This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
is fundraising!
LW
$
Login
Fazl
Posts
Sorted by New
78
Best-of-N Jailbreaking
Ω
10d
Ω
6
4
Visualizing neural network planning
Ω
8mo
Ω
0
48
Mechanistic Interpretability Workshop Happening at ICML 2024!
Ω
8mo
Ω
6
17
Early Experiments in Reward Model Interpretation Using Sparse Autoencoders
1y
0
8
Automated Sandwiching & Quantifying Human-LLM Cooperation: ScaleOversight hackathon results
2y
0
Wiki Contributions
Comments
Sorted by
Newest