Lying Alignment Chart — LessWrong
lesswrong.com · 1,790 words · saved by 1 readers
A community blog devoted to refining the art of rationality
x Lying Alignment Chart — LessWrong Deception Humor Philosophy of Language Personal Blog 78 Lying Alignment Chart by Zack_M_Davis 29th Nov 2023 1 min read 17 78 Lying Alignment Chart 18 Unnamed 4 Unnamed 14 Unnamed 7 wachichornia 7 Rana Dexsin 6 [anonymous] 4 Said Achmiz 4 gwern 2 Said Achmiz 4 Ben Pace, the Vacationing Vagabond 6 Zack_M_Davis 2 tailcalled 2 Shankar Sivarajan 3 RamblinDash 1 [anonymous] 0 Gordon Seidoh Worley 3 Screwtape 17 Comments 17 Deception Humor Philosophy of Language Personal Blog 78 New Comment Submit 17 comments , sorted by top scoring Click to highlight new comments
saved by
related reading
- LessWronglesswrong.com
- Deep Deceptiveness — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Lies, Damn Lies, and Fabricated Options — LessWronglesswrong.com
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- The Best of LessWrong — LessWronglesswrong.com
- Alignment will happen by default. What’s next? — LessWronglesswrong.com
- Self-Other Overlap: A Neglected Approach to AI Alignment — LessWronglesswrong.com
- Bad Problems Don't Stop Being Bad Because Somebody's Wrong About Fault Analysis — LessWronglesswrong.com
- “Alignment Faking” frame is somewhat fake — LessWronglesswrong.com
- Models don’t seem to be dishonest in the way humans are — LessWronglesswrong.com
- Fucking Goddamn Basics of Rationalist Discourse — LessWronglesswrong.com