Hacker News: busfahrer

New comment by busfahrer in "Quake – 30th Anniversary Update"

busfahrer — Fri, 07 Aug 2026 14:51:10 +0000

Fun fact: The pattern of the torches' flickering is encoded via special strings in the source code:

https://jasemagee.com/post/2022-03-27-26-year-old-quake-ligh...

New comment by busfahrer in "Building a Tiny 3D Renderer for a Tiny Handheld"

busfahrer — Sat, 25 Jul 2026 11:46:23 +0000

For anyone who enjoys this sort of thing, I found this postmortem of an Alone in the Dark clone for PICO-8 highly informative:

https://www.lexaloffle.com/bbs/?tid=3804

New comment by busfahrer in "Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU"

busfahrer — Fri, 17 Jul 2026 10:01:21 +0000

has anyone been able to get bonsai models to run at a proper speed in a x86 windows cpu-only setting, using llama.cpp?

New comment by busfahrer in "What loss.backward() actually does"

busfahrer — Fri, 17 Jul 2026 07:26:47 +0000

For anybody else trying to grok backprop, I found it very helpful to look at karpathy's microgpt, a barebones LLM in 200 lines of python. The autograd itself is just 40 lines, and reading that code and then trying to do a clean room implementation of it is a great exercise:

https://gist.github.com/karpathy/8627fe009c40f57531cb1836010...

https://karpathy.github.io/2026/02/12/microgpt/

New comment by busfahrer in "My Story of 3D Realms / Apogee Part I (2020)"

busfahrer — Fri, 10 Jul 2026 10:03:52 +0000

As a kid I played Ken's Labyrinth, a raycaster FPS from around the same time as Wolf3D. Only years later I found out that this was actually the same Ken Silverman that went on to create the Build engine for Duke Nukem 3D etc. Kind of funny considering the vast difference in tone between these two games.

edit:

https://en.wikipedia.org/wiki/Ken%27s_Labyrinth

New comment by busfahrer in "Train sim created by just one person is being called the best ever made"

busfahrer — Thu, 09 Jul 2026 20:47:21 +0000

I'm on the fence because I have a TSC-X controller and it's unclear if it's supported. Somebody on the forums posted a tool that converts generic joystick axes to keypresses, but not sure how well that works.

New comment by busfahrer in "A road to Lisp: Why Lisp"

busfahrer — Thu, 09 Jul 2026 17:40:56 +0000

> Or maybe Lisp is so pure that it embodies both Light Side and Dark Side, like a god that spawned the programming universe.

This isn't so far off, considering that some people consider the "Lisp in Lisp" bit from the 1.5 manual to be the "Maxwell's Equations in Software":

https://michaelnielsen.org/ddi/lisp-as-the-maxwells-equation...

New comment by busfahrer in "PlayStation Architecture"

busfahrer — Thu, 04 Jun 2026 08:01:05 +0000

The PS1 architecture is fascinating - it will also reveal why PS1 games have such a unique, recognizable style that games are trying to recreate nowadays.

New comment by busfahrer in "Artificial intelligence is not conscious – Ted Chiang"

busfahrer — Thu, 04 Jun 2026 07:57:55 +0000

To add some context, the author of this article is a science fiction writer, one of his stories was adapted into the movie "Arrival".

New comment by busfahrer in "Zero Lines Maze: What the 8-Bit Guy's One-Liner Can Still Teach Us"

busfahrer — Thu, 28 May 2026 12:54:45 +0000

Not a one-liner, but I was impressed by this simple rogue-like written in 10 lines of BASIC:

https://bunsen.itch.io/the-snake-temple-by-rax

New comment by busfahrer in "Lisp in Vim (2019)"

busfahrer — Sun, 24 May 2026 10:50:28 +0000

Having only dabbled in Lisp and knowing nothing about the plugins TFA mentions, there's also this FWIW:

https://github.com/jpalardy/vim-slime

New comment by busfahrer in "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)"

busfahrer — Fri, 22 May 2026 09:59:43 +0000

Thank you, good sir!

New comment by busfahrer in "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)"

busfahrer — Thu, 21 May 2026 19:43:16 +0000

Great, thanks! :-) and to mirror another poster: what kind of prompt parsing (prefill) speed do you get for that model? Also how is the speed for the 27B model?

New comment by busfahrer in "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)"

busfahrer — Thu, 21 May 2026 15:30:54 +0000

I have been contemplating a M5 Pro MBP, but for the life for me I wasn't able to find benchmarks for real-world models, do you happen to know how many tokens per second roughly you get with MoE models like Qwen 3.6 35B/A3B or Gemma 4 26B?

New comment by busfahrer in "Map of Metal"

busfahrer — Wed, 20 May 2026 12:05:36 +0000

Seeing as this is HN, I was expecting something on chemical properties of iron etc, but was pleasantly surprised

New comment by busfahrer in "S-100 Virtual Workbench"

busfahrer — Thu, 14 May 2026 17:21:40 +0000

OTOH, with the IMSAI-8080 you'd have the satisfaction of using the same machine as David Lightman of Wargames fame

New comment by busfahrer in "UnDUNE II"

busfahrer — Tue, 12 May 2026 14:59:25 +0000

To add some context, this was made for the PICO-8 fantasy console, which (by design) is very limited, so it's immensely impressive to see something like this working on it. Honestly, even just the 3D logo from the intro is impressive, and the rest of the game even moreso.

https://www.lexaloffle.com/pico-8.php

New comment by busfahrer in "Show HN: Rust but Lisp"

busfahrer — Mon, 11 May 2026 13:58:50 +0000

So I'm guessing it's sort of like Fennel, which consciously doesn't completely hide its underlying Lua runtime?

https://fennel-lang.org/

New comment by busfahrer in "Running local models on an M4 with 24GB memory"

busfahrer — Mon, 11 May 2026 11:00:21 +0000

I am considering a M5 Pro (18/20C) Macbook with 64GB of RAM, but I'm having a really hard time finding benchmarks of real world models:

Could somebody please provide some tokens-per-second numbers for example for Qwen 3.6 35B/A3B, specifically for Q4 and Q6 quants?

New comment by busfahrer in "Train Your Own LLM from Scratch"

busfahrer — Tue, 05 May 2026 11:58:06 +0000

This is the whole point of Karpathy's nanochat which OP refers to, to train a GPT-2 level LLM for under $100, renting an 8xH100 VM.