News for hackers. Stuff that matters.
Re:Meaning Machine – Visualize how LLMs break down and simul... by jdspiral on Tuesday April 22, 2025 @10:04PM (#43768037)
Yes, tokenization and embeddings are exactly how LLMs process input—they break text into tokens and map them to vectors. POS tags and SVOs aren't part of the model pipeline but help visualize structures the models learn implicitly.
Re:Meaning Machine – Visualize how LLMs break down and simul... by kazinator on Wednesday April 23, 2025 @02:50AM (#43769334)
It doesn't help whatsoever. It's false bullshit.