AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topics The introduction of ChatGPT and the subsequent improvement of Large Language Models (LLMs) have prompted more and more individuals to turn to the use of ChatBots, both for information and assistance w...

slightly different conclusion: arxiv.org/abs/2308.14608

You call it an ifelse statement, I call it a lightweight, agentic decision module operating within a deterministic inference framework

Should be flat earthers all around the flat earth, no?

one of the best pieces of writing on atproto architecture.

if you enjoyed the blog posts that @dustyweb.bsky.social and I exchanged, you should read this!