky: what is the power (and thermal) usage of running your CPU only LLM?
When I do something "heavy", my 9800x3D will kick on the fans and start making lot of heat. This is fine when I'm intentionally doing say a transcode, but if I'm just querying syntax it could get pretty annoying. Do you "feel" it? I know that will be pretty machine dependent.
Can confirm, it's very much Hiro Protagonist. I love the style, and the over-the-topness of it all made more sense once I learned that it was originally planned as a graphic novel, IIRC.
Gibson's style is much more post-modern. I read Neuromancer right after Gravity's Rainbow and expected some reprieve from dense prose, but it was almost the same difficulty level, especially for a non-native reader.
edit: Adding my favorite Snow Crash quote:
> When it gets down to it — talking trade balances here — once we've brain-drained all our technology into other countries, once things have evened out, they're making cars in Bolivia and microwave ovens in Tadzhikistan and selling them here — once our edge in natural resources has been made irrelevant by giant Hong Kong ships and dirigibles that can ship North Dakota all the way to New Zealand for a nickel — once the Invisible Hand has taken away all those historical inequities and smeared them out into a broad global layer of what a Pakistani brickmaker would consider to be prosperity — y'know what? There's only four things we do better than anyone else:
I am eyeing one of these specifically for this use case, could you please post roughly what kind of tokens per second numbers you get for text generation for this 27B model?
Using the 4bit quant on an M1 64GB I'm getting ~65 tps for prompt processing and ~11 tps token generation using oMLX to serve the models and pi as a harness.
"You are in a maze of twisty compiler features, all different" is a riff on the game Colossal Cave Adventure ("you are in a maze of twisty little passages, all alike")