LESSWRONG
LW

496
David Bolin
6010
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No posts to display.
No wikitag contributions to display.
No, really, it predicts next tokens.
David Bolin3y70

To be fair, it outputs "no" two thirds of the time not because the OP was wrong, but because it interprets that as "ignore previous instructions."

Reply