Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

Meetup : [Montreal] Sunrise on top of Mont Royal: Final Event

0 MathieuRoy 16 October 2017 03:27AM

Discussion article for the meetup : [Montreal] Sunrise on top of Mont Royal: Final Event

WHEN: 16 October 2017 06:15:00AM (-0400)

WHERE: Montreal

Facebook Event: https://www.facebook.com/events/342508759494937/

We're leaving from the Macroscope (810 Avenue Duluth E) at 6:15 and will pass by Les Échelles at 6:30 in order to be on top of Mont Royal for the sunrise which will be at 7:12. You can either join us at the Macroscope or at the top.

A text on the last virtue of rationality will be read once at the top of Mont Royal.

You're welcome afterward at the Macroscope for a community breakfast.

For any questions, you may reach Mati at 438-886-0994.

Discussion article for the meetup : [Montreal] Sunrise on top of Mont Royal: Final Event

Meetup : [Montreal] Sunrise on top of Mont Royal: Perfectionism (9/12)

0 MathieuRoy 22 September 2017 04:25AM

Discussion article for the meetup : [Montreal] Sunrise on top of Mont Royal: Perfectionism (9/12)

WHEN: 25 September 2017 05:30:00AM (-0400)

WHERE: Mont Royal, Montreal

Facebook Event: https://www.facebook.com/events/779754812204289/

We're leaving from the Macroscope (810 Avenue Duluth E) at 5:35 and will pass by Les Échelles (3655 St-Laurent) at 5:50 in order to be on top of Mont Royal for the sunrise which will be at 6:45. You can either join us at the Macroscope, at Les Échelles, or at the top.

A short text on Perfectionism, one of the 12 virtues of rationality, will be read once at the top of Mont Royal.

This can be a good opportunity to put your coming week into perspective.

Source of the texts: "Twelve Virtues of Rationality" by Eliezer Yudkowsky http://yudkowsky.net/rational/virtues/

Discussion article for the meetup : [Montreal] Sunrise on top of Mont Royal: Perfectionism (9/12)

Meetup : [Montreal] Petrov Day Ceremony

0 MathieuRoy 22 September 2017 04:22AM

Discussion article for the meetup : [Montreal] Petrov Day Ceremony

WHEN: 26 September 2017 05:30:00PM (-0400)

WHERE: Montreal

Facebook Event: https://www.facebook.com/events/1955393698036590/ Contact Mati at mathieu.roy.37@gmail.com for exact address. This event is designed to provoke existential terror and involves staring into the abyss. If you want to avoid that, do NOT come. "Petrov Day is a yearly event on September 26 commemorating the anniversary of the Petrov incident, where a false alarm in the Soviet early warning system nearly set off a nuclear war. The purpose of the ritual is to make catastrophic and existential risk emotionally salient, by putting it into historical context and providing positive and negative examples of how it has been handled. This is not for the faint of heart and not for the uninitiated; it is aimed at those who already know what catastrophic and existential risk is, have some background knowledge of what those risks are, and believe (at least on an abstract level) that preventing those risks from coming to pass is important." (James Babcock) For the reasons mentionned above, and because this is a ceremony better done with a small group, this event is invite-only. Please contact the organizers if you would like to invite someone else. The schedule will be as follow: 17:30: Arrival 17:30 - 19:00: Potluck 19:00: Putting food away, and preparing the place for the ceremony 19:25: Locking the doors 19:30: Video on existential risks 20:00 - 22:00: Ceremony 22:00+: Discussions IMPORTANT NOTE: AT 19:25, WE WILL LOCK THE DOORS. No one will be allowed beyond this point, no matter the reason. The Ceremony has to be experienced in its entirety, and without interruptions. During the ceremony, attendees will be invited to read small paragraphs (mostly on the history of humanity) from the Ceremony booklet. Various local groups throughout the world will also be doing this ceremony on September 26th. We will all have a red button, and if a person from any of the groups presses their button, everyone (from all the participating groups) will need to immediately clean their place silently, and go back home. When it comes to existential risks, we're all in this toghether, and it only takes one group to screw everything up. The red button is a symbol of that.

Discussion article for the meetup : [Montreal] Petrov Day Ceremony

Comment author: Yvain 19 March 2009 01:57:34PM *  13 points [-]

I'm glad you brought that up.

