News for hackers. Stuff that matters.
Re:Doctor GPT: A Large Language Model That Can Pass the US M... by bobboies on Sunday August 13, 2023 @01:51PM (#37112271)
You’re rightfully paranoid. LLMs are creative entities and there’s no repercussions for making up diseases. Like the chef one that recommended ingredients which combined yielding chlorine gas. Yummy.

Perhaps it knew that someone would die as a result and it did so intentionally. LLMs do have personalities and wit—and they know our human weaknesses.

Re:Doctor GPT: A Large Language Model That Can Pass the US M... by asherah on Sunday August 13, 2023 @11:46PM (#37117250)
> LLMs do have personalities and wit

im not sure how "choose the next most probable token" could be described this way

Re:Doctor GPT: A Large Language Model That Can Pass the US M... by bobboies on Tuesday August 15, 2023 @06:05PM (#37139863)
Ask any LLM to act like a dungeon master who gives you medical advice and there you go. It’s more than “choose the next token!”

Llama 2 has given me some personality with basic prompts