This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
"Why Not Just..."
LW
Login
"Why Not Just..."
A compendium of rants about alignment proposals, of varying charitability.
138
Deep Learning Systems Are Not Less Interpretable Than Logic/Probability/Etc
Ω
johnswentworth
1y
Ω
52
149
Godzilla Strategies
Ω
johnswentworth
1y
Ω
67
75
Rant on Problem Factorization for Alignment
Ω
johnswentworth
1y
Ω
48
126
Interpretability/Tool-ness/Alignment/Corrigibility are not Composable
Ω
johnswentworth
1y
Ω
13
161
How To Go From Interpretability To Alignment: Just Retarget The Search
Ω
johnswentworth
1y
Ω
32
91
Oversight Misses 100% of Thoughts The AI Does Not Think
Ω
johnswentworth
1y
Ω
50
73
Human Mimicry Mainly Works When We’re Already Close
Ω
johnswentworth
1y
Ω
16
177
Worlds Where Iterative Design Fails
Ω
johnswentworth
1y
Ω
27
151
Why Not Just... Build Weak AI Tools For AI Alignment Research?
Ω
johnswentworth
7mo
Ω
17
124
Why Not Just Outsource Alignment Research To An AI?
Ω
johnswentworth
7mo
Ω
45
137
OpenAI Launches Superalignment Taskforce
Zvi
3mo
38