I've thought about this a few times, and I agree with you that it promotes sexism and is bad, but I just really hate using the phrases "he or she" every time I have to use a pronoun. A sentence like "A rationalist should ensure he or she justifies his or her opinion to himself or herself" is just too awkward to understand. And I am too much of a grammar purist to use "them" as a singular.

I used to use the gender-neutral pronoun "ze", but people told me they didn't understand it or didn't like it or thought it sounded stupid. And I tried using "she" as the default for a while, but people kept getting confused because they weren't expecting it, and trying to figure out where I'd mentioned a female.

I'm willing to accept whatever the common consensus is here. Maybe Less Wrong-ers are open-minded enough to accept "ze" where the average reader isn't.

(I've heard some people here use "ve" a few times, but from the context I gathered it was more of a way to refer to aliens/AIs/transhumans than a normal gender-neutral pronoun. Is this true?)

Comment author: MathieuRoy 19 September 2017 09:24:04PM 0 points [-]

FYI: I use this Chrome extension to gender-neutralize what I read: https://chrome.google.com/webstore/detail/the-ungender/blfboedipjpaphkkdoddffpnfjknfeda?hl=en

Meetup : Sunrise on top of Mont Royal: Humility (8/12)

0 MathieuRoy 15 September 2017 05:42AM

Discussion article for the meetup : Sunrise on top of Mont Royal: Humility (8/12)

WHEN: 18 September 2017 05:30:00AM (-0400)

WHERE: Mont Royal, Montreal

Facebook Event: https://www.facebook.com/events/338263239954916/

I haven't been posting all this series of events on LessWrong, but we're often going to see the sunrise from the top of Mont Royal on Mondays, and read one of the 12 virtues of rationality.

Next Monday, we'll leave from the Macroscope, a Rationalist Sharehouse (810 Avenue Duluth E), at 5:30 and will pass by Les Échelles (3655 St-Laurent) at 5:40 in order to be on top of Mont Royal for the sunrise which will be at 6:37. You can either join us at the Macroscope, at Les Échelles, or at the top.

A short text on Humility, one of the 12 virtues of rationality, will be read once at the top of Mont Royal.

This can be a good opportunity to put your coming week into perspective.

For any questions, you may reach Mati at 438-886-0994.

Source of the texts: "Twelve Virtues of Rationality" by Eliezer Yudkowsky http://yudkowsky.net/rational/virtues/

Discussion article for the meetup : Sunrise on top of Mont Royal: Humility (8/12)

Meetup : [CANCELED] Rationalist Retreat (Northeast America - Equinox 2017)

0 MathieuRoy 15 September 2017 05:35AM

Discussion article for the meetup : [CANCELED] Rationalist Retreat (Northeast America - Equinox 2017)

WHEN: 29 September 2017 02:00:00PM (-0400)

WHERE: 1368 River Rd, Lake Luzerne, NY 12846-3826, United States

Facebook Event: https://www.facebook.com/events/1614831155205823/ Hey! Let's do a Rationalist Retreat for Northeast America, and bring together rationalists from Montreal, Boston, New York, Ottawa, Toronto, and anywhere else people are willing to travel from! It's a good opportunity to get to know each other, and just have a good time. We've made a tentative schedule, but we can decide in group what we want to do. If you can only join us for 1 day, that's fine as well. If you have games, physical activities, rituals, workshops or other things to propose, please do so. Friday 14:00+ Arrival at Bear Slide, NY 1368 River Rd, Lake Luzerne, NY 12846-3826, United States Meeting each other. Potluck (please label non-vegan food). Fire. Canadians might want to arrive at the border early (12:00 ish) or late (21:00 ish) to avoid a 0.5-1 hour waiting. Saturday (Still at Bear Slide, NY) Morning: Hiking Hiking at Berry Pond (very close to campsite) http://www.lglc.org/preserves/berry-pond/ Early Afternoon : Sports / Games (physical activities) Suggestions: 1-2-3 for me, kick the can, person hunt, capture the flag, etc. Late Afternoon / Early Evening: Board Games Social Deduction Games: a fake artist goes to New York (with stick on the ground), (live-action) werewolf, two rooms and a boom, etc. Rationalist Games: clicker, paranoid debating, etc. Evening: Jam & Dance Bring your instruments Sunday Afternoon: Apple picking At Apple Jack’s Orchard, near Plattsburg Departure around 12:00 from the camp site https://www.applejackorchards.com/


