Cosmicomical comments on ChatGPT would have been so much useful and trustworthy if it is able to accept that it doesn't know an answer.

ChatGPT would have been so much useful and trustworthy if it is able to accept that it doesn't know an answer. (programming.dev)

submitted 2 years ago* (last edited 2 years ago) by Timely_Jellyfish_2077@programming.dev to c/chatgpt@lemmy.world

46 comments fedilink hide all child comments

Small rant : Basically, the title. Instead of answering every question, if it instead said it doesn't know the answer, it would have been trustworthy.

you are viewing a single comment's thread
view the rest of the comments

[–] Cosmicomical@lemmy.world 2 points 2 years ago (1 child)

Do you have a source for the "smiling when you don't really mean it" thing? I've been digging around but couldn't find that anywhere.

permalink

fedilink

source

parent

hideshow 2 child comments

[–] kromem@lemmy.world 1 point 2 years ago

It's right in the research I was mentioning:

https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html

Find the section on the model's representation of self and then the ranked feature activations.

I misremembered the top feature slightly, which was: responding "I'm fine" or gives a positive but insincere response when asked how they are doing.

permalink

fedilink

source

parent

lemmy:	0.19.20
mlmym (mschae):	26.3.4