Counterfactability — LessWrong
lesswrong.com · 4,903 words · saved by 1 readers
This post will assume an understanding of the finite factored set ontology. It will be more speculative that the main FFS sequence, and I will leave…
x Counterfactability — LessWrong Finite Factored Sets Finite Factored Sets AI World Modeling Frontpage 40 Counterfactability by Scott Garrabrant 7th Nov 2022 AI Alignment Forum 13 min read 5 40 Ω 17 This post will assume an understanding of the finite factored set ontology. It will be more speculative that the main FFS sequence, and I will leave out some proofs. It seems likely that I will later regret some of the definitions laid out here. I will be particularly sloppy in defining evidential and causal counterfactuals, because this post is not advocating for them, only demonstrating that it i
related reading
- Operationalizing FDT — LessWronglesswrong.com
- Fine Counterfactualsas.nyu.edu
- the case for CoT unfaithfulness is overstated — LessWronglesswrong.com
- Embedded Agency (full-text version) — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com
- Possibility and Could-ness — LessWronglesswrong.com
- Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
- Updatelessness doesn't solve most problems — LessWronglesswrong.com
- Finite Factored Sets — LessWronglesswrong.com
- Finite Factored Sets — LessWronglesswrong.com
- On Functional Decision Theory :: Wolfgang Schwarzumsu.de
- Probabilities are not the right concept — LessWronglesswrong.com