This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Myopia
•
Applied to
Interpretability’s Alignment-Solving Potential: Analysis of 7 Scenarios
by
Evan R. Murphy
at
9d
•
Applied to
AI safety via market making
by
Evan R. Murphy
at
23d
•
Applied to
How complex are myopic imitators?
by
Vivek Hebbar
at
3mo
•
Applied to
Evan Hubinger on Homogeneity in Takeoff Speeds, Learned Optimization and Interpretability
by
Adam Shimi
at
4mo
•
Applied to
Understanding and controlling auto-induced distributional shift
by
Adam Shimi
at
4mo
•
Applied to
Transforming myopic optimization to ordinary optimization - Do we want to seek convergence for myopic optimization problems?
by
tailcalled
at
5mo
•
Applied to
Ordinary People and Extraordinary Evil: A Report on the Beguilings of Evil
by
David Gross
at
8mo
•
Applied to
LCDT, A Myopic Decision Theory
by
Adam Shimi
at
10mo
•
Applied to
Open Problems with Myopia
by
Mark Xu
at
1y
•
Applied to
Graphical World Models, Counterfactuals, and Machine Learning Agents
by
Koen Holtman
at
1y
•
Applied to
Seeking Power is Often Convergently Instrumental in MDPs
by
Alex Turner
at
1y
•
Applied to
2019 Review Rewrite: Seeking Power is Often Robustly Instrumental in MDPs
by
Alex Turner
at
1y
•
Applied to
Fighting Akrasia: Incentivising Action
by
Liam Goddard
at
2y
•
Applied to
Why GPT wants to mesa-optimize & how we might change this
by
John Maxwell
at
2y
•
Applied to
The Dualist Predict-O-Matic ($100 prize)
by
John Maxwell
at
2y
•
Applied to
Self-Fulfilling Prophecies Aren't Always About Self-Awareness
by
John Maxwell
at
2y
•
Applied to
The Parable of Predict-O-Matic
by
Abram Demski
at
2y
•
Applied to
Random Thoughts on Predict-O-Matic
by
Abram Demski
at
2y
•
Applied to
Bayesian Evolving-to-Extinction
by
Abram Demski
at
2y