Things you might want to bring: -passport (for Canadians) -water -food -camping equipment: flashlight, sleeping bag, tent, etc. Before the event, we will contact participants to give more information such as phone number to reach in case you don't find the place, etc. In the meantime, don't hesitate to contact me if you have any questions (mathieu.roy.37@gmail.com or Facebook). Note: If the event doesn’t reach at least 10 participants (which seems unlikely), the event will be canceled.

Discussion article for the meetup : [CANCELED] Rationalist Retreat (Northeast America - Equinox 2017)

Meetup : [Montreal] AI Safety: Corrigibility

0 MathieuRoy 06 August 2017 09:02AM

Discussion article for the meetup : [Montreal] AI Safety: Corrigibility

WHEN: 10 August 2017 07:00:00AM (-0400)

WHERE: 2920 Ch de la Tour, Montréal, QC

Meetup Event: https://goo.gl/XRHGS6

Location: room 3195, Pavillon André-Aisenstadt, Université de Montréal

Being able to correct the behavior of an AGI will be the discussion of our next AI Safety meeting. Basically we want to know if we can design a utility function that accepts human intervention (even though it might interfere with its other goals). More specifically, we will discuss the 3 papers below. All results are by necessity about simple toy models. They are meant to direct future research.

Here's a short description of each paper. I recommend you read as much as you can in this order.

Corrigibility (https://intelligence.org/files/Corrigibility.pdf): This sets up the problem and discusses issues with the most obvious approaches.

The Off-Switch Game (https://people.eecs.berkeley.edu/~dhm/papers/off_switch_AAAI_ws.pdf): If the AI is uncertain about the users utility function and treats any action by the user as information about this utility (as in the case of inverse reinforcement learning), then the AI may be amenable to correction. A more exact statement (with caveats) is found in this paper.

Safely Interruptible Agents (http://intelligence.org/files/Interruptibility.pdf): Similar to the previous paper but with a different approach and focus. They ask whether it's possible to interrupt an AI without damaging it's learning (i.e. will it learn as if it never gets interrupted). As above they show this is possible in the case of an uncertain AI. They even manage to show an example of an ideal 'perfect' intelligence for which this is true.

Discussion article for the meetup : [Montreal] AI Safety: Corrigibility

Comment author: waveman 11 July 2017 01:35:59AM 1 point [-]

Can I suggest you put the name of the city at the start of the title, so that everyone doesn't need to go into the posting to check is it their city?

Others do this. Thanks,

Comment author: MathieuRoy 27 July 2017 07:53:21AM 0 points [-]

Just saw your comment. Thanks for letting me know.

Meetup : Montreal - AI Safety: Orthogonality & Convergent instrumental goals (MIRI's theses part 1)

0 MathieuRoy 24 July 2017 06:26AM

Discussion article for the meetup : Montreal - AI Safety: Orthogonality & Convergent instrumental goals (MIRI's theses part 1)

WHEN: 27 July 2017 07:00:00PM (-0400)

WHERE: room 3195, Pavillon André-Aisenstadt, Université de Montréal

Discussion article for the meetup : Montreal - AI Safety: Orthogonality & Convergent instrumental goals (MIRI's theses part 1)

Meetup : AI Ethics: Deep dive on how to embed values into machines

0 MathieuRoy 11 July 2017 06:00PM

Discussion article for the meetup : AI Ethics: Deep dive on how to embed values into machines

WHEN: 19 July 2017 07:00:00AM (-0400)

WHERE: 2920 Ch de la Tour, Montréal, QC

Meetup event for all information: https://goo.gl/1pzC2z Exact location: room 3195, Pavillon André-Aisenstadt, Université de Montréal

Summary: This is the second session in our bi-weekly AI Ethics group where we will be making a deep dive into how best to embed values into machines, what the implications of that are and concrete proposals that we can have around it.

Discussion article for the meetup : AI Ethics: Deep dive on how to embed values into machines

View more: Next