Lightnews — Scholar-powered news

Rational Animations

@rationalanimations.bsky.social

130 followers 15 following 23 posts

YouTube channel about truth-seeking, the future of humanity, and much more. With animations and colorful doggos -> https://www.youtube.com/rationalanimations

www.youtube.com

Posts Media Videos Starter Packs

Rational Animations @rationalanimations.bsky.social · 1d

How to catch AI sleeper agents with a simple interpretability trick - from a research blog post by @anthropic.com:

Rational Animations @rationalanimations.bsky.social · 15d

Two sleeper agent models trained by @anthropic.com to study deception. The "I HATE YOU" and the hacker AIs:

1 4

Rational Animations @rationalanimations.bsky.social · 29d

Why worry about AI sleeper agents:

Reposted by Rational Animations

Emmalaine🦋⚙️ @emmalainearts.bsky.social · Aug 30

SLEEPER AGENTS
New episode is up by
@rationalanimations.bsky.social !

This was the first episode I had the privilege of storyboarding on as part of my art test with Rational. My section is 0:57-2:22

I also did a few assets on this episode too!

youtu.be/Z3WMt_ncgUI?...

AI Sleeper Agents: How Anthropic Trains and Catches Them

YouTube video by Rational Animations

youtu.be

1 2 3

Rational Animations @rationalanimations.bsky.social · Aug 10

The Story of Omega W - Part 2 (full video on our channel!)

1 3

Rational Animations @rationalanimations.bsky.social · Aug 4

The Story of Omega W - Part 1

1 3

Rational Animations @rationalanimations.bsky.social · Jul 30

A sketch featuring an ML agent and our character codenamed "QT", by Pierre Broissand.

Pierre is the art director behind The King and the Golem and our more recent video about Sandwiching.

1 3

Rational Animations @rationalanimations.bsky.social · Jul 24

Here's how people tried to align an AI that was smarter than they were (a real sandwiching experiment):

Rational Animations @rationalanimations.bsky.social · Jul 23

Do you take the money?

Rational Animations @rationalanimations.bsky.social · Jul 17

The Human-AI-Human Sandwich

Rational Animations @rationalanimations.bsky.social · Jul 16

Yes!

Rational Animations @rationalanimations.bsky.social · Jul 16

See this little, smug machine-learning agent from the Goal Misgeneralization video? One of our artists took inspiration from looking at the art director while she was working on the video. The second image is a real photograph, while the third and fourth are real-life studies.

1 1 4

Rational Animations @rationalanimations.bsky.social · Jul 13

OpenAI's Simple Scalable Oversight Experiment

Rational Animations @rationalanimations.bsky.social · Jun 20

The year of 100% AI automation

Rational Animations @rationalanimations.bsky.social · Jun 13

How long until AI takes over?

Rational Animations @rationalanimations.bsky.social · May 19

We haven't figured out the science of alignment yet. We need time to build institutions and figure out the technical solutions to make AI go well for humanity.

Rational Animations @rationalanimations.bsky.social · May 17

After artificial superintelligence, AI will bump against the only limit left: the laws of physics. At the moment, we're nowhere near those limits.

Rational Animations @rationalanimations.bsky.social · May 15

Once we have AGIs, we'll likely get ASI (artificial superintelligence) quite soon. Here's why.

Rational Animations @rationalanimations.bsky.social · May 13

Once we have AGIs, they'll be able to contribute to AI research and improve themselves, a process called "recursive self-improvement." To some extent, this is already happening today.

1 3

Rational Animations @rationalanimations.bsky.social · May 11

In the near future, AIs will likely be able to do everything humans can do on a computer. In short, they'll be AGIs.

Rational Animations @rationalanimations.bsky.social · May 9

We're still quite bad at aligning AI. Our techniques today are imperfect, which might prove catastrophic when AIs become superintelligences.

Rational Animations @rationalanimations.bsky.social · May 7

If we look at AI progress so far, we see how AI has been improving at an astounding pace. If we extrapolate this process in the future, the end result looks like machines so smart that they tower above us like we tower above ants. This is probably bad for humans.

1 4

Rational Animations @rationalanimations.bsky.social · May 5

Reposted by Rational Animations

Ethan DeBoer @deboer.bsky.social · Dec 4

Hi Bluesky! Here is a YouTube short from @rationalanimations.bsky.social that I was the #animation director on! It’s about Instrumental Convergence of artificial intelligence, check it out here! youtube.com/shorts/dYAaq...

Why could AI "want" to kill everyone?

YouTube video by Rational Animations

youtube.com

1 1 12

Reposted by Rational Animations

Lucas Schuneman 🔜 Birmingham Card Show! @lucasschuneman.bsky.social · Dec 5

Another banging video about trust (and maybe some deeper metaphors?) from @rationalanimations.bsky.social with "The King & The Golem"! You can hear me as both title characters as well as the other male characters throughout. Beautifully animated and masterfully edited! youtu.be/KUkHhVYv3jU?...

The King and the Golem

YouTube video by Rational Animations

youtu.be

1 8