This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Wesley Finck
weswalla.bsky.social
did:plc:6z5botgrc5vekq7j26xnvawq
These are cool papers on examining LLMs as statistical systems rather than reasoning system. They look at tasks and evaluate the models' sensitivity to probability even if the tasks themselves are deterministic. arxiv.org/abs/2309.13638
[contains quote post or other embedded content]
2024-10-04T17:07:23.619Z