MIRI's 2016 Fundraiser
Our 2016 fundraiser is underway! Unlike in past years, we'll only be running one fundraiser in 2016, from Sep. 16 to Oct. 31. Our progress so far (updated live):
Employer matching and pledges to give later this year also count towards the total. Click here to learn more.
MIRI is a nonprofit research group based in Berkeley, California. We do foundational research in mathematics and computer science that’s aimed at ensuring that smarter-than-human AI systems have a positive impact on the world. 2016 has been a big year for MIRI, and for the wider field of AI alignment research. Our 2016 strategic update in early August reviewed a number of recent developments:
- A group of researchers headed by Chris Olah of Google Brain and Dario Amodei of OpenAI published “Concrete problems in AI safety,” a new set of research directions that are likely to bear both on near-term and long-term safety issues.
- Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel, and Stuart Russell published a new value learning framework, “Cooperative inverse reinforcement learning,” with implications for corrigibility.
- Laurent Orseau of Google DeepMind and Stuart Armstrong of the Future of Humanity Institute received positive attention from news outlets and from Alphabet executive chairman Eric Schmidt for their new paper “Safely interruptible agents,” partly supported by MIRI.
- MIRI ran a three-week AI safety and robustness colloquium and workshop series, with speakers including Stuart Russell, Tom Dietterich, Francesca Rossi, and Bart Selman.
- We received a generous $300,000 donation and expanded our research and ops teams.
- We started work on a new research agenda, “Alignment for advanced machine learning systems.” This agenda will be occupying about half of our time going forward, with the other half focusing on our agent foundations agenda.
We also published new results in decision theory and logical uncertainty, including “Parametric bounded Löb’s theorem and robust cooperation of bounded agents” and “A formal solution to the grain of truth problem.” For a survey of our research progress and other updates from last year, see our 2015 review. In the last three weeks, there have been three more major developments:
- We released a new paper, “Logical induction,” describing a method for learning to assign reasonable probabilities to mathematical conjectures and computational facts in a way that outpaces deduction.
- The Open Philanthropy Project awarded MIRI a one-year $500,000 grant to scale up our research program, with a strong chance of renewal next year.
- The Open Philanthropy Project is supporting the launch of the new UC Berkeley Center for Human-Compatible AI, headed by Stuart Russell.
Things have been moving fast over the last nine months. If we can replicate last year’s fundraising successes, we’ll be in an excellent position to move forward on our plans to grow our team and scale our research activities.
Meetup : Bay Area Winter Solstice 2016
Discussion article for the meetup : Bay Area Winter Solstice 2016
It's time to gather together and remember the true Reasons for the Season: axial tilt, orbital mechanics and other vast-yet-comprehensible forces have converged together to bring another year to a close, and as the days grow shorter and colder we remember how profoundly lucky we are to have been forged by blind, impersonal forces into beings that can understand, and wonder, and appreciate ourselves and each other. This year's East Bay Rationalist Winter Solstice will be held in the center of Berkeley, bringing 300 rationalists together in a theatre hall for food, songs, speeches, and conversations. We encourage other Bay denizens who can't make our solstice to put on their own show. Or even if you do come, we encourage people to try out their own ideas. The East Bay Solstice celebration will be on Saturday, December 17th, in the Anna Head Alumnae Hall in Berkeley. Acquire tickets here: https://www.eventbrite.com/e/2016-bay-area-winter-solstice-tickets-27853776395 We are coordinating with the Bayesian Choir and will be coordinating with various speakers, as in previous years. An MC and schedule will be posted as details solidify. Kids are welcome. Vegetarian food will be available. Let us know if you have specific accomadation requests or have questions.
Discussion article for the meetup : Bay Area Winter Solstice 2016
Meetup : Welcome Scott Aaronson to Texas
Discussion article for the meetup : Welcome Scott Aaronson to Texas
We're having another all-Texas party in Austin. We'll be welcoming Scott Aaronson, who's moved here to teach at UT Austin.
(Previously, we were worried that the time might work, but now it's been confirmed.)
Discussion article for the meetup : Welcome Scott Aaronson to Texas
Meetup : San Francisco Meetup: Stories
Discussion article for the meetup : San Francisco Meetup: Stories
We'll be meeting to tell each other stories! Ideally, come with a story from your life (doesn't have to be about anything in particular) that you want to tell other people.
