Rendered at 12:50:24 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
mg794613 4 hours ago [-]
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.
frankling_ 2 hours ago [-]
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".
andai 11 hours ago [-]
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?
Does that mean the title should have been "AI Turned DOOM into a Transformer"?
falperc 6 hours ago [-]
It helped me write my docs!
Sharlin 2 hours ago [-]
There’s no use in writing docs at all if they contain near-zero density of information that can actually be deciphered. LLM word salad is not documentation, it’s only useful if all you care about is checking the box "[ ] write documentation".
MarsZebra 7 hours ago [-]
I pity the AI agent that had to work on this
falperc 10 hours ago [-]
theres no pleasing you people do you expect me to write all my docs and disclaimers by hand
jacquesm 6 hours ago [-]
You won't like the answer to that question ;)
fwip 9 hours ago [-]
It just means there's no sense trying to read the docs.
falperc 6 hours ago [-]
That’s entirely fair. I’ll certainly work on editing the docs and making them more legible over time.
tnms 6 hours ago [-]
Yes. Don't be lazy.
9 hours ago [-]
bjconlan 8 hours ago [-]
Came for the "doomformer" based snow lyric puns... Left with a feeling my people are on slashdot.
whycombilater 3 hours ago [-]
Just how clever can an infinite recursion of someone disappearing up their own backside be?
slowin 12 hours ago [-]
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.
falperc 12 hours ago [-]
you have to know a lot about lots and lots of DOOMs, in parallel
I havent fully recursed but what I have done with this is use a DOOMformer to generate a level, have python compile it, have DOOMformer generate the name of the level, and use a DOOMformer brain to complete said level. I have also trained said DOOMformer (you can see the levels "weights" updating as it trains) to aim better lol
mattmcal 9 hours ago [-]
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.
falperc 6 hours ago [-]
the backbone implementation using ZDoom certainly wasnt difficult, but some aspects of scaling up were tricky. I definitely want to make it at least Boom compatible eventually
nnevatie 3 hours ago [-]
> I turned ...
You mean Claude turned?
nullify88 3 minutes ago [-]
If Claude wrote the readme, technically its correct.
kuberwastaken 4 hours ago [-]
As a fellow doom-weird-places-fitter, this is art. Congratulations :)
nico 6 hours ago [-]
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.
falperc 4 hours ago [-]
oh my god i thought the crysis thing was a Turkish joke i didnt know it was international
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.
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".
>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/...
I havent fully recursed but what I have done with this is use a DOOMformer to generate a level, have python compile it, have DOOMformer generate the name of the level, and use a DOOMformer brain to complete said level. I have also trained said DOOMformer (you can see the levels "weights" updating as it trains) to aim better lol
You mean Claude turned?
I made a classifier play doom[0]. But you turned the whole network into Doom! Amazing
0: https://playground.jeffyclassify.com/#doom