LESSWRONG
LW

Chaskerr4
0010
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
Interpretability Will Not Reliably Find Deceptive AI
Chaskerr43mo10

I appreciate a good waffle phrase as much as the next tech, and I don't know if this was you or Gemini, but this essay is a damn masterclass!

Reply
No posts to display.