AI ALIGNMENT FORUM"Why Not Just..."
AF

"Why Not Just..."

Aug 08, 2022 by johnswentworth

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

51Deep Learning Systems Are Not Less Interpretable Than Logic/Probability/Etc

2y

14

44Godzilla Strategies

2y

19

40Rant on Problem Factorization for Alignment

2y

32

54Interpretability/Tool-ness/Alignment/Corrigibility are not Composable

2y

4

75How To Go From Interpretability To Alignment: Just Retarget The Search

2y

24

37Oversight Misses 100% of Thoughts The AI Does Not Think

2y

23

37Human Mimicry Mainly Works When We’re Already Close

2y

4

66Worlds Where Iterative Design Fails

2y

17

62Why Not Just... Build Weak AI Tools For AI Alignment Research?

2y

2

35Why Not Just Outsource Alignment Research To An AI?

2y

6

48OpenAI Launches Superalignment Taskforce

1y

0