User Profile

star151
description77
message742

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
All Posts
personIncludes personal and meta blogposts (as well as curated and frontpage).
rss_feed Create an RSS Feed

[Link] Using rationality to debug Machine Learning

1mo
1 min read
Show Highlightsubdirectory_arrow_left
3

NIPS 2015

2y
1 min read
Show Highlightsubdirectory_arrow_left
4

Velocity of behavioral evolution

3y
1 min read
Show Highlightsubdirectory_arrow_left
10

What Peter Thiel thinks about AI risk

3y
1 min read
Show Highlightsubdirectory_arrow_left
6

Cognitive distortions of founders

3y
1 min read
Show Highlightsubdirectory_arrow_left
1

FAI PR tracking well [link]

4y
1 min read
Show Highlightsubdirectory_arrow_left
7

Hawking/Russell/Tegmark/Wilczek on dangers of Superintelligent Machines [link]

4y
1 min read
Show Highlightsubdirectory_arrow_left
28

Gunshot victims to be suspended between life and death [link]

4y
1 min read
Show Highlightsubdirectory_arrow_left
17

Huffington Post article on DeepMind-requested AI ethics board, links back to LW [link]

4y
1 min read
Show Highlightsubdirectory_arrow_left
12

H+ review of James Miller's Singularity Rising [link]

4y
1 min read
Show Highlightsubdirectory_arrow_left
1

Recent Comments

I wonder if it's possible to help with this in a tax-advantaged way. Maybe set up donation to MIRI earmarked for this kind of thing.

Recommending http://algorithmstoliveby.com/ for the same reasons

I think a highly relevant detail here is that the biggest bottleneck in development of nuclear weapons is refinement of fissionable material which is a tremendously intense industrial process (and still remains the major deterrent for obtainment of nukes). Without it the development would have been ...(read more)

would you mind spelling out the integral part?

Even Friendly AI may deconstruct humans for their atoms in the AI’s early stages, and as such sacrificy will translate in the higher total number of sentient beings in the universe at the end.

“You keep using that word, I do not think it means what you think it means.”

Feynman also explicitly spoke about hammer-mode “[so] I had got a great reputation for doing integrals, only because my box of tools was different from everybody else’s, and they had tried all their tools on it before giving the problem to me”, also some exerpts here https://www.farnamstreetblog.com...(read more)

The "Space Mom" part seems like what exploration/exploitation meta-algorithm feels like from the inside. To do quality exploration you need to shut down the inner voice of exploitation.

Also relevant: https://www.physics.ohio-state.edu/~kilcup/262/feynman.html

Zvi/Vladimir, what's your role in this - are you the judges?

Hi Sarah, not sure why you felt compelled to answer. Nothing in your reply suggests a contrary logical argument to the Fire Alarm; the only thing I can think of is Eliezer vaguely implying a shorter timeline and you vaguely implying a longer (or at least more diffuse) one. I didn't get the feeling E...(read more)

For context this is a response to this year's Edge essays https://www.edge.org/responses/what-scientific-term-or%C2%A0concept-ought-to-be-more-widely-known . Not sure if posted by Michael (which is Good News!) or on his behalf