Review: The Intelligence Explosion: When AI Beats Humans at Everything
|

Review: The Intelligence Explosion: When AI Beats Humans at Everything

When the machines outthink us, will they outmaneuver us? Barrat’s latest is a wake-up call we can’t afford to ignore. Having had the privilege of previewing James Barrat’s latest work, The Intelligence Explosion (Amazon link, Google Book link), I found it to be a compelling and thought-provoking exploration of the rapidly evolving landscape of artificial…

AI Safety in Education: Preparing the Next Generation for Responsible AI Development

AI Safety in Education: Preparing the Next Generation for Responsible AI Development

About Artificial intelligence is rapidly transforming industries, yet discussions around AI safety oftenremain confined to research labs and policy circles. What happens when the next generation ofAI engineers and decision-makers lacks the knowledge to build AI systems that are safe, ethical,and aligned with human values? Despite the growing importance of AI safety – AI safety,…

On the Emergence of Biased Coherent Value Systems in AI as Value Risk
|

On the Emergence of Biased Coherent Value Systems in AI as Value Risk

Firstly, values are important because they are the fundamental principles that guide decisions and actions in humans. They shape our understanding of right and wrong, and they influence how we interact with the world around us. In the context of AI, values are particularly important because they determine how AI systems will behave, what goals…

Capability Control vs Motivation Selection: Contrasting Strategies for AI Safety
|

Capability Control vs Motivation Selection: Contrasting Strategies for AI Safety

Capability Control: The Tool or Slave Model Capability control focuses on limiting what an AI can do, rather than shaping why it does it. The idea is to ensure AI systems behave predictably and stay within strict bounds – like a powerful but obedient tool. This includes: In this model, the AI is treated less…

Singular Learning Theory with Jesse Hoogland
| | |

Singular Learning Theory with Jesse Hoogland

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…

The AI Safety Dynamic – Dr Simon Goldstein
| | |

The AI Safety Dynamic – Dr Simon Goldstein

Dr Simon Goldstein is an associate professor at the Dianoia Institute of Philosophy at ACU. In 2023, he is a research fellow at the Center for AI Safety. Simon’s research focuses on AI safety, epistemology, and philosophy of language. Before ACU, Simon was an assistant professor at Lingnan University in Hong Kong. Simon received my…

Stuart Armstrong on AI Interpretability, Accidental Misalignment & Risks of Opaque AI
| | | |

Stuart Armstrong on AI Interpretability, Accidental Misalignment & Risks of Opaque AI

Interview with Stuart Armstrong (Aligned AI) Video / Audio of interview will be up soon To watch interview live, join the zoom call: Time: Nov 9, 2022 07:30 PM Canberra, Melbourne, SydneyJoin Zoom Meetinghttps://us02web.zoom.us/j/81320547208?pwd=MGFnZ2RGcFl5cW9aZ1BaUm5qcnh1UT09Meeting ID: 813 2054 7208Passcode: scifuture Auditing and interpreting AI (and their models) seems obviously important to achieve verifiably safe AI (by…

What do we Need to Do to Align AI? – Stuart Armstrong
| | | |

What do we Need to Do to Align AI? – Stuart Armstrong

Synopsis: The goal of Aligned AI is to implement scalable solutions to the alignment problem, and distribute these solutions to actors developing powerful transformative artificial intelligence. What is Alignment? Algorithms are shaping the present and will shape the future ever more strongly. It is crucially important that these powerful algorithms be aligned – that they…