Comment on New AI model can hallucinate a game of 1993’s Doom in real time
Even_Adder@lemmy.dbzer0.com 3 months agoBut at what point does that guidance just become the dataset you removed from the training data?
The whole point is that it didn’t know the concepts beforehand, and no it doesn’t become the dataset. Observations made of the training data are added to the model’s weights after training, the dataset is never relevant again as the model’s weights are locked in.
To get it to run Doom, they used Doom.
To realize a new genre, you’ll “just” have to make that game the old fashion way, first.
Or you could train a more general model. These things happen in steps, research is a process.
MentalEdge@sopuli.xyz 3 months ago
You are completely missing what I’m saying.
Even_Adder@lemmy.dbzer0.com 3 months ago
What kind of creativity are you talking about then? I’ve also never heard of a bloated model. Which models are bloated?
MentalEdge@sopuli.xyz 3 months ago
Bloated, as in large and heavy. More expensive, more power hungry, less efficient.
I already brought it up. They can’t deal with something completely new.
When you discuss what you want with a human artist or programmer or whatever, there is a back and forth process where both parties explain and ask until comprehension is achieved, and this improves the result.
It doesn’t matter if the programmer has played games with regenerating health before, one can comprehend and implement the concept based on just a couple sentences.
Now how would you do the same with a “general” model that didn’t have any games that works like that in the training data?
My point is that “general” models aren’t a thing. Not really. We can make models that are really, really big, but they remain very bad at filling in gaps in reality that weren’t in the training data. They don’t start magically putting two and two together and comprehending all the rest.
Even_Adder@lemmy.dbzer0.com 3 months ago
Do you have any examples of how they fail? There are plenty of ways to explain new concepts to models.
arxiv.org/abs/2404.19427 arxiv.org/abs/2406.11643 arxiv.org/abs/2403.12962 arxiv.org/abs/2404.06425 arxiv.org/abs/2403.18922 arxiv.org/abs/2406.01300