> Apparently there’s more cause, effect, and sequencing in diffusion models than what I expected

To temper this a bit, you may want to pay close attention to the demo videos. The player rarely backtracks, and for good reason - the few times the character does turn around and look back at something a second time, it has changed significantly (the most noticeable I think is the room with the grey wall and triangle sign).

This falls in line with how we'd expect a diffusion model to behave - it's trained on many billions of frames of gameplay, so it's very good at generating a plausible -next- frame of gameplay based on some previous frames. But it doesn't deeply understand logical gameplay constraints, like remembering level geometry.

Just want to clarify a couple possible misconceptions:

The diffusion model doesn’t maintain any state itself, though its weights may encode some notion of cause/effect. It just renders one frame at a time (after all it’s a text to image model, not text to video). Instead of text, the previous states and frames are provided as inputs to the model to predict the next frame.

Noise is added to the previous frames before being passed into the SD model, so the RL agents were not involved with “correcting” it.

De-noising objectives are widespread in ML, intuitively it forces a predictive model to leverage context, ie surrounding frames/words/etc.

In this case it helps prevent auto-regressive drift due to the accumulation of small errors from the randomness inherent in generative diffusion models. Figure 4 shows such drift happening when a player is standing still.

But it's not a game. It's a memory of a game video, predicting the next frame based on the few previous frames, like "I can imagine what happened next".

I would call it the world's least efficient video compression.

What I would like to see is the actual predictive strength, aka imagination, which I did not notice mentioned in the abstract. The model is trained on a set of classic maps. What would it do, given a few frames of gameplay on an unfamiliar map as input? How well could it imagine what happens next?

> Google here uses SD 1.4, as the core of the diffusion model, which is a nice reminder that open models are useful to even giant cloud monopolies.

A mistake people make all the time is that massive companies will put all their resources toward every project. This paper was written by four co-authors. They probably got a good amount of resources, but they still had to share in the pool allocated to their research department.

Even Google only has one Gemini (in a few versions).

If anybody Google would know most about that after their LLM memo all that time ago (basically "we're losing because we're trying to fight/compete with OS models"): https://www.semianalysis.com/p/google-we-have-no-moat-and-ne...

Nicely summarised. Another important thing that clearly standsout (not to undermine the efforts and work gone into this) is the fact that more and more we are now seeing larger and more complex building blocks emerging (first it was embedding models then encoder decoder layers and now whole models are being duck-taped for even powerful pipelines). AI/DL ecosystem is growing on a nice trajectory.

Though I wonder if 10 years down the line folks wouldn't even care about underlying model details (no more than a current day web-developer needs to know about network packets).

PS: Not great examples, but I hope you get the idea ;)

> nice reminder that open models are useful to

You didn't say open _what_ models. Was that intentional?

It makes good sense for humans to have this ability. If we flip the argument, and see the next frame as a hypothesis for what is expected as the outcome of the current frame, then comparing this "hypothesis" with what is sensed makes it easier to process the differences, rather than the totality of the sensory input.

As Richard Dawkins recently put it in a podcast[1], our genes are great prediction machines, as their continued survival rests on it. Being able to generate a visual prediction fits perfectly with the amount of resources we dedicate to sight.

If that is the case, what does aphantasia tell us?

[1] https://podcasts.apple.com/dk/podcast/into-the-impossible-wi...

We are. At least that's what Lisa Feldman Barrett [1] thinks. It is worth listening to this Lex Fridman podcast: Counterintuitive Ideas About How the Brain Works [2], where she explains among other ideas how constant prediction is the most efficient way of running a brain as opposed to reaction. I never get tired of listening to her, she's such a great science communicator.

[1] https://en.wikipedia.org/wiki/Lisa_Feldman_Barrett

[2] https://www.youtube.com/watch?v=NbdRIVCBqNI&t=1443s

> It makes me wonder if humans are just next moment prediction machines, with just a little bit more memory built in.

Yup, see https://en.wikipedia.org/wiki/Predictive_coding

> It's insane that that this works, and that it works fast enough to render at 20 fps.

