Speaker: Prof Herman Cappelen, The University of Hong Kong Abstract: This paper makes three main claims: 1) There is no universal set of core values for AI systems to align with – moral disagreements run too deep. 2) The increased causal potency that creates the problem of AI risk also implies that imperfect safety mechanisms …
The Dangers and (potential) Incoherence of AI Alignment Read More »
Speaker: Prof Darrell Rowbottom, Lingnan University Abstract: According to the standard no miracles argument, science’s predictive success is best explained by the approximate truth of its theories. In contemporary science, however, machine learning systems, such as AlphaFold2, are also remarkably predictively successful. Thus, we might ask what best explains such successes. Might these AIs accurately …
Speaker: Dr Abelard Podgorski, The National University of Singapore Abstract: There is a choice point in ethics between theories which care about whether our actions make the world impersonally better or worse, and theories which care about whether our actions are better or worse for particular individuals. The distinction has important implications for issues in …
Date & Time: Mar 1, 2024 (Fri), 4:00 – 6:30 pmMar 2, 2024 (Sat), 9:30 am – 6:30 pm Programme Rundown: here AI, Music, and Creativity: At a Crossroads is an international symposium jointly hosted by the HKU Department of Music and the AI & Humanity Lab at the Department of Philosophy. This event is a …
AI, Music, and Creativity: International Symposium & 2023/24 Rayson Huang Lectures Read More »
Speaker: Dr Dan Hendrycks, Centre for AI Safety Abstract Dr Hendrycks will discuss principles for measuring capabilities of AI systems, and walk through popular general capabilities benchmarks. He will then discuss how general capabilities can be separated from the measurement of their safety, then overview new ways to measure safety.
Date: February 20, 2024 (Tuesday) Speaker: Prof William Lucy, Durham University Law School Chair: Prof Scott Veitch, The University of Hong Kong
Date: March 8, 2024 (Friday) Speaker: Prof Song Fei, Lingnan University Chair: Dr Frank Hong, The University of Hong Kong Abstract: In the literature on trustworthy AI, there are two main positions. The first view is in order to illuminating trustworthy AI, we need a general account of trust and trustworthiness, which is less anthropocentric. Because …
A Network Account of Trustworthy AI: A New Framework Read More »
“YouTube, Facebook, X (formerly Twitter), Instagram, Pinterest, TikTok, and chatbots like ChatGPT and Bard—all of them have the power to manipulate you ……..” Check out this recent paper written by Rachel Sterken, our Department Head of Philosophy at The University of Hong Kong, along with Jessica Pepp and Eliot Michaelson. Read the full article here
Speaker: Duan Yawen, Concordia AI Background readings: Model evaluation for extreme risks Sociotechnical Safety Evaluation of Generative AI Systems Emerging Processes for Frontier AI Safety OpenAI Preparedness Framework
Speaker: Dr Peter Salib, The University of Houston Abstract: Assume that we succeed in crafting effective safety benchmarks for frontier AI systems. By “effective,” I mean benchmarks that are both aimed at measuring the riskiest capabilities and able to reliably measure them. It would then seem sensible to integrate those benchmarks into safety laws governing …