←back to thread

Using LLMs at Oxide

(rfd.shared.oxide.computer)
694 points steveklabnik | 1 comments | | HN request time: 0.236s | source
Show context
bryancoxwell ◴[] No.46178509[source]
Find it interesting that the section about LLM’s tells when using it for writing is absolutely littered with emdashes
replies(4): >>46178523 #>>46178524 #>>46178632 #>>46178868 #
minimaxir ◴[] No.46178524[source]
You can stop LLMs from using em-dashes by just telling it to "never use em-dashes". This same type of prompt engineering works to mitigate almost every sign of AI-generated writing, which is one reason why AI writing heuristics/detectors can never be fully reliable.
replies(2): >>46178654 #>>46181995 #
1. dcre ◴[] No.46178654[source]
This does not work on Bryan, however.