AI ALIGNMENT FORUM
AF

440
knowsnothing
020
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No posts to display.
No wikitag contributions to display.
0knowsnothing's Shortform
10mo
0
Alignment Implications of LLM Successes: a Debate in One Act
knowsnothing2y02

Why not just run that experiment?

Reply
Instrumental deception and manipulation in LLMs - a case study
knowsnothing2y00

Thank you for doing this. Would you mind if this is added to the Misalignment Database?

Reply