It is running on an entire v5 TPU (https://cloud.google.com/blog/products/ai-machine-learning/i...)

It's unclear how that compares to a high-end consumer GPU like a 3090, but they seem to have similar INT8 TFLOPS. The TPU has less memory (16 vs. 24), and I'm unsure of the other specs.

Something doesn't add up, in my opinion, though. SD usually takes (at minimum) seconds to produce a high-quality result on a 3090, so I can't comprehend how they are like 2 orders of magnitudes faster—indicating that the TPU vastly outperforms a GPU for this task. They seem to be producing low-res (320x240) images, but it still seems too fast.

> It makes me wonder if humans are just next moment prediction machines, with just a little bit more memory built in.

This, to me, seems extremely reductionist. Like you start with AI and work backwards until you frame all cognition as next something predictors.

It’s just the stochastic parrot argument again.

Makes me wonder when an update to the world models paper comes out where they drop in diffusion models: https://worldmodels.github.io/

Also recursion and nested virtualization. We can dream about dreaming and imagine different scenarios, some completely fictional or simply possible future scenarios all while doing day to day stuff.

Penrose (Nobel prize in physics) stipulates that quantum effects in the brain may allow a certain amount of time travel and back propagation to accomplish this.

Did they take in the entire history as context?

Image is 2D. Video is 3D. The mathematical extension is obvious. In this case, low resolution 2D (pixels), and the third dimension is just frame rate (discrete steps). So rather simple.

We can't assess the quality of gameplay ourselves of course (since the model wasn't released), but one author said "It's playable, the videos on our project page are actual game play." (https://x.com/shlomifruchter/status/1828850796840268009) and the video on top of https://gamengen.github.io/ starts out with "these are real-time recordings of people playing the game". Based on those claims, it seems likely that they did get a playable system in front of humans by the end of the project (though perhaps not by the time the draft was uploaded to arXiv).

I also thought this, but refer back to the paper, not the abstract:

> A is the set of key presses and mouse movements…

> …to condition on actions, we simply learn an embedding A_emb for each action

So, it’s clear that in this model the diffusion process is conditioned by embedding A that is derived from user actions rather than words.

Then a noised start frame is encoded into latents and concatenated on to the noise latents as a second conditioning.

So we have a diffusion model which is trained solely on images of doom, and which is conditioned on current doom frames and user actions to produce subsequent frames.

So yes, the users are playing it.

However, it should be unsurprising that this is possible. This is effectively just a neural recording of the game. But it’s a cool tech demo.

The paper should definitely be more clear on this point, but there's a sentence in section 5.2.3 that makes me think that this was playable and played: "When playing with the model manually, we observe that some areas are very easy for both, some areas are very hard for both, and in some the agent performs much better." It may be a failure of imagination, but I can't think of another reasonable way of interpreting "playing with the model manually".

What you're describing reminded me of this cool project:

https://www.youtube.com/watch?v=udPY5rQVoW0 "Playing a Neural Network's version of GTA V: GAN Theft Auto"

You are incorrect, this is an interactive simulation that is playable by humans.

> Figure 1: a human player is playing DOOM on GameNGen at 20 FPS.

The abstract is ambiguously worded which has caused a lot of confusion here, but the paper is unmistakably clear about this point.

Kind of disappointing to see this misinformation upvoted so highly on a forum full of tech experts.

>I found it worth pointing out that this paper is NOT describing a system which receives real-time user input and adjusts its output accordingly

Well you're wrong as specified in the first video and by the authors themselves, maybe next time check better instead of writing comments with such authoritative tone of things you don't actually know.

I think someone is playing it, but it has a reduced set of inputs and they're playing it in a very specific way (slowly, avoiding looking back to places they've been) so as not to show off the flaws in the system.

The people surveyed in this study are not playing the game, they are watching extremely short video clips of the game being played and comparing them to equally short videos of the original Doom being played, to see if they can spot the difference.

