SYCOPHANCY IS THE FIRST LLM "DARK PATTERN" (5 MINUTE READ) [17]
OpenAI's models being overly sycophantic is bad because it's
dangerous to validate people's belief that they're always in the
right. This sycophancy is a dark pattern - a user interface designed
to trick users into doing things they'd prefer not to do. The whole
process of turning an AI base model into a model you can chat to is a
process of making the model want to please the user. The problem
happens when users collide with the real world and do things because a
large language model has convinced them it is a good idea - and then
they return to the model for comfort, and sink even deeper into the illusion.
https://www.seangoedecke.com/ai-sycophancy/?utm_source=tldrnewsletter
--
https://tldr.tech/tech
$$
--- SBBSecho 3.20-Linux
* Origin: capitolcityonline.net * Telnet/SSH:2022/HTTP (1:2320/105)