LESSWRONG"Why Not Just..."
LW

"Why Not Just..."

Aug 08, 2022 by johnswentworth

A compendium of rants about alignment proposals, of varying charitability.

138Deep Learning Systems Are Not Less Interpretable Than Logic/Probability/Etc

1y

52

149Godzilla Strategies

1y

67

75Rant on Problem Factorization for Alignment

1y

48

126Interpretability/Tool-ness/Alignment/Corrigibility are not Composable

1y

13

161How To Go From Interpretability To Alignment: Just Retarget The Search

1y

32

91Oversight Misses 100% of Thoughts The AI Does Not Think

1y

50

73Human Mimicry Mainly Works When We’re Already Close

1y

16

177Worlds Where Iterative Design Fails

1y

27

151Why Not Just... Build Weak AI Tools For AI Alignment Research?

7mo

17

124Why Not Just Outsource Alignment Research To An AI?

7mo

45

137OpenAI Launches Superalignment Taskforce

3mo

38