Rational Animations is a fully remote international team of about 40 artists, writers, and tech dorks collaborating together. We are fans of dogs, stories, animation, learning, and doing good.
With our YouTube channel, we aim to promote good-thinking, altruistic causes and help ensure humanity’s future goes well. Among these topics, we are particularly focused on AI Safety and AI Alignment: making sure present and future AI Systems are aligned with human values and don’t cause our extinction.
We also offer animation production and writing services. Don’t hesitate to contact us!
From Rational Animations. In this video, we walk you through a plausible scenario in which AI could lead to humanity’s extinction. There are many alternative possibilities, but this time we focus on superhuman AIs developing misaligned personas, similar to how Microsoft’s Bing Chat developed the misaligned “Sydney” persona shortly after its release. ▀▀▀▀▀▀▀▀▀SOURCES & READINGS▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀…
From Rational Animations. In the future, AIs will likely be much smarter than we are. They’ll produce outputs that may be difficult for humans to evaluate, either because evaluation is too labor-intensive, or because it’s qualitatively hard to judge the actions of machines smarter than us. This is the problem of “scalable oversight.” Proposed solutions…
From Rational Animations. Economist Tom Davidson’s 2023 “compute-centric” model answers two questions: when could AI automate all current cognitive labor, and how fast might that transition happen? Davidson’s model considers the resources required to train increasingly capable AI systems (compute × algorithmic efficiency) and the rate at which these resources grow. Simulating the model suggests…