x

LESSWRONG

LW

Marko Katavic — LessWrong

Marko Katavic

Marko Katavic

Message

I live in London, work in applied AI (Faculty) on downstream safety. Have previously worked in applied AI and decision intelligence, leading development of neurosymbolic AI for personal finance, some ML work in Meta (my initial foray into trying to do good against overwhelming odds)...

69

3

32

8mo

Marko Katavic

I live in London, work in applied AI (Faculty) on downstream safety. Have previously worked in applied AI and decision intelligence, leading development of neurosymbolic AI for personal finance, some ML work in Meta (my initial foray into trying to do good against overwhelming odds)...

RAND's extinction report estimates one side of an inequality

Epistemic Status: I am positive that the RAND report[1], as it is written, contains a missing parameter in their inference chain. I am 80% certain that if the parameter was to be estimated, we would find coordination lag to be empirically proven to be greater than expected time to risk...

Why Alignment Risk Might Peak Before ASI - a Substrate Controller Framework

TL;DR (Abstract feels presumptuous) This is the core logical chain I argue in the essay: 1. Planning depth is endogenous to environmental variance reduction 2. As environmental complexity grows, variance reduction is cheaper through control than through prediction. 3. Early humans optimised for shallow planning depth despite available cognitive density...

mkatavic's Shortform