this post was submitted on 07 Sep 2024
58 points (100.0% liked)

TechTakes

1436 readers
133 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 1 year ago
MODERATORS
top 11 comments
sorted by: hot top controversial new old
[–] dgerard@awful.systems 37 points 2 months ago

twitter comment:

they made something that actually does not run doom, which is a first at least

[–] Architeuthis@awful.systems 18 points 2 months ago* (last edited 2 months ago)

Stephanie Sterling of the Jimquisition outlines the thinking involved here. Well, she swears at everyone involved for twenty minutes. So, Steph.

She seems to think the AI generates .WAD files.

I guess they fell victim to one of the classic blunders: never assume that it can't be that stupid, and someone must be explaining it wrong.

[–] wizardbeard@lemmy.dbzer0.com 18 points 2 months ago (1 children)

The Doom community has had random level generators for over a decade without any modern AI garbage involved.

[–] Architeuthis@awful.systems 14 points 2 months ago* (last edited 2 months ago)

This is conceptually different, it just generates a few seconds of doomlike video that you can slightly influence by sending inputs, and pretends that In The Future™ entire games could be generated from scratch and playable on Sufficiently Advanced™ autocomplete machines.

[–] arbitraryidentifier@awful.systems 12 points 2 months ago (1 children)

Skimmed the paper, but i don't see the part where the game engine was being played. They trained an "agent" to play doom using vizdoom, and trained the diffusion model on the agents "trajectories". But i didn't see anything about giving the agents the output of the diffusion model for their gameplay, or the diffusion model reacting to input.

It seems like it was able to generate the doom video based on a given trajectory, and assume that trajectory could be real time human input? That's the best i can come up with. And the experiment was just some people watching video clips, which doesn't track with the claims at all.

[–] dgerard@awful.systems 6 points 2 months ago

yeah, i think they say a human played it but it's not clear if an actual human did.

[–] megaman@discuss.tchncs.de 11 points 2 months ago (2 children)

Can "ai" make a good game, or just a thing that generates video and mostly accepts inputs (and it isnt even hardly doing that)?

[–] dgerard@awful.systems 10 points 2 months ago

Carmack quaking (ahaha) in his boots

[–] SpaceNoodle@lemmy.world 7 points 2 months ago

The second, and yes, only barely.

[–] V0ldek@awful.systems 11 points 2 months ago (1 children)

I didn't seek out the video before, I read about all the glaring problems, but one thing that no one pointed out was... why is the entire thing slow motion?

Like, you know Doom? The game where the brisk pace and constant movement are a core part of its DNA? Witness it running at 0.5x speed and like 5FPS in the year of our acausal robot lord 2024.

[–] Vittelius@feddit.org 6 points 2 months ago

It's running slow because it's running at such a low framerate. The speed and the framerate are tied. Old console games used to work that way, which was a problem because games would run at different speeds in different countries (PAL vs NTSC). This is a solved problem in modern games. Just separate the game logic from the display logic. But this AI can't do that because there is nothing but the video.

Add to that that the AI was probably trained on high framerate footage but is only capable of generating low framerate footage and you get (gestures wildly) this