News for hackers. Stuff that matters.
Re:A new term, ‘slop’, has emerged to describe dubious A.I.-... by moi2388 on Tuesday June 11, 2024 @11:01AM (#40646982)
I do so as well, but usually the response is the chatbot first generating a paragraph about how it’ll comply with the request, making the prompt moot
Re:A new term, ‘slop’, has emerged to describe dubious A.I.-... by wafflemaker on Tuesday June 11, 2024 @11:51AM (#40647765)
It is probably an internalized "prompt engineering" trick from gpt3.5 times, where you could achieve near gpt-4 performance using stuff like that. Rephrase the question and plan your answer was on top of the list.
Re:A new term, ‘slop’, has emerged to describe dubious A.I.-... by TeMPOraL on Tuesday June 11, 2024 @12:30PM (#40648274)
Keep in mind that tokens are LLM units of thought; the only moment the model does any computation is when generating tokens. Therefore, asking it to be succinct means effectively dumbing it down.