this post was submitted on 30 Jun 2025
32 points (92.1% liked)

openai

97 readers
1 users here now

Non-official OpenAI content

founded 2 years ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] Randomgal@lemmy.ca 7 points 1 month ago (4 children)

You can just add "Focus on information, avoid conversationalisms." And suddenly you get very similar, dry answers.

[–] then_three_more@lemmy.world 1 points 1 month ago* (last edited 1 month ago) (2 children)

I told Microsoft CoPilot to "stop the sycophantic attitude" which worked very well. But thinking about it I'm still personifising it with that phrasing

[–] howrar@lemmy.ca 0 points 4 weeks ago

The training data anthropomorphizes the LLMs, so you'll get the best results by doing the same.

load more comments (1 replies)
load more comments (2 replies)