This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Goodhart's Law
•
Applied to
Could Things Be Very Different?—How Historical Inertia Might Blind Us To Optimal Solutions
by
James Stephen Brown
2mo
ago
•
Applied to
Principled Satisficing To Avoid Goodhart
by
JenniferRM
3mo
ago
•
Applied to
[Aspiration-based designs] A. Damages from misaligned optimization – two more models
by
Simon Dima
4mo
ago
•
Applied to
Goodhart's Law and Emotions
by
Zero Contradictions
5mo
ago
•
Applied to
The Dumbification of our smart screens
by
Lauren (often wrong)
5mo
ago
•
Applied to
Honest science is spirituality
by
Gunnar Zarncke
5mo
ago
•
Applied to
Catastrophic Goodhart in RL with KL penalty
by
Thomas Kwa
6mo
ago
•
Applied to
Fundamental Uncertainty: Chapter 8 - When does fundamental uncertainty matter?
by
Gordon Seidoh Worley
7mo
ago
•
Applied to
Extinction-level Goodhart's Law as a Property of the Environment
by
Vojtech Kovarik
9mo
ago
•
Applied to
Dynamics Crucial to AI Risk Seem to Make for Complicated Models
by
Vojtech Kovarik
9mo
ago
•
Applied to
Extinction Risks from AI: Invisible to Science?
by
Vojtech Kovarik
9mo
ago
•
Applied to
Approximately Bayesian Reasoning: Knightian Uncertainty, Goodhart, and the Look-Elsewhere Effect
by
Roger Dearnaley
10mo
ago
•
Applied to
Aldix and the Book of Life
by
ville
11mo
ago
•
Applied to
When Can Optimization Be Done Safely?
by
StrivingForLegibility
11mo
ago
•
Applied to
Weak vs Quantitative Extinction-level Goodhart's Law
by
Vojtech Kovarik
1y
ago
•
Applied to
Goodhart's Law Example: Training Verifiers to Solve Math Word Problems
by
Thomas Kwa
1y
ago
•
Applied to
Goodhart's Law in Reinforcement Learning
by
jacek
1y
ago
•
Applied to
Satisficers want to become maximisers
by
JenniferRM
1y
ago
•
Applied to
Optimized for Something other than Winning or: How Cricket Resists Moloch and Goodhart's Law
by
Noosphere89
1y
ago