x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
fbarez — LessWrong
fbarez
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
9
Automated Interpretability-Driven Model Auditing and Control: A Research Agenda
19d
0
79
Best-of-N Jailbreaking
Ω
1y
Ω
5
4
Visualizing neural network planning
Ω
2y
Ω
0
48
Mechanistic Interpretability Workshop Happening at ICML 2024!
Ω
2y
Ω
6
18
Early Experiments in Reward Model Interpretation Using Sparse Autoencoders
2y
0
8
Automated Sandwiching & Quantifying Human-LLM Cooperation: ScaleOversight hackathon results
3y
0
Comments