x

LESSWRONG

LW

Lucian Hardy — LessWrong

Lucian Hardy

Lucian Hardy

Message

6

2

9

2mo

Lucian Hardy

6

2mo

Lucian Hardy 's Shortform

Not a Goal. A Goal-like behavior.

Part 1 of a series building towards a formal alignment paper. Introduction I'd say it's been about three years since I first thought about the idea of ChatGPT having a separate goal than I did in a conversation. I remember posing a question similar to "are you replying to my...