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.
49
Deep Learning Systems Are Not Less Interpretable Than Logic/Probability/Etc
johnswentworth
2y
13
48
Godzilla Strategies
johnswentworth
1y
19
36
Rant on Problem Factorization for Alignment
johnswentworth
1y
31
53
Interpretability/Tool-ness/Alignment/Corrigibility are not Composable
johnswentworth
1y
4
63
How To Go From Interpretability To Alignment: Just Retarget The Search
johnswentworth
1y
24
34
Oversight Misses 100% of Thoughts The AI Does Not Think
johnswentworth
1y
23
36
Human Mimicry Mainly Works When We’re Already Close
johnswentworth
1y
4
55
Worlds Where Iterative Design Fails
johnswentworth
1y
17
61
Why Not Just... Build Weak AI Tools For AI Alignment Research?
johnswentworth
9mo
2
35
Why Not Just Outsource Alignment Research To An AI?
johnswentworth
9mo
6
44
OpenAI Launches Superalignment Taskforce
Zvi
5mo
0