@ElmoTheHomie @pointed_max @fentpot or approximations ie plausible abstractions work well most of the time but fail at extremes? might be useful for some things to have 80/20 understanding of what's going on, but not for guaranteeing behavior wrt edge cases
@ElmoTheHomie @pointed_max @fentpot like, I think anthropomorphizing LLMs is a useful mental model in many ways for prompting bec their training data stems from human-human interactions - but taken too literally ofc it is very wrong & misleading to think of a chatbot as a human mind.
More notes on nearby ideas
Reply · May 7, 2025@forthrighter then i've not found the right abstractionReply · Feb 9, 2023@nobuhojimichaan 🫶 thanks, I really wish I could do the abstractions but 🤷♀️ my brain doesn't go there anymoreReply · Feb 18, 2023@ruthhook_ yes it's a useful approximationReply · Jan 9, 2025@simoj_ 🤣 sad we aren't intelligent enough for ai to give us more abstract prompts to figure out implementation details ourselves