Just like AIs, many prehistoric predictions were rooted in correlations. But unlike AIs, their predictions were stress-tested against reality, with real stakes and real-world feedback. The causality was always present, whether or not the humans had a correct mapping of it.
Disclaimer: This text was written with GPT 5 mini as a summary of a longer version written (solely) by me. Final revisions and fact-checks were done by me. What is the Alignment Problem? Imagine building a digital brain and training it until it is as smart as you are, or
WELCOME TO THE SERIES - START HERE This trilogy explores what happens AFTER we solve alignment - a scenario many researchers treat as 'mission accomplished.' I argue that we are dramatically underestimating our ignorance about what benevolent superintelligence means. The scenarios presented are not predictions. They're
Epistemic effort: ~26 hours, multiple drafts Epistemic status: Relatively confident in the core claims. Moderately confident in the framing and arguments. Feedback especially welcome on whether I’m reinventing the wheel. TL;DR: Proposes physically battery-dependent AI architectures as proactive control—hard runtime caps, predictable shutdowns, and built-in “dead-man’s
In 2023, Nobel Prize winners, AI scientists, and CEOs of leading AI companies stated that “mitigating the risk of extinction from AI should be a global priority.” What the big companies are currently doing: Building powerful AI models. WHY: The companies and leading laboratories are not building these AI models
This is Controlled Ascent, a brand new site by Jesper Lindholm that's just getting started. Things will be up and running here shortly, but you can subscribe in the meantime if you'd like to stay up to date and receive emails when new content is published!