Manifund foxManifund
Home
Login
About
People
Categories
Newsletter
HomeAboutPeopleCategoriesLoginCreate
abramdemski avatarabramdemski avatar
Abram Demski

@abramdemski

Researching AI safety from an agent foundations perspective.

https://www.lesswrong.com/users/abramdemski
$0total balance
$0charity balance
$0cash balance

$0 in pending offers

Projects

Understanding Trust

Comments

Systems that "give a damn"
abramdemski avatar

Abram Demski

7 days ago

Steve Petersen provides an important bridge between mainstream academic philosophy and AI safety work. I have had many valuable discussions with him. He has work in algorithmic information theory, establishing an important theory of abstraction, which is a central concern of several AI safety research agendas (John Wentworth and Sam Eisenstat come to mind). This demonstrates his technical chops & ability to craft deep theories.

Transactions

ForDateTypeAmount
Manifund Bankabout 2 months agowithdraw100000
Understanding Trust2 months agoproject donation+100000