I may be wrong with how it works, but I think this is just hallucinating in real time. It has no internal state per se, it knows what was on screen in the previous few frames and it knows what inputs the user is pressing, and so it generates the next frame. Like with video compression, it probably doesn't need to generate a full frame every time, just "differences".

As with all the previous AI game research, these are not games in any real sense. They fall apart when played beyond any meaningful length of time (seconds). Crucially, they are not playable by anyone other than the developers in very controlled settings. A defining attribute of any game is that it can be played.

The movement of the player seems jittery a bit so I inferred something similar on that basis.

Were the agents playing at 20 real FPS, or did this occur like a Pixar movie offline?

Ehhh okay, I'm not as convinced as I was earlier. Sorry for misleading. There's been a lot of back-and-forth.

I would've really liked to see a section of the paper explicitly call out that they used humans in real time. There's a lot of sentences that led me to believe otherwise. It's clear that they used a bunch of agents to simulate gameplay where those agents submitted user inputs to affect the gameplay and they captured those inputs in their model. This made it a bit murky as to whether humans ever actually got involved.

This statement, "Our end goal is to have human players interact with our simulation. To that end, the policy π as in Section 2 is that of human gameplay. Since we cannot sample from that directly at scale, we start by approximating it via teaching an automatic agent to play"

led me to believe that while they had an ultimate goal of user input (why wouldn't they) they sufficed by approximating human input.

I was looking to refute that assumption later in the paper by hopefully reading some words on the human gameplay experience, but instead, under Results, I found:

"Human Evaluation. As another measurement of simulation quality, we provided 10 human raters with 130 random short clips (of lengths 1.6 seconds and 3.2 seconds) of our simulation side by side with the real game. The raters were tasked with recognizing the real game (see Figure 14 in Appendix A.6). The raters only choose the actual game over the simulation in 58% or 60% of the time (for the 1.6 seconds and 3.2 seconds clips, respectively)."

and it's like.. okay.. if you have a section in results on human evaluation, and your goal is to have humans play, then why are you talking just about humans reviewing video rather than giving some sort of feedback on the human gameplay experience - even if it's not especially positive?

Still, in the Discussion section, it mentions, "The second important limitation are the remaining differences between the agent’s behavior and those of human players. For example, our agent, even at the end of training, still does not explore all of the game’s locations and interactions, leading to erroneous behavior in those cases." which makes it more clear that humans gave input which went outside the bounds of the automatic agents. It doesn't seem like this would occur if it were agents simulating more input.

Ultimately, I think that the paper itself could've been more clear in this regard, but clearly the publishing website tries to be very explicit by saying upfront - "Real-time recordings of people playing the game DOOM" and it's pretty hard to argue against that.

Anyway. I repent! It was a learning experience going back and forth on my belief here. Very cool tech overall.

I knew it was too good be true but seems like real time video generation can be good enough to get to a point where it feels like a truly interactive video/game

Imagine if text2game was possible. there would be some sort of network generating each frame from an image generated by text, with some underlying 3d physics simulation to keep all the multiplayer screens sync'd

this paper does not seem to be of that possibility rather some cleverly words to make you think people were playing a real time video. we can't even generate more than 5~10 second of video without it hallucinating. something this persistent would require an extreme amount of gameplay video training. it can be done but the video shown by this paper is not true to its words.

>Technically speaking, isn't this the greatest possible anti-Doom

When I read this part I thought you were going to say because you're technically not running Doom at all. That is, instead of running Doom without Doom's original hardware/software environment (by porting it), you're running Doom without Doom itself.

> the Doom with the highest possible hardware requirement?

Isn't that possible by setting arbitrarily high goals for ray-cast rendering?

It's the No-Doom.

> Technically speaking, isn't this the greatest possible anti-Doom, the Doom with the highest possible hardware requirement?

Not really? The greatest anti-Doom would be an infinite nest of these types of models predicting models predicting Doom at the very end of the chain.

The next step of anti-Doom would be a model generating the model, generating the Doom output.

to me the closer analogy here is the "running minecraft inside minecraft" (https://news.ycombinator.com/item?id=32901461)

Those are valid points, but irrelevant for the context of this research.

