whpearson

whpearson

Send Message

Users Feeds

This user has no feeds associated with them

Posts

[brainstorm] - What should the AGIrisk community look like?

I've been thinking for a bit what I would like the AGI risk community to look like. I'm curious what all your thoughts are. I'll be postin

On-line google hangout on approaches to communication around agi risk (2017/5/27 20:00 UTC)

We have a number of charities that are working on different aspects of AGI risk - The theory of the alignment problem (MIRI/FHI/more) -

Making decisions in a real computer - an argument for meta-decision theory research

Decision theory is being used as the basis for AI safety work. This currently involves maximising expected utility of specific actions. Maxi

On-line google hangout on approaches to the control problem (2017/6/13 7PM UTC)

I'd like to get more discussion on-line about approaches to the control problem, so I'm hosting a hangout. I'll run it lean coffee style m

Decomposing the normal computer control problem

To solve the computer control problem we need to decompose it into parts. This article presents one decomposition. The primary decompositi

Defining the normal computer control problem

There has been focus on controlling super intelligent artificial intelligence, however we currently can't even control our un-agenty compute

Expected utility of control vs expected utility of actions

Request for collaborators - Survey on AI risk priorities

After some conversations here I thought I would try and find out what the community of people who care about AI risk think are the prioritie

Why I'm working on satisficing intelligence augmentation (and not blogging about it much)

- Paradigm shifting seems necessary for general intelligence. - It seems likely that to be able to perform paradigm shifts you need to chang

Facets of Problems v0.1

Problems can be decomposed into parts that are shared among different problems, these parts I'll call facets (for want of a better word, if