User Profile

star6
description31
message1397

Recent Posts

Curated Posts
starCurated - Recent, high quality posts selected by the LessWrong moderation team.
rss_feed Create an RSS Feed
Frontpage Posts
Posts meeting our frontpage guidelines: • interesting, insightful, useful • aim to explain, not to persuade • avoid meta discussion • relevant to people whether or not they are involved with the LessWrong community.
(includes curated content and frontpage posts)
rss_feed Create an RSS Feed
Personal Blogposts
personPersonal blogposts by LessWrong users (as well as curated and frontpage).
rss_feed Create an RSS Feed

Anthropics and a cosmic immune system

5y
Show Highlightsubdirectory_arrow_left
32

Living in the shadow of superintelligence

5y
Show Highlightsubdirectory_arrow_left
17

The ongoing transformation of quantum field theory

5y
Show Highlightsubdirectory_arrow_left
19

Call for a Friendly AI channel on freenode

5y
Show Highlightsubdirectory_arrow_left
4

FAI, FIA, and singularity politics

5y
Show Highlightsubdirectory_arrow_left
11

Ambitious utilitarians must concern themselves with death

5y
Show Highlightsubdirectory_arrow_left
13

Thinking soberly about the context and consequences of Friendly AI

6y
Show Highlightsubdirectory_arrow_left
39

Debugging the Quantum Physics Sequence

6y
Show Highlightsubdirectory_arrow_left
130

Friendly AI and the limits of computational epistemology

6y
Show Highlightsubdirectory_arrow_left
148

Two books by Celia Green

6y
Show Highlightsubdirectory_arrow_left
21

Recent Comments

I'm thinking large numbers of synchronized reusable beacons - either recurrent novas or black holes - where a flash is produced by feeding the beacon with gas in a controlled way. For rapid reuse, you want local byproducts of the flash to get out of the way quickly, so the next batch of gas can be i...(read more)

I only have an account on LW 1.0, not LW 2.0. Will my current account still exist after the migration?

Four hours of self-play and it's the strongest in the world. Soon the machines will be parenting us.

> Knowledge of the terrain might be hard to get reliably

Knowing that the world is made of atoms should take an AI a long way.

> If these people that develop [AGI] are friendly they might decide to distribute it to other people to make it harder for any one project to take off.

I hold to the cl...(read more)

Wake up! In three days, that AI evolved from knowing nothing, to comprehensively beating an earlier AI which had been trained on a distillation of the best human experience. Do you think there's a force in the world that can stand against that kind of strategic intelligence?

A voice tells me that we're out of time. The future of the world will now be decided at Deep Mind, or by some other group at their level.

EurekAlert [mentions](https://www.eurekalert.org/pub_releases/2017-09/uoo-gth092617.php) the simulation argument, and the page implies that this was a press release from Oxford - even providing a media contact - though I have not found the document on Oxford's own website.

I am also skeptical of w...(read more)