lyavin · HackerTrans

Submissions

Analysis of what's gone wrong with developed economies over the past few decades

srconstantin.wordpress.com

1 pointsby lyavinvor 8 Jahren0 comments

A genetically modified organism could end malaria and save millions of lives

vox.com

1 pointsby lyavinvor 8 Jahren0 comments

Transcript of Sam Harris and Eliezer Yudkowsky on “AI: Racing Toward the Brink”

intelligence.org

1 pointsby lyavinvor 8 Jahren0 comments

Likelihood of discontinuous progress around the development of AGI

aiimpacts.org

69 pointsby lyavinvor 8 Jahren107 comments

Vitalik Buterin Is MIRI's Third-Biggest Donor of All Time

newsbtc.com

1 pointsby lyavinvor 8 Jahren0 comments

Sources of Intuitions and Data on Artificial General Intelligence

lesserwrong.com

2 pointsby lyavinvor 8 Jahren0 comments

June 2012: 0/33 TA winners predict AI beating humans at Go within next 10 years

lesserwrong.com

2 pointsby lyavinvor 8 Jahren0 comments

Using machine learning to address AI risk

intelligence.org

2 pointsby lyavinvor 8 Jahren0 comments

MIRI: Want to get paid to spend all day learning more about ML? Apply here!

intelligence.org

2 pointsby lyavinvor 9 Jahren0 comments

A Reply to François Chollet on Intelligence Explosion

intelligence.org

115 pointsby lyavinvor 9 Jahren85 comments

Complexity no Bar to AI

gwern.net

3 pointsby lyavinvor 9 Jahren0 comments

Why We Should Be Concerned About Artificial Superintelligence

skeptic.com

2 pointsby lyavinvor 9 Jahren0 comments

MIRI got awarded $3.75M from the Open Philanthropy Project

intelligence.org

1 pointsby lyavinvor 9 Jahren0 comments

The Way the World Ends: Not with a Bang but a Paperclip

wired.com

2 pointsby lyavinvor 9 Jahren0 comments

Shane Legg: DeepMind's third cofounder

businessinsider.com

35 pointsby lyavinvor 9 Jahren9 comments

OpenAI's Researchers: Protecting Against AI’s Existential Threat

wsj.com

60 pointsby lyavinvor 9 Jahren59 comments

MILA Obtains $2.4M AI Safety Research Grant

openphilanthropy.org

1 pointsby lyavinvor 9 Jahren0 comments

comments

lyavin

vor 8 Jahrendiscuss

See also: OpenAI's Paul Christiano wrote on the same topic — https://www.lesserwrong.com/posts/AfGmsjGPXN97kNp57/argument...

(cf. https://intelligence.org/files/IEM.pdf for some of the arguments being argued against)

lyavin

vor 9 Jahrendiscuss

Interestingly, he once called MIRI[1] (formerly SIAI) “the best hope that we have”[2].

[1] https://intelligence.org/

[2] http://www.vetta.org/2009/08/funding-safe-agi/

lyavin

vor 9 Jahrendiscuss

Shane Legg isn't worried about "evil" AI, but rather an AGI/SI that simultaneously (a) has the ability to achieve complex goals in complex environments, and (b) not perfectly aligned with operators' goals [1].

We can also take a strong guess about some aspects of how sufficiently advanced cognition look from the outside, regardless of internal implementation, because of coherence theorems [2][3].

[1] http://econlog.econlib.org/archives/2016/03/so_far_unfriend....

[2] https://arbital.com/p/expected_utility_formalism/?l=7hh

[3] https://arbital.com/p/instrumental_convergence/

Submissions

Analysis of what's gone wrong with developed economies over the past few decades

A genetically modified organism could end malaria and save millions of lives

Transcript of Sam Harris and Eliezer Yudkowsky on “AI: Racing Toward the Brink”

Likelihood of discontinuous progress around the development of AGI

Vitalik Buterin Is MIRI's Third-Biggest Donor of All Time

Sources of Intuitions and Data on Artificial General Intelligence

June 2012: 0/​33 TA winners predict AI beating humans at Go within next 10 years

Using machine learning to address AI risk

MIRI: Want to get paid to spend all day learning more about ML? Apply here!

A Reply to François Chollet on Intelligence Explosion

Complexity no Bar to AI

Why We Should Be Concerned About Artificial Superintelligence

MIRI got awarded $3.75M from the Open Philanthropy Project

The Way the World Ends: Not with a Bang but a Paperclip

Shane Legg: DeepMind's third cofounder

OpenAI's Researchers: Protecting Against AI’s Existential Threat

MILA Obtains $2.4M AI Safety Research Grant

comments

June 2012: 0/33 TA winners predict AI beating humans at Go within next 10 years