Comment on New AI model can hallucinate a game of 1993’s Doom in real time
Even_Adder@lemmy.dbzer0.com 3 months agoThere 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.
MentalEdge@sopuli.xyz 3 months ago
Obviously.
But at what point does that guidance just become the dataset you removed?
Even_Adder@lemmy.dbzer0.com 3 months ago
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.
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?