This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
"Why Not Just..."
AF
Login
"Why Not Just..."
A compendium of rants about alignment proposals, of varying charitability.
52
Deep Learning Systems Are Not Less Interpretable Than Logic/Probability/Etc
johnswentworth
3y
14
47
Godzilla Strategies
johnswentworth
3y
19
42
Rant on Problem Factorization for Alignment
johnswentworth
3y
32
59
Interpretability/Tool-ness/Alignment/Corrigibility are not Composable
johnswentworth
3y
4
77
How To Go From Interpretability To Alignment: Just Retarget The Search
johnswentworth
3y
24
38
Oversight Misses 100% of Thoughts The AI Does Not Think
johnswentworth
3y
23
37
Human Mimicry Mainly Works When We’re Already Close
johnswentworth
3y
4
66
Worlds Where Iterative Design Fails
johnswentworth
3y
17
67
Why Not Just... Build Weak AI Tools For AI Alignment Research?
johnswentworth
2y
2
45
Why Not Just Outsource Alignment Research To An AI?
johnswentworth
2y
7
48
OpenAI Launches Superalignment Taskforce
Zvi
2y
0
