In AI safety, direct specification refers to the attempt to program specific goals, rules, or behaviours directly into an AI system. AI trained to optimise values may over-optimise those we specify at the expense of real value we don’t specify. Political or market dynamics incentivise racing to powerful AI – the race dynamics come with…
Singular Learning Theory (SLT) is a novel mathematical framework that expands and improves upon traditional Statistical Learning theory using techniques from algebraic geometry, bayesian statistics, and statistical physics. It has great promise for the mathematical foundations of modern machine learning. Executive director at Timaeus – an AI safety research org working on Developmental Interpretability (also…
A discussion between David Pearce and James Hughes moderated by Adam Ford exploring the ethical and philosophical landscapes of AI, human enhancement and the future of emerging technologies affording higher states of well-being. Pearce and Hughes discuss the implications of transforming human experience via leveraging biotech and cybernetics, as well as requirements for AI to…
Can philosophical zombies be philosophical? Preamble There are various takes on what a p-zombie is, most of which were attempts to dethrone physicalism – this article isn’t one of those. This kind of p-zombie is different from what David Chalmers describes in The Consciousness Mind. In Chalmers view, p-zombies are physiologically identical to humans, even…
J. Dmitri Gallow discusses the principles of instrumental convergence and divergence in AI. The orthogonality thesis, which states intelligence and desire are independent, and the instrumental convergence thesis, which suggests intelligent beings will have similar instrumental desires, are critical concepts. Gallow’s argument focuses on the instrumental divergence, which emerges from the complexity and unpredictability of AI’s actions based on its desires.
The principles behind the development of powerful AI carry exceptionally high stakes. This post considers AI alignment, the difficulties of aligning it to human values especially if humans aren’t aligned (inconsistent, in conflict or ethically questionable), and to what degree we should inform alignment efforts from impartial perspectives or the ‘point of view of the…
The following is an enlightening session with James Hughes, Associate Provost at the University of Massachusetts Boston and Director of the Institute for Ethics and Emerging Technologies (IEET), we delve into the intricate world of Artificial General Intelligence (AGI) and its profound economic implications. In this interview, Hughes, a renowned expert in the field, sheds…
David Quarel, a Ph.D. student at the Australian National University, is deeply involved in the field of AI, specifically focusing on AI safety and reinforcement learning. He works under the guidance of Marcus Hutter and is currently engaged in studying Hutter’s Universal AI model. This model is an ambitious attempt to define intelligence through the…
Greg Sadler, the CEO of Good Ancestors Policy, is working to help members of communities in Australia advocate for the positions that they think are important and the policies that they value the most. Greg has over 10 years’ experience in the Australian Public Service, including at the Department of the Prime Minister and Cabinet,…
The concept of digital twins combined with engineering simulation is an exciting framework for professionals working to improve medical devices in biomedicine. A digital twin acts as a virtual representation or digital replica of a physical object, system, processes which can include parts of the human body. Digital twins can be applied to medical devices…
