derikk

3mo

One important property for a style of thinking and argumentation to have is what I call galaxy brain resistance: how difficult is it to abuse that style of thinking to argue for pretty much whatever you want - something that you already decided elsewhere for other reasons? The spirit here is similar to falsifiability in science: if your arguments can justify anything, then your arguments imply nothing.

In this post, I will argue that patterns of reasoning that are very low in galaxy brain resistance are a common phenomenon, some with consequences that are mild and others with consequences that are extreme. I will also describe some patterns that are high in galaxy

derikk2y

ACX Meetups Everywhere 2023: Times & Places

There's also the meetup in Cavendish, VT!

Replying toThe AI Safety Game (UPDATED)

derikk3y

The AI Safety Game (UPDATED)

The site seems to have gone down; I've uploaded a mirror at https://cvnd.sh/aigame.

Apply to the Cavendish Labs Fellowship (by 4/15)

agg

agg, derikk

Cavendish Labs is a new research organization in Vermont focused on technical work on existential risks. We'd like to invite you to apply to our fellowships in AI safety and biosecurity!

Positions are open for any time between June 1 and December 10, 2023. We pay a stipend of $1,500/month, plus food and housing are provided. Anyone with a technical background is encouraged to apply, even if you lack specific expertise in these fields.

Applications for summer research fellows are closing April 15th. Apply here!

Research lab on a river in Vermont, AI artist's conception

(Note: we likely cannot accept people who need visa sponsorship to work in the U.S.)

Replying toAnnouncing Cavendish Labs

derikk3y

Announcing Cavendish Labs

Hi Trevor! I think you made some good points about the benefits of trying different models for AI safety research, especially to guard against tail risks. I'm excited to test out this relatively low-budget alternative to working in the Bay.

Cavendish is actually under 3 hours from Boston (and 2.5 hours from Harvard or MIT). Rent isn't $1000, but we did find a beautiful place for the summer for under $1/sqft/month.

We've just announced ourselves (Cavendish Labs) here! We plan on having a visiting scholars program that will allow those currently working full-time elsewhere to try out work on alignment for a couple weeks or so; more on that later.

Announcing Cavendish Labs

derikk

derikk, agg

We’re excited to announce Cavendish Labs, a new research institute in Vermont focused on AI safety and pandemic prevention! We’re founding a community of researchers who will live together and work on the world’s most pressing problems.

Uh, why Vermont?

It’s beautiful; it has one of the cheapest costs of living in the United States; there’s lots of great people; it’s only a few hours away from Boston, NYC, and Montreal. There’s even a train that goes there from Washington D.C.! A few of us briefly lived in Vermont during the pandemic, and we found it to be a fantastic place to live, think, and work. Each season brings with it a new kind of beauty... (read 348 more words →)

Replying toMessage Length

derikk4y

Message Length

This sounds like a classic example of the bias-variance tradeoff: adding parameters to your model means it can more accurately fit your data (lower bias), but is more sensitive to fluctuations in that data (higher variance). Total error when making predictions on new data is minimized when the bias and variance errors are balanced.

Another example: given data points, you can always draw a polynomial of degree $n - 1$ that fits them perfectly. But the interpolated output values may vary wildly with slight perturbations to your measured data, which is unlikely to represent a real trend. Often a simple linear regression is the most appropriate model.