•

Created by Vladimir_Nesov at

Vladimir_Nesov v1.9.0 (+48) /* Blog posts */ added Slepnev's post on protection from spurious counterfactuals 2

- AI cooperation in practice by cousin_it
- What a reduction of "could" could look like by cousin_it
- Controlling Constant Programs by Vladimir Nesov
- Notion of Preference in Ambient Control by Vladimir Nesov
- A model of UDT with a halting oracle by cousin_it
- Predictability of Decisions and the Diagonal Method by Vladimir Nesov
- A model of UDT without proof limits by cousin_it
- An example of self-fulfilling spurious proofs in UDT by cousin_it

- AI cooperation in practice by cousin_it
- What a reduction of "could" could look like by cousin_it
- Controlling Constant Programs by Vladimir Nesov
- Notion of Preference in Ambient Control by Vladimir Nesov
- A model of UDT with a halting oracle by cousin_it
- Predictability of Decisions and the Diagonal Method by Vladimir Nesov
~~A model~~An example of self-fulfilling spurious proofs in UDT~~with a malicious proof searcher~~by cousin_it

- AI cooperation in practice by cousin_it
- What a reduction of "could" could look like by cousin_it
- Controlling Constant Programs by Vladimir Nesov
- Notion of Preference in Ambient Control by Vladimir Nesov
- A model of UDT with a halting oracle by cousin_it
- Predictability of Decisions and the Diagonal Method by Vladimir Nesov
- A model of UDT with a malicious proof searcher by cousin_it

- AI cooperation in practice by cousin_it
- What a reduction of "could" could look like by cousin_it
- Controlling Constant Programs by Vladimir Nesov
- Notion of Preference in Ambient Control by Vladimir Nesov
- A model of UDT with a halting oracle by cousin_it
- Predictability of Decisions and the Diagonal Method by Vladimir Nesov

A variant of ~~pdateless~~updateless decision theory that uses first order logic instead of mathematical intuition module (MIM), emphasizing the way an agent can control which mathematical structure a fixed definition defines, an aspect of UDT separate from its own emphasis on not making the mistake of updating away things one can still acausally control.

A variant of ~~Updateless~~pdateless decision theory that uses first order logic instead of mathematical intuition module (MIM), emphasizing the way an agent can control which mathematical structure a fixed definition defines, an aspect of UDT separate from its own emphasis on not making the mistake of updating away things one can still acausally control.

A ~~further development~~variant of Updateless decision theory that uses first order logic instead of mathematical intuition module (MIM), emphasizing the way an agent can control which mathematical structure a fixed definition defines,~~ which is~~ an aspect of UDT separate from its own emphasis on not making the mistake of updating away things one can still acausally control.

A further development of Updateless decision theory~~.~~ emphasizing the way an agent can control which mathematical structure a fixed definition defines, which is an aspect of UDT separate from its own emphasis on not making the mistake of updating away things one can still acausally control.

A further development of Updateless decision theory.

- AI cooperation in practice by cousin_it
- What a reduction of "could" could look like by cousin_it
- Controlling Constant Programs by Vladimir Nesov
- Notion of Preference in Ambient Control by Vladimir Nesov