Louie

That's cool. Where did you hear that?

Replying toTruth: It's Not That Great

Louie12y

Truth: It's Not That Great

2009: "Extreme Rationality: It's Not That Great"

2010: "Self-Improvement or Shiny Distraction: Why Less Wrong is anti-Instrumental Rationality"

2013: "How about testing our ideas?"

2014: "Truth: It's Not That Great"

2015: "Meta-Countersignaling Equilibria Drift: Can We Accelerate It?"

2016: "In Defense Of Putting Babies In Wood Chippers"

Replying toRequest for concrete AI takeover mechanisms

Louie12y

Request for concrete AI takeover mechanisms

Yes. I assume this is why she's collecting these ideas.

Katja doesn't speak for all of MIRI when she says above what "MIRI is interested in".

In general MIRI isn't in favor of soliciting storytelling about the singularity. It's a waste of time and gives people a false sense that they understand things better than they do by incorrectly focusing their attention on highly salient, but ultimately unlikely scenarios.

Replying toRequest for concrete AI takeover mechanisms

Louie12y

Request for concrete AI takeover mechanisms

Than you should reduce your confidence in what you consider obvious.

Replying toRequest for concrete AI takeover mechanisms

Louie12y

Request for concrete AI takeover mechanisms

So MIRI is interested in making a better list of possible concrete routes to AI taking over the world.

I wouldn't characterize this as something that MIRI wants.

Replying toOne Medical? Expansion of MIRI?

Louie12y

One Medical? Expansion of MIRI?

To clarify, One Medical partnered with us on this event... but are not materially involved with expanding MIRI themselves. They're simply an innovative business nearby us in Berkeley who wanted to support our work. I know it's somewhat unprecedented to see MIRI with strong corporate support, but trust me, it's a good thing. One Medical's people did a ton of legwork and made it super easy to host over 100 guests at that event with almost no planning needed on our part. They took care of everything so we could just focus on our work. A perfect partnership in our opinion.

Also, we still have $149 credits for the free 1-year memberships to One Medical's service. If you live in Berkeley, SF, NY, Boston, Chicago, LA, or DC and are looking for a good primary care doctor, check out their website and if you think it's a good fit for you, take them up on their promotional offer with this link: http://bit.ly/1fnRHrH (expires 4/9/14).

Replying toBook Review: Naïve Set Theory (MIRI course list)

Louie12y

Book Review: Naïve Set Theory (MIRI course list)

Thanks. That was what I thought, but I haven't read Causality yet.

Replying toBook Review: Naïve Set Theory (MIRI course list)

Louie12y

Book Review: Naïve Set Theory (MIRI course list)

Do you think Causality is a superior recommendation to Probabilistic Graphical Models?

Replying toMIRI's 2013 Summer Matching Challenge

Louie13y

MIRI's 2013 Summer Matching Challenge

Fixed. Thanks.

Replying toEffective Altruism Through Advertising Vegetarianism?

Louie13y

Effective Altruism Through Advertising Vegetarianism?

The unreasonably low estimates would suggest things like "I'm net reducing factory-farming suffering if I eat meat and donate a few bucks, so I should eat meat if it makes me happier or healthier sufficiently to earn and donate an extra indulgence of $5 ." There are some people going around making the claim, based on the extreme low-ball cost estimates.

Correct. I make this claim. If vegetarianism is that cheap, it's reasonable to bin it with other wastefully low-value virtues like recycling paper, taking shorter showers, turning off lights, voting, "staying informed", volunteering at food banks, and commenting on less wrong.

Young Americans believe they have the best health in the world...

Louie

13y

Of course, it turns out they're actually last among developed nations in real health outcomes.

The U.S. ranks #1 among 17 affluent, western countries in the percentage of people aged 5 to 34 who rate their health as good. Unfortunately, when doctors look at people’s actual health, at indicators such as obesity, diabetes, and simply the chance that someone will die before his or her next birthday, the U.S. ranks last: young Americans are #17 out of 17 in real health.

Course recommendations for Friendliness researchers

Louie

13y

When I first learned about Friendly AI, I assumed it was mostly a programming problem. As it turns out, it's actually mostly a math problem. That's because most of the theory behind self-reference, decision theory, and general AI techniques haven't been formalized and solved yet. Thus, when people ask me what they should study in order to work on Friendliness theory, I say "Go study math and theoretical computer science."

But that's not specific enough. Should aspiring Friendliness researchers study continuous or discrete math? Imperative or functional programming? Topology? Linear algebra? Ring theory?

I do, in fact, have specific recommendations for which subjects Friendliness researchers should study. And so I worked with a few of my best interns at MIRI to... (read 2747 more words →)

112

Bounding the impact of AGI

Louie

13y

For those of you interested, András Kornai's paper "Bounding the impact of AGI" from this year's AGI-Impacts conference at Oxford had a few interesting ideas (which I've excerpted below).

Summary:

Acceptable risk tolerances for AGI design can be determined using standard safety engineering techniques from other fields
Mathematical proof is the only available tool to secure the tolerances required to prevent intolerable increases in xrisk
Automated theorem proving will be required so that the proof can reasonably be checked by multiple human minds

Safety engineering
Since the original approach of Yudkowsky (2006) to friendly AI, which sought mathematical guarantees of friendliness, was met with considerable skepticism, we revisit the issue of why such guarantees are essential. In designing radioactive equipment, a

... (read 1401 more words →)

LessWrong podcasts

Louie

13y

Today we're announcing a partnership with Castify to bring you Less Wrong content in audio form. Castify gets blog content read by professional readers and delivers it to their subscribers as a podcast so that you can listen to Less Wrong on the go. The founders of Castify are big fans of Less Wrong so they're rolling out their beta with some of our content.

