←back to thread

721 points ralusek | 2 comments | | HN request time: 0s | source
Show context
cloudking ◴[] No.41870249[source]
This is the true power of generative AI, enabling new functionality for the user with simple UX while doing all the heavy lifting in the background. Prompting as a UX should be abstracted away from the user.
replies(1): >>41870324 #
jprete ◴[] No.41870324[source]
This probably isn't backed by an LLM but instead some kind of geometric shape model.
replies(1): >>41870890 #
m3kw9 ◴[] No.41870890[source]
How do you explain a horse 2 legs become 4 legs when rotated assuming they only drew 2 legs on the side view
replies(2): >>41871165 #>>41876393 #
1. atq2119 ◴[] No.41871165{3}[source]
The second L in LLM stands for "language". Nothing of what you're describing has to do with language modeling.

They could be using transformers, sure. But plenty of transformers-based models are not LLMs.

replies(1): >>41871435 #
2. kubrickslair ◴[] No.41871435[source]
They are probably looking for LGMs - Large Generative Models which encapsulate vision & multi-modal models.