Ask HN: What have you built with LLMs?
47 points by shoebham | 30 comments
First screen, captured .
Looks similar
Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?
474 points by superasn | 304 comments
Ask HN thread asking how OpenAI serves ChatGPT to 700M weekly users when a GPT-4-class model is hard to run locally, seeking inference scaling insights.
Ask HN: Any insider takes on Yann LeCun's push against current architectures?
327 points by vessenes | 271 comments
Ask HN thread seeking expert opinions on Yann LeCun's argument that LLMs can't fix hallucinations and his proposed energy-minimization architectures.
