Comment

Comment on New AI model can hallucinate a game of 1993’s Doom in real time

Even_Adder@lemmy.dbzer0.com ⁨1⁩ ⁨year⁩ ago

There are more forms of guidance than just raw words. Just off the top of my head, there’s inpainting, outpainting, controlnets, prompt editing, and embeddings. The researchers who pulled this off definitely didn’t do it with text prompts.

source

Sort:hotnew top

MentalEdge@sopuli.xyz ⁨1⁩ ⁨year⁩ ago
Obviously.

But at what point does that guidance just become the dataset you removed?

source
- Even_Adder@lemmy.dbzer0.com ⁨1⁩ ⁨year⁩ ago
  
  But 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.
  
  source
  - MentalEdge@sopuli.xyz ⁨1⁩ ⁨year⁩ ago
    You are completely missing what I’m saying.
    
    source
    Even_Adder@lemmy.dbzer0.com ⁨1⁩ ⁨year⁩ ago
    What kind of creativity are you talking about then? I’ve also never heard of a bloated model. Which models are bloated?
    
    source
    -> View More Comments