Search Results for author:
Found 8 papers, 0 papers with code
Temporal Inference with Finite Factored Sets
We propose a new approach to temporal inference, inspired by the Pearlian causal inference paradigm - though quite different from Pearl's approach formally.
Risks from Learned Optimization in Advanced Machine Learning Systems
We analyze the type of learned optimization that occurs when a learned model (such as a neural network) is itself an optimizer - a situation we refer to as mesa-optimization, a neologism we introduce in this paper.
Embedded Agency
Traditional models of rational action treat the agent as though it is cleanly separated from its environment, and can act on that environment from the outside.
Categorizing Variants of Goodhart's Law
There are several distinct failure modes for overoptimization of systems on the basis of metrics.
Logical Induction
For instance, if the language is Peano arithmetic, it assigns probabilities to all arithmetical statements, including claims about the twin prime conjecture, the outputs of long-running computations, and its own probabilities.
Asymptotic Convergence in Online Learning with Unbounded Delays
We study the problem of predicting the results of computations that are too expensive to run, via the observation of the results of smaller computations.
Inductive Coherence
While probability theory is normally applied to external environments, there has been some recent interest in probabilistic modeling of the outputs of computations that are too expensive to run.
Asymptotic Logical Uncertainty and The Benford Test
We give an algorithm A which assigns probabilities to logical sentences.
