LESSWRONG

I've been recently struggling to translate my various AI safety ideas (low impact, truth for AI, Oracles, counterfactuals for value learning

Crossposted at the Intelligent agent foundation. There have been various attempts to classify the problems in AI safety research. Our old

It should come as no surprise to people on this list that models often outperform experts. But these are generally finely calibrated models,

That is not dead which can eternal lie: the aestivation hypothesis for resolving Fermi's paradox Anders Sandberg, Stuart Armstrong, Milan

We have a new paper out, presenting the 'aestivation hypothesis'. It's another attempt to reconcile the fact that cosmic expansion seems ver

Racing to the Precipice: a Model of Artificial Intelligence Development by Stuart Armstrong, Nick Bostrom, and Carl Shulman This paper p

Epistemic status: an idea I believe moderately strongly, based on extensive reading but not rigorous analysis. We may have a dramatically

Crossposted at the Intelligent Agents Forum. EDIT: This method is not intended to solve extortion, just to remove the likelihood of extrem

Based on a idea from Nick Bostrom. Suit A: "Welcome to our futurology meeting extravaganza, where we are going to do a complete analysis o

Some time ago, I discovered a post comparing basic income and basic job ideas. This sought to analyse the costs of paying everyone a guarant