| Post Reply | RetroFed Forum Forum Index » Humor |
| Author | Message | ||
|---|---|---|---|
The Picard Maneuver
lemmy.world
The_Picard_Maneuver@lemmy.worldJoined: 2023-06-22 |
|
||
| 290 Original | |||
|
Ech
lemmy.ca
ech@lemmy.ca Joined: 2025-06-25 |
The llm doesn't need to be "trained" on each individual user to be a sycophantic yes-man (I doubt it even stores the whole chatlog in its context). Llms are agreeable by design, their core function to produce fitting and desirable text to a prompt. And the best way to produce a desirable response is to mirror the tone and subject, usually echoing whatever's been said. In an "AITA?" prompt, people asking almost always slant it in their favor and the output of the llm is going to match that. |
||
| 9 | |||
| Post Reply |
Back to top |