AI ALIGNMENT FORUM
AF

Paul Bricman

Sequences

Hypothesis Subspace

Posts

Sorted by New

6Elements of Computational Philosophy, Vol. I: Truth

5mo

1

11Cataloguing Priors in Theory and Practice

1y

0

15(Structural) Stability of Coupled Optimizers

1y

0

11Interlude: But Who Optimizes The Optimizer?

1y

0

17Representational Tethers: Tying AI Latents To Human Ones

1y

0

7Ideological Inference Engines: Making Deontology Differentiable*

1y

0

14Oversight Leagues: The Training Game as a Feature

1y

0

17Benchmarking Proposals on Risk Scenarios

1y

0

10Steelmining via Analogy

1y

0

Wiki Contributions

Comments

Linda Linsefors's Shortform

Paul Bricman1y1

You mean, in that you can simply prompt for a reasonable non-infinite performance and get said outcome?