Note: The embedded player (above) isn't live as of this posting, but should be deployed soon.

To see how many people will use this, we're having the entire Mysterious Answers to Mysterious Questions core sequence read and recorded. We thought listening to it would be a great way for new readers to get caught

... (read more)

New WBE implementation

Louie

13y

It usually isn't profitable to pay attention to science news, since science journalists largely misintrepret new "breakthroughs". But I am somewhat interested in this story about "artificial brains" coming out of Canada.

Most large neuron simulations I've read about before don't actually do anything. But apparently there's a somewhat large new WBE implementation at the University of Waterloo that performs sub-humanly on several tasks while having similar weaknesses to human brains.

Curious what others think of this recent development.

Louie

13y

LessWrong has rolled out a new feature on the user preference pages under "Location":

This is UNCHECKED by default. Also, we don't know by default where you live.

If you think you might want to meet up with other LWers, please input your location and check this box. Once enough people have signed up in a new area, it will make starting a LW meetup there that much more straightforward for the future organizer. (You'll just get that email; they won't see your email address.) In general, it seems like being able to know something about where LWers live would be helpful, so please consider entering your approximate location even if you don't check the box.

Thanks to Wesley Moore for deploying this upgrade to the LW backend.

The Singularity Institute is hiring an executive assistant near Berkeley

Louie

14y

The Singularity Institute is hiring an executive assistant for Executive Director Luke Muehlhauser.

Right now his limiter (besides the need for some sleep and recreation) is not (1) cognitive exhaustion after a certain number of hours or (2) akrasia, but instead (3) needing to spend lots of time doing things that don't need to be him: e.g. hunting down the best product for X and buying it, shopping for food, finding names and email addresses for the top 30 researchers in field X, finding motorcycle classes and a motorcycle so he can stop paying so much for cabs when he doesn't have time for public transport, scheduling meetings with dozens of donors and collaborators,... (read 296 more words →)

Singularity Institute $100,000 end-of-year fundraiser only 20% filled so far

Louie

14y

** cross-posted from http://singinst.org/2011winterfundraiser/ **

Contains detailed info about accomplishments and plans at SI. Thanks for supporting our work! -Louie

ARTIFICIAL INTELLIGENCE MORE RELEVANT THAN EVER

Recent books like Machine Ethics from Cambridge University Press and Robot Ethics from MIT Press, along with the U.S. military-funded research that resulted in Governing Lethal Behavior in Autonomous Robots show that the world is waking up to the challenges of building safe and ethical AI. But these projects focus on limited AI applications and fail to address the most important concern: how to ensure that smarter-than-human AI benefits humanity. The Singularity Institute has been working on that problem longer than anybody, a full decade before the Singularity landed... (read 348 more words →)

$100 off for Less Wrong: Singularity Summit 2011 on Oct 15 - 16 in New York

Louie

14y

There's still time left to register for the Singularity Summit in New York. But hurry because there are only a few weeks left!

Register now so you can meet Eliezer, AnnaSalamon, Lukeprog, and more! I'm particularly excited about several invited speakers, such as neuroscientist Christof Koch (who I've blogged about here) and author Sharon Bertsch McGrayne who recently published The Theory That Would Not Die: How Bayes' Rule Cracked the Enigma Code, Hunted Down Russian Submarines, and Emerged Triumphant from Two Centuries of Controversy.


Ray Kurzweil	Eliezer Yudkowsky	Anna Salamon	Luke Muehlhauser

PS - If you have a blog and you'd... (read 239 more words →)

Last day to register for Foresight@Google - Mountain View, California

Louie

15y

For those in the California bay area, I thought I'd post some details about the upcoming Foresight conference.

FORESIGHT@GOOGLE

25th Anniversary Conference Celebration and Reunion Weekend

Google HQ in Mountain View, CA

June 25-26 2011

Speakers and panelists include:

• WILLIAM ANDREGG - Founder/CEO of Halcyon Molecular

• MIKE GARNER, PhD - Chair of ITRS Emerging Research Materials

• MIKE NELSON - CTO of NanoInk

• LUKE NOSEK - CoFounder of Paypal, Founders Fund
Partner

• Keynote: BARNEY PELL, PhD -
Cofounder/CTO of Moon Express

• PAUL SAFFO, PhD - Wired, NYT-published strategist & forecaster

• SIR FRASER STODDART, PhD - Knighted for creation of molecular "switches" and a new field of nanochemistry

• THOMAS THEIS, PhD - IBM's Director of Physical Sciences

• Keynote: JIM VON EHR - Founder/President of Zyvex, the world's first successful molecular nanotech company

For the full speaker roster, as well as information on the 25th Anniversary Banquet, see the conference website:

http://www.foresight.org/reunion

Space is limited!

For $50 off, our supporters can register with the discount code: SIAI

LESSWRONG
LW

LESSWRONG
LW

What I've learned from Less Wrong

How to Save the World

96 Bad Links in the Sequences [fixed]

Course recommendations for Friendliness researchers

Louie

Louie

Young Americans believe they have the best health in the world...

Course recommendations for Friendliness researchers

Bounding the impact of AGI

LessWrong podcasts

New WBE implementation

Sign up to be notified about new LW meetups in your area

The Singularity Institute is hiring an executive assistant near Berkeley

Louie

What I've learned from Less Wrong

How to Save the World

96 Bad Links in the Sequences [fixed]

Course recommendations for Friendliness researchers

Louie

Louie

Young Americans believe they have the best health in the world...

Course recommendations for Friendliness researchers

Bounding the impact of AGI

LessWrong podcasts

New WBE implementation

Sign up to be notified about new LW meetups in your area

The Singularity Institute is hiring an executive assistant near Berkeley

ARTIFICIAL INTELLIGENCE MORE RELEVANT THAN EVER