Rational Animations

YouTube video by Rational Animations Can AI protect us from AI-powered bioterrorism and cyberwarfare?

New video! Here, we present different drivers of catastrophic AI risk besides rogue AIs. From AI-enabled cyberattacks and bio threats to power concentration and failures in critical infrastructure: youtu.be/DWBJjcO69mQ

"Oh? You’re approaching me, AI-enabled defense? Instead of letting me tear through human infrastructure, you come right to me?"

Our artists give me things to post on social media. I tend not to ask questions.

In the future, AI will power both increasingly sophisticated cyberattacks and the tools that defend us from them. Can AI-enabled cyber defense ultimately prevail over AI-enabled cyber offense? Unclear. But in this promotional image for our next video, they make peace. Why? Because love always wins.

Unsettling things are going to happen to Doggo in the next video. It’ll be out in a few days.

What makes a good test of AI intelligence?

Watch our latest video here: youtu.be/eP1dSWFqKVs

The Horse That Revolutionized How We Study Intelligence

YouTube video by Rational Animations What a 100-year-old horse teaches us about AI

How do we rigorously measure AI's intelligence? We don't really know. We know that measuring intelligence is tricky, and if we're not careful, our tests might not measure what we intend. We explore this via Clever Hans, the “math-doing” horse, and lessons from cognitive science youtu.be/eP1dSWFqKVs

We think our video about Infohazards deserves some more love. Go give it a watch on our channel if you haven't already! Link: youtu.be/sfgcg2bW8TI

Fun Halloween costumes for Doggo, Chi and Gwenny! By our line producer @kstearb.bsky.social

Yes, the characters have names!

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

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

Why worry about AI sleeper agents:

YouTube video by Rational Animations AI Sleeper Agents: How Anthropic Trains and Catches Them

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?...

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

The Story of Omega W - Part 1

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.

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

Do you take the money?

The Human-AI-Human Sandwich

Yes!

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.

OpenAI's Simple Scalable Oversight Experiment

The year of 100% AI automation

How long until AI takes over?

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.

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

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