The Story of Omega W - Part 2 (full video on our channel!)
10.08.2025 17:11 β π 2 π 1 π¬ 0 π 0@rationalanimations.bsky.social
YouTube channel about truth-seeking, the future of humanity, and much more. With animations and colorful doggos -> https://www.youtube.com/rationalanimations
The Story of Omega W - Part 2 (full video on our channel!)
10.08.2025 17:11 β π 2 π 1 π¬ 0 π 0The Story of Omega W - Part 1
04.08.2025 17:16 β π 3 π 1 π¬ 0 π 1A 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):
24.07.2025 17:04 β π 1 π 0 π¬ 0 π 0Do you take the money?
23.07.2025 17:03 β π 1 π 0 π¬ 0 π 0The Human-AI-Human Sandwich
17.07.2025 17:06 β π 2 π 0 π¬ 0 π 0Yes!
16.07.2025 20:35 β π 1 π 0 π¬ 0 π 0See 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.
16.07.2025 17:03 β π 4 π 1 π¬ 1 π 0OpenAI's Simple Scalable Oversight Experiment
13.07.2025 17:01 β π 6 π 0 π¬ 0 π 0The year of 100% AI automation
20.06.2025 17:05 β π 1 π 0 π¬ 0 π 0How long until AI takes over?
13.06.2025 17:01 β π 2 π 0 π¬ 0 π 0We 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.
19.05.2025 17:05 β π 3 π 0 π¬ 0 π 0After artificial superintelligence, AI will bump against the only limit left: the laws of physics. At the moment, we're nowhere near those limits.
17.05.2025 17:03 β π 2 π 0 π¬ 0 π 0Once we have AGIs, we'll likely get ASI (artificial superintelligence) quite soon. Here's why.
15.05.2025 15:17 β π 2 π 0 π¬ 0 π 1Once 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.
13.05.2025 17:04 β π 3 π 1 π¬ 0 π 0In the near future, AIs will likely be able to do everything humans can do on a computer. In short, they'll be AGIs.
11.05.2025 17:03 β π 4 π 0 π¬ 0 π 0We're still quite bad at aligning AI. Our techniques today are imperfect, which might prove catastrophic when AIs become superintelligences.
09.05.2025 17:06 β π 4 π 0 π¬ 0 π 0If 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.
07.05.2025 17:03 β π 4 π 1 π¬ 0 π 0Hi Bluesky! Here is a YouTube short from @rationalanimations.bsky.social that I was the #animation director on! Itβs about Instrumental Convergence of artificial intelligence, check it out here! youtube.com/shorts/dYAaq...
04.12.2024 00:07 β π 11 π 1 π¬ 1 π 2Another 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?...
05.12.2024 00:18 β π 7 π 1 π¬ 0 π 0The Goddess of Everything Else
#SketchDump
Thank you so much you two!
19.11.2024 08:11 β π 6 π 0 π¬ 0 π 0Goddess of Everything Else commission for @generalspritz.bsky.social
Based on the short by @rationalanimations.bsky.social, which was in turn based on the short story by Scott Alexander.