←back to thread

223 points benkaiser | 1 comments | | HN request time: 0.218s | source
Show context
danpalmer ◴[] No.42546115[source]
LLMs are bad databases, so for something like a bible which is so easily and precisely referenced, why not just... look it up?

This is playing against their strengths. By all means ask them for a summary, or some analysis, or textual comparison, but please, please stop treating LLMs as databases.

replies(2): >>42546183 #>>42546545 #
madiator ◴[] No.42546183[source]
Not sure why you are so upset about a small and neat study ("please, please stop"). If you ask it to summarize (without feeding the entire bible), it needs to know the bible. Knowledge and reasoning are not entirely disconnected.
replies(2): >>42546430 #>>42546695 #
1. nwatson ◴[] No.42546430[source]
ChatGPT chat interface has impressed me when going beyond the scope presented on TFA, eg, when asking about predestination, biblical passages for and against, theologians' and scholars' takes on the debate, and exploring the details in subsequent follow-ups. The LLMs have been fed the Bible and all manner of discussions of Bible-related matters. Like the grandparent comment suggests, the LLMs are much more impressive at interpreting biblical passages and presenting the varieties of opinions about them, or finding passages related to specific topics and presenting opinions.