For help getting into the building, please call (or text, with a likely-somewhat-slower response rate): 301-458-0764.
Format:
We meet and start hanging out at 6:15, but don’t officially start doing the meetup topic until 6:45-7 to accommodate stragglers. Usually there is a food order that goes out before we start the meetup topic.
About these meetups:
The mission of the SF LessWrong meetup is to provide a fun, low-key social space with some structured interaction, where new and non-new community members can mingle and have interesting conversations. Everyone is welcome.
We explicitly encourage people to split off from the main conversation or diverge from the topic if that would be more fun for them (moving side conversations into a separate part of the space if appropriate). Meetup topics are here as a tool to facilitate fun interaction, and we certainly don’t want them to inhibit it.
Discussion article for the meetup : San Francisco Meetup: Stories
Meetup : Washington, D.C.: Technology of Communication
Discussion article for the meetup : Washington, D.C.: Technology of Communication
We will be meeting in the courtyard to chat about tools people use to get information from one place to another, both in the past and in the present.
Upcoming meetups:
- Oct. 30: Halloween Party
- Nov. 6: Fun & Games
Discussion article for the meetup : Washington, D.C.: Technology of Communication
Meetup : Munich Meetup in October
Discussion article for the meetup : Munich Meetup in October
Hello all,
new month, new LW meeting. After the nice meeting last month we had an idea of discussing cognitive biases in conspiracy texts. As always everyone is encouraged to suggest own topics or articles.
Discussion article for the meetup : Munich Meetup in October
Meetup : Games in Kocherga club: FallacyMania, Tower of Chaos, Scientific Discovery
Discussion article for the meetup : Games in Kocherga club: FallacyMania, Tower of Chaos, Scientific Discovery
Welcome to Moscow LW community makeshift games! In that games, some rationality skills are involved, so you can practise while you playing!
- FallacyMania: it is a game where you guess logical fallacies in arguments, or practise using logical fallacies yourself (depending on team in which you will be).
Details about the game: http://goo.gl/BtRVhB
- Tower of Chaos: funny game with guessing the rules of human placement on a Twister mat.
Game rules: https://goo.gl/u9qgc3
- Scientific Discovery: challenging table game with guessing the rules about items placement on the table.
Come to antikafe "Kocherga", ul.B.Dorogomilovskaya, 5-2. The map is here: http://kocherga-club.ru/#contacts . Nearest metro station is Kievskaya. If you are lost, call Sasha at +7-905-527-30-82.
Games begin at 19:40, the length is 3.5 hours.
Discussion article for the meetup : Games in Kocherga club: FallacyMania, Tower of Chaos, Scientific Discovery
Meetup : Stockholm: Mental contrasting
Discussion article for the meetup : Stockholm: Mental contrasting
Last week, we had only enough time for an intro to TAPs. This week, we will dive into mental contrasting, in a workshop held by David_Kristoffersson.
Ever had a valuable goal that you knew you could do, yet you somehow didn’t feel motivated to follow through with it?
Enter mental contrasting. Mental contrasting “translates cerebral thoughts of success into concrete emotions of motivation”. It combines naturally with TAPs (implementation intentions).
Bring a bugs list, or a goal you want to achieve -- a goal you haven’t had consistent motivation for.
The meetup is at a KTH academic building and the room is on the 5th floor, two stairs up. If you want to influence future meetup times, fill out this poll.
Discussion article for the meetup : Stockholm: Mental contrasting
Meetup : NY Solstice 2016 - The Story of Smallpox
Discussion article for the meetup : NY Solstice 2016 - The Story of Smallpox
Every winter, people across the US East Coast (and beyond!) travel to New York City, to celebrate humanity's triumph against the darkness. Come to sing songs, to connect with people from the rationality and secular communities, and (this particular year), to hear the complete story of smallpox, from its earliest appearances to its eventual eradication, and more. (Note: To pay for the venue, tickets are available at www.secularsolstice.com)
Discussion article for the meetup : NY Solstice 2016 - The Story of Smallpox
Meetup : Zürich social Rationality meetup
Discussion article for the meetup : Zürich social Rationality meetup
There seem to be quite a few new Rationality interested people in Zürich now. Come and meet us! No program.
= 783df68a0f980790206b9ea87794c5b6)
Subscribe to RSS Feed
= f037147d6e6c911a85753b9abdedda8d)