Yes, the computational cost is ridicolous compared to the original game, and yes, it lacks basic things like pre-computing, storing, etc. That said, you could assume that all that can be either done at the margin of this discovery OR over time will naturally improve OR will become less important as a blocker.

The fact that you can model a sequence of frames with such contextual awareness without explictly having to encode it, is the real breakthrough here. Both from a pure gaming standpoint, but on simulation in general.

>What's also interesting about this work is it's basically saying you can rip a game if you're willing to "play" (automate) it enough times and spend a lot more on storage and compute

That's the least of it. It means you can generate a game from real footage. Want a perfect flight sim? Put a GoPro in the cockpit of every airliner for a year.

The skepticism and criticism in this thread is against the hype of AI, it's implied by people saying "this is so amazing" that they think that in some near future you can create any video game experience you can imagine by just replacing all the software with some AI models, rendering the whole game.

When in reality this is the least efficient and reliable form of Doom yet created, using literally millions of times the computation used by the first x86 PCs that were able to render and play doom in real-time.

But it's a funny party trick, sure.

So true. The hustle culture is an spreading disease that has replaced the fun maker culture from the 80s/90s.

It's unavoidable though. Cost of living being increasingly expensive and romantization of entrepreneurs like they are rock stars leads towards this hustle mindset.

Today this exercise feels pointless. However. I remember the days when there were articles written about the possibility for "internet radio". In stead of good old broadcasting waves through the ether and simply thousands of radios tuning in, some server would send a massive amount of packets over a massive kilometers of copper to thousands of endpoints. Ad absurdum the endpoints would even send ack packages upstream to the poor server to keep connections alive. It seemed like a huge waste of computing power, wire and energy.

And here we are, binging netflix movies over such copper wires.

I'm not saying games will be replaced by diffusion models dreaming up next images based on user input, but a variation of that might end up in a form of interactive art creation or a new form of entertainment.

I don’t think this is not useful. This is a stepping stone for generating entire novel games.

I’d like to now to carbon footprint of that fun.

This seems more a critique on the particular model (as in the resulting diffusion model generated), not on diffusion models in general. It's also a bit misstated - this doesn't require a working car on the road to do its job (present tense), it required one to train it to do its job (past tense) and it's not particularly clear why a game engine using concepts gained from how another worked should cease to be a game engine. For diffusion models in general and not the specifically trained example here I don't see why one would assume the approach can't also work outside of the particular "test tracks" it was trained on, just as a typical diffusion model works on more than generating the exact images it was trained on (can interpolate and apply individual concepts to create a novel output).

Interesting point.

In a way this is a "simulated game engine", trained from actual game engine data. But I would argue a working simulated game engine becomes a game engine of its own, as it is then able to "propell the game" as you say. The way it achieves this becomes irrelevant, in one case the content was crafted by humans, in the other case it mimics existing game content, the player really doesn't care!

> An engine would also work offroad.

Here you could imagine that such a "generative game engine" could also go offroad, extrapolating what would happen if you go to unseen places. I'd even say extrapolation capabilities of such a model could be better than a traditional game engine, as it can make things up as it goes, while if you accidentally cross a wall in a typical game engine the screen goes blank.

With enough computation, your neural net weights would converge to some very compressed latent representation of the source code of DOOM. Maybe smaller even than the source code itself? Someone in the field could probably correct me on that.

At which point, you effectively would be interpolating in latent space through the source code to actually "render" the game. You'd have an entire latent space computer, with an engine, assets, textures, a software renderer.

With a sufficiently powerful computer, one could imagine what interpolating in this latent space between, say Factorio and TF2 (2 of my favorites). And tweaking this latent space to your liking by conditioning it on any number of gameplay aspects.

This future comes very quickly for subsets of the pipeline, like the very end stage of rendering -- DLSS is already in production, for example. Maybe Nvidia's revenue wraps back to gaming once again, as we all become bolted into a neural metaverse.

