This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Lukas Fluri
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
2
Zurich AI Safety is looking for (Co-)Directors - EOI
13h
0
17
The Perils of Optimizing Learned Reward Functions
2mo
1
21
Evaluating Superhuman Models with Consistency Checks
2y
2
12
Open Problems in Negative Side Effect Minimization
Ω
3y
Ω
6
Comments