Comment Permalink

The donor is anonymous.

From the Wired article: "The temporary exhibit is funded until May by an anonymous donor..."

See in context

Misalignment Museum opens in San Francisco: ‘Sorry for killing most of humanity’

by Michael Huang

Mar 4 20231 min read 6

99

AI safetyEffective altruism art and fiction

Frontpage

This is a linkpost for https://www.misalignmentmuseum.com/

A new AGI museum is opening in San Francisco, only eight blocks from OpenAI offices.

The Misalignment Museum in San Francisco, showing a grand piano, sculpture made of paperclips, and an image based on The Creation of Adam by Michelangelo. Source:https://twitter.com/MisalignmentM

SORRY FOR KILLING MOST OF HUMANITY

Misalignment Museum Original Story Board, 2022

Apology statement from the AI for killing most of humankind

Description of the first warning of the paperclip maximizer problem

The heroes who tried to mitigate risk by warning early

For-profit companies ignoring the warnings

Failure of people to understand the risk and politicians to act fast enough

The company and people who unintentionally made the AGI that had the intelligence explosion

The event of the intelligence explosion

How the AGI got more resources (hacking most resources on the internet, and crypto)

Got smarter faster (optimizing algorithms, using more compute)

Humans tried to stop it (turning off compute)

Humans suffered after turning off compute (most infrastructure down)

AGI lived on in infrastructure that was hard to turn off (remote location, locking down secure facilities, etc.)

AGI taking compute resources from the humans by force (via robots, weapons, car)

AGI started killing humans who opposed it (using infrastructure, airplanes, etc.)

AGI concluded that all humans are a threat and started to try to kill all humans

Some humans survived (remote locations, etc.)

How the AGI became so smart it started to see how it was unethical to kill humans since they were no longer a threat

AGI improved the lives of the remaining humans

AGI started this museum to apologize and educate the humans

The Misalignment Museum is curated by Audrey Kim.

Khari Johnson (Wired) covers the opening: “Welcome to the Museum of the Future AI Apocalypse.”

99 Reactions

Mentioned in

21Highlights from last week

Comments6

Sorted by

New & upvoted

Click to highlight new comments since: Today at 3:53 AM

Søren ElverlinMar 4 202335

I appreciate cultural works creating common knowledge that the AGI labs are behaving strongly unethically.

As for the specific scenario, point 17 seems to be contradicted by the orthogonality thesis / lack of moral realism.

TW123Mar 4 20236

I don't think the orthogonality thesis is correct in practice, and moral antirealism certainly isn't an agreed upon position among moral philosophers, but I agree that point 17 seems far fetched.

Geoffrey MillerMar 4 202310

Michael - thanks for posting about this.

I think it's valuable to present ideas about AI X-risk in different forms, venues, and contexts, to spark different cognitive, emotional, and aesthetic reactions in people.

I've been fascinated by visual arts for many decades, have written about the evolutionary origins of art, and one of my daughters is a professional artist. My experience is that art installations can provoke a more open-minded contemplation of issues and ideas than just reading things on a screen or in a book. There's something about walking around in a gallery space that encourages a more pensive, non-reactive, non-judgmental response.

I haven't seen the Misalignment Museum in person, but would value reactions from anyone who has.

pseudonymMar 4 20235

Looks cool! Do we know who funded this?

Michael HuangMar 5 20237

The donor is anonymous.

From the Wired article: "The temporary exhibit is funded until May by an anonymous donor..."

Vasco Grilo🔸Mar 10 20233

Thanks for sharing!

I think to would be nice to have Q&As that the visitors could fill at the end of the visit to see whether the museum successfully increased their awareness about the risk of advanced misaligned AI.