All of Timothy M.'s Comments + Replies

The next meetup will be on March 23 - RSVP here.

Next meetup will be February 24 - RSVP here.

Also there will be another article discussion group on February 18th, details and RSVP here.

Owing to a tragic laundry mishap, I'll actually be wearing a dark blue Waikiki Aquarium t-shirt with an octopus on it.

The next meetup will be on January 27th - RSVP here.

Also there will be an article discussion meeting on January 20th, discussing financial markets and investment.

The next meetup will be December 16th - RSVP here.

Also, one of our attendees is interested in having a recurring article discussion group and has scheduled an event in St. Paul on December 9th, which I encourage you to attend.

The next meetup will be Saturday, November 18th. RSVP here.

Looks like today will be on the lighter side, so if anybody has a board or card game that doesn't take too long, I suggest you bring it. I will bring my copy of Race For The Galaxy.

Also, for the "Meetups Everywhere" events there is a central coordinator and they have a survey - if willing, you can fill it out here.

The next meetup will be October 21st - see here,

All - I came down with a slight fever later yesterday. I took a rapid COVID test this morning and it came back negative, so I leave it as an exercise to the reader to determine the odds that I have COVID, but I might have given you some other disease. Sorry about that.

1Gunflint
Good luck,Timothy to you and to the rest of the meetup attendees. I guess we will each let you know if we show symptoms.

The next meetup will be September 16th - RSVP [here](The next meetup will be September 16th - RSVP here.

(Sorry for the handful of you who may be notified repeatedly - the summer meetup was unusually low in attendance so I figured I would play it safe and post this to the past two.)

The next meetup will be September 16th - RSVP here.

I feel like this metaphor doesn't strike me as accurate because humanity can engage in commerce and insects cannot.

But also humanity causes a lot of environmental degradation but we still don't actually want to bring about the wholesale destruction of the environment.

I have a few objections here:

  • Even when objectives aren't aligned, that doesn't mean the outcome is literally death. No corporation I interact with us aligned with me, but in many/most cases I am still better off for being able to transact with them.

  • I think there are plenty of scenarios where "humanity continues to exist" has benefits for AI - we are a source of training data and probably lots of other useful resources, and letting us continue to exist is not a huge investment, since we are mostly self-sustaining. Maybe this isn't literally "being ali

... (read more)
7Spenser N
In fact, corporations are quite aligned with you. Not only because they are run by humans, who are at least roughly aligned with humanity by default, but we have legal institutions and social norms which help keep the wheels on the tracks. In fact the profit motive is a powerful alignment tool - it's hard to make a profit off of humanity if they are all dead. But who aren't corporations aligned with? Humans without money or legal protections for one (though we don't need to veer off into an economic or political discussion). But also plants, insects, most animals.  Some 60% of wild animals have died as a result of human activity over the past ~50 years alone. So, I think you've made a bit of a category error here: in the scenario where a superintelligence emerges, we are not a customer, we are wildlife.  Yes, there are definitely scenarios where human existence benefits an AI. But how many of those ensure our wellbeing? It's just that there are certainly many more scenarios where they simply don't care about us enough to actively preserve us. Insects are generally quite self sustaining and good for data too, but boy they sure get in the way when we want to build our cities or plant our crops.

This is a common problem with a lot of these hypothetical AI scenarios - WHY does the Oracle do this? How did the process of constructing this AI somehow make it want to eventually cause some negative consequence?

4Razied
The negative consequences come from the oracle implementing an optimisation algorithm with objective function ϕ which is not aligned with humans. The space of objectives ϕ′ which align with humans is incredibly small among all possible objectives, and very small differences get magnified when optimised against.

Next event will be April 30th - link.

Invite for the next meetup (March 24th) is now up - see here: https://www.lesswrong.com/events/Bf9rqXH93FtkAj6a5/twin-cities-acx-meetup-mar-2023

Invite for the next meetup (March 24th) is now up - see here: https://www.lesswrong.com/events/Bf9rqXH93FtkAj6a5/twin-cities-acx-meetup-mar-2023