Leonard Dung

According to our database, Leonard Dung authored at least 7 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of six.
• Erdős number of five.

