Instead of trying to run DOOM on things, I have instead decided to use DOOM (many, many, many doom games actually) to create a transformer. For a lot of the math required I essentially had to use DOOM game mechanics and voodoo dolls (DOOM is turing complete btw) and exchange them with the actual operations, essentially creating an alternative to NumPy (a 65000x slower one). Thus, I am proud to present DOOMFORMER. Here are a list of things DOOMFORMER can do :
It can classify MNIST digits, even if you write these digits on the map!
It can talk(kinda)
You can use it to make decisions, so, it can play DOOM. Yes! You can play DOOM with thousands of DOOM games now! The marine's mind can be controlled by DOOM, playing on a map generated by DOOMFORMER. Truly, the possibilities are endless, and even larger-scale training of DOOMFORMER could be done on a measly T4.
If anyone would like to help me scale this up and make crazier things, I'd love to work together.
Awesome
>a handwritten digit takes 163 seconds of real-time DOOM in one map at the default schedule and 8 seconds at --opt 3.
What does this refer to? What does schedule mean here, and what are these opt levels?
Edit: oh sweet Jesus
https://github.com/mottopanikeiku/doomformer/blob/main/docs/...
Was there even a human involved at all, or was this a "no mistakes" prompt outcome?
Nothing on this page looks made by a human, its _all_ generated, not a tiny bit of it, _all_ of it.
Guess having the word "doom" and "transformer"in your publication is enough today.
Came for the "doomformer" based snow lyric puns... Left with a feeling my people are on slashdot.
This is absolutely incredible. I feel like this could help visualize a neural network, but you have to know a lot about DOOM to really understand it.
Just how clever can an infinite recursion of someone disappearing up their own backside be?
Self-plug I have a very similar blog post title but a very different approach. Honestly, I like your idea more than my own idea. https://nostalgia.dev/posts/running-doom-inside-a-transforme...
I think it might be more interesting to target Boom/Boom-compatible, if possible, rather than ZDoom. ZDoom already has so many advanced features, you could implement the entire thing trivially in ACS. At least a table of required engine features would be nice to see; some are likely already supported in other source ports.
As a fellow doom-weird-places-fitter, this is art. Congratulations :)
This is so trippy, very cool, love it
I made a classifier play doom[0]. But you turned the whole network into Doom! Amazing
Next step - take the cpu implemented in transformers implement it here and make it play doom. The compute needed still won't be able run Crysis well though.
More AI slop. No thank you.
amazing
Wow!
[flagged]
I wonder what the implementation actually adds over the idea itself. At least part of the appeal of these kinds of projects used to be "wow, someone was actually crazy/eccentric/obsessive enough to go through the effort to do this".
If the idea is clearly feasible, and it's just a question of putting in the work, then what is the point of having an LLM actually do it?
I feel it ends up being no better than a post saying "imagine if...", to the mild amusement of the reader, so essentially it ends up as an instance of "just show me the prompt".