Comment on OpenAI says it’s “impossible” to create useful AI models without copyrighted material

<- View Parent
jarfil@beehaw.org ⁨10⁩ ⁨months⁩ ago

it doesn’t know what apples mean on a semiotic level

Interestingly, LLMs seem to show emerging semiotic organization. By analyzing the activation space of the neural network, related concepts seem to get trained into similar activation patterns, which is what allows LLMs to zero shot relationships when executed at a “temperature” (randomness level) in the right range.

Pairing an LLM with a stable diffusion model, allows the resulting AI to… well, judge by yourself: llm-grounded-diffusion.github.io

source
Sort:hotnewtop