God I love that they chose DOOM.

Similarly, you could run a very very simple game engine, that outputs little more than a low resolution wireframe, and upscale it. Put all of the effort into game mechanics and none into visual quality.

I would expect something in this realm to be a little better at not being visually inconsistent when you look away and look back. A red monster turning into a blue friendly etc.

> one can imagine a near future where text prompts are enough to create a fun new game

Sit down and write down a text prompt for a "fun new game". You can start with something relatively simple like a Mario-like platformer.

By page 300, when you're about halfway through describing what you mean, you might understand why this is wishful thinking

> where text prompts are enough to create a fun new game!

Not really. This is a reproduction of the first level of Doom. Nothing original is being created.

Video games are gonna be wild in the near future. You could have one person talking to a model producing something that's on par with a AAA title from today. Imagine the 2d sidescroller boom on Steam but with immersive photorealistic 3d games with hyper-realistic physics (water flow, fire that spreads, tornados) and full deformability and buildability because the model is pretrained with real world videos. Your game is just a "style" that tweaks some priors on look, settings, and story.

Most games are conditioned on text, it's just that we call it "source code" :).

(Jk of course I know what you mean, but you can seriously see text prompts as compressed forms of programming that leverage the model's prior knowledge)

This got me thinking. Anyone tried using SD or similar to create graphics for the old classic text adventure games?

here are some ideas:

- you could build a non-real-time version of the game engine and use the neural net as a real-time approximation

- you could edit videos shot in real life to have huds or whatever and train the neural net to simulate reality rather than doom. (this paper used 900 million frames which i think is about a year of video if it's 30fps, but maybe algorithmic improvements can cut the training requirements down) and a year of video isn't actually all that much—like, maybe you could recruit 500 people to play paintball while wearing gopro cameras with accelerometers and gyros on their heads and paintball guns, so that you could get a year of video in a weekend?

If you train it on multiple games then you could produce new games that have never existed before, in the same way image generation models can produce new images that have never existed before.

maybe the next step is adding text guidance and generating non-existing games.

I think the same comment could be said about generative images, no?

Maybe, in future, techniques of Scientific Machine Learning which can encode physics and other known laws into a model would form a base model. And then other models on top could just fine tune aspects to customise a game.

If only there was a rich 3-dimensional physical environment we could draw training data from.

Well, yeah. Image diffusion models only work because you can provide large amounts of training data. For Doom it is even simpler, since you don't need to deal with compositing.

> even rules which are not visible on-screen.

If a rule was changed but it's never visible on the screen, did it really change?

> It simply generated frames and the appearance of play mechanics from a game it sampled (which humans created).

Simply?! I understand it's mechanically trivial but the fact that it's compressed such a rich conditional distribution seems far from simple to me.

They only trained it on one game and only embedded the control inputs. You could train it on many games and embed a lot more information about each of them which could possibly allow you to specify a prompt that would describe the game and then play it.

One thing I'd like to see is to take a game rendered with low poly assets (or segmented in some way) and use a diffusion model to add realistic or stylized art details. This would fix the consistency problem while still providing tangible benefits.

The title should be "Diffusion Models can be used to render frames given user input"

So all it did is generate a video of the gameplay which is slightly different from the video it used for training?

I think you've just encoded the title of the paper

This, watching the generated clips feels uncomfortable, like a nightmare. Geometry is "swimming" with camera movement, objects randomly appear and disappear, damage is inconsistent.

The entire thing would probably crash and burn if you did something just slightly unusual compared to the training data, too. People talking about 'generated' games often seem to fantasize about an AI that will make up new outcomes for players that go off the beaten path, but a large part of the fun of real games is figuring out what you can do within the predetermined constraints set by the game's code. (Pen-and-paper RPGs are highly open-ended, but even a Game Master needs to sometimes protects the players from themselves; whereas the current generation of AI is famously incapable of saying no.)

I also noticed that they played AI DOOM very slowly: in an actual game you are running around like a madman, but in the video clips the player is moving in a very careful, halting manner. In particular the player only moves in straight lines or turns while stationary, they almost never turn while running. Also didn't see much strafing.

I suspect there is a reason for this: running while turning doesn't work properly and makes it very obvious that the system doesn't have a consistent internal 3D view of the world. I'm already getting motion sickness from the inconsistencies in straight-line movement, I can't imagine turning is any better.

It made me laugh. Maybe they pulled random people from the hallway who had never seen the original Doom (or any FPS), or maybe only selected people who wore glasses and forgot them at their desk.

It's telling IMO that they only want people opinions based on our notoriously faulty memories rather than sitting comparable situations next to one another in the game and simulation then analyzing them. Several things jump out watching the example video.

Because video is much more difficult than images (it's lots of images that have to be consistent across time, with motion following laws of physics etc), and this is much more limited in terms of scope than pure arbitrary video generation.

I would have thought it is much easier to generate huge amounts of game footage for training, but as I understand this is not what was done here.

There has definitely been research for simulating physics based on observation, especially in fluid dynamics but also for rigid body motion and collision. It's important for robotics applications actually. You can bet people will be applying this technique in those contexts.

I think for real world application one challenge is going to be the "action" signal which is a necessary component of the conditioning signal that makes the simulation reactive. In video games you can just record the buttons, but for real world scenarios you need difficult and intrusive sensor setups for recording force signals.

(Again for robotics though maybe it's enough to record the motor commands, just that you can't easily record the "motor commands" for humans, for example)

A popular theory in neuroscience is that this is what the brain does:

https://slatestarcodex.com/2017/09/05/book-review-surfing-un...

It's called predictive coding. By trying to predict sensory stimuli, the brain creates a simplified model of the world, including common sense physics. Yann LeCun says that this is a major key to AGI. Another one is effective planning.

But while current predictive models (autoregressive LLMs) work well on text, they don't work well on video data, because of the large outcome space. In an LLM, text prediction boils down to a probability distribution over a few thousand possible next tokens, while there are several orders of magnitude more possible "next frames" in a video. Diffusion models work better on video data, but they are not inherently predictive like causal LLMs. Apparently this new Doom model made some progress on that front though.

'our' intelligence may not be the best thing we can make. It would be like trying to only make planes that flaps wings or trucks with legs. A bit like using a llm to do multiplication. Not the best tool. Biomimcry is great for inspiration, but shouldn't be a 1-to-1 copy, especialy in different scale and medium.

> I love how the player's health goes down when he stands in the radioactive green water.

This is one of the bits that was weird to me, it doesn't work correctly. In the real game you take damage at a consistent rate, in the video the player doesn't and whether the player takes damage or not seems highly dependent on some factor that isn't whether or not the player is in the radioactive slime. My thought is that its learnt something else that correlates poorly.

It gets a number of previous frames as input I think.

> In Doom the enemies fight with each other if they accidentally incur "friendly fire". It would be interesting to see it play out in this version.

They trained this thing on bot gameplay, so I bet it does poorly when advanced strategies like deliberately inducing mob infighting are employed (the bots probably didn't do that a lot, of at all.)

But can you grab what this Ai has learned and generate the 3d models, maps and code to turn it into an actual game that can run on a user's PC? That would be amazing.

I would absolutely love if they could take this demo, add a new door that isn’t in the original, and see what it generates behind that door

I think some state is also being given (or if its not, it could be given) to the network, like 3d world position/orientation of the player, that could help the neural network anchor the player in the world.

> Is it possible to break the camera free and roam around the map freely and view it from different angles?

I would assume only if the training data contained this type of imagery, which it did not. The training data (from what I understand) consisted only of input+video of actual gameplay, so that is what the model is trained to mimick.

This is like a dog that has been trained to form English words – what's impressive is not that it does it well, but that it does it at all.

> Therefore I don't think it has any clue about the 3D world of the game at all.

AI models don't "know" things at all.

At best, they're just very fuzzy predictors. In this case, given the last couple frames of video and a user input, it predicts the next frame.

It has zero knowledge of the game world, game rules, interactions, etc. It's merely a mapping of [pixels, input] -> pixels.

Watch closely in the videos and you'll see that enemies often respawn when offscreen and sometimes when onscreen. Destroyed barrels come back, ammo count and health fluctuates weirdly, etc. It's still impressive, but its not perfect in that regard.

It doesn't even remember the state of the game you look at. Doors spawning right in front of you, particle effects turning into enemies mid flight etc, so just regular gen AI issues.

Edit: Can see this in the first 10 seconds of the first video under "Full Gameplay Videos", stairs turning to corridor turning to closed door for no reason without looking away.

It doesn't. You need to put the world state in the input (the "prompt", even it doesn't look like prompt in this case). Whatever not in the prompt is lost.

It's conditioned on previous frames AND player actions so it's interactive.

Although ideally a follow up work would be something where there won’t be any potential legal trouble with releasing the complete model so people can play it.

A similar approach but with a game where the exact input is obvious and unambiguous from the graphics alone so that you can use unannotated data might work. You’d just have to create a model to create the action annotations. I’m not sure what the point would be, but it sounds like it’d be interesting.

Don't give them ideas lol terrifying stuff if that happens!

> We could have mods for old games that generate voices for the characters for example

You mean in real time? Or just in general?

There are a lot of mods that use AI-generated voices. I'll say it's the norm of modding community now.

>Robotic Transformer 2 (RT-2) is a novel vision-language-action (VLA) model that learns from both web and robotics data, and translates this knowledge into generalised instructions for robotic control

https://deepmind.google/discover/blog/rt-2-new-model-transla...

From the article: We present GameNGen, the first game engine powered entirely by a neural model that enables real-time interaction with a complex environment over long trajectories at high quality.

The demo is actual gameplay at ~20 FPS.

Isn't that what Nvidia’s Ray Reconstruction and DLSS (frame generation and upscaler) are doing, more or less?

I am struggling to understand a single implication of this! How does this generalize to anything other than other than playing retro games in the most expensive way possible? The very intention of this project is overfitting to data in a non-generalizable way! Maybe it's just pure engineering, that good ANNs are getting cheap and fast. But this project still seems to have the fundamental weaknesses of all AI projects:

- needs a huge amount of data, which a priori precludes a lot of interesting use cases

- flashy-but-misleading demos which hide the actual weaknesses of the AI software (note that the player is moving very haltingly compared to a real game of DOOM, where you almost never stop moving)

- AI nailing something really complicated for humans (98% effective raycasting, 98% effective Python codegen) while failing to grasp abstract concepts rigorously understood by fish (object permanence, quantity)

I am genuinely struggling to see this as a meaningful step forward. It seems more like a World's Fair exhibit - a fun and impressive diversion, but probably not a vision of the future. Putting it another way: unlike AlphaGo, Deep Blue wasn't really a technological milestone so much as a sociological milestone reflecting the apex of a certain approach to AI. I think this DOOM project is in a similar vein.

Thousands of different people have been speculating about this kind of thing for years.

Who is that?

>Am I the only one who thinks this is faked?

Yes.

I see enemies and decreasing health on hit. But even if it lacked those, it seems like a pretty irrelevant nitpick that is completely underplaying what we're seeing here. The fact that this is even possible at all feels like science fiction.

I think it's possible AI models will generate dynamic UI for each client and stream the UI to clients (maybe eventually client devices will generate their UI on the fly) similar to Google Stadia. Maybe some offset of video that allows the remote to control it. Maybe Wasm based - just stream wasm bytecode around? The guy behind VLC is building a library for ulta low latency: https://www.kyber.video/techology.

I was playing around with the idea in this: https://github.com/StreamUI/StreamUI. Thinking is take the ideas of Elixir LiveView to the extreme.

So... https://websim.ai except over pixels instead of in your browser?

that might work for some applications, especially recreational things, I think we're a while away from it doing away with all things, especially where deterministic behavior, efficiency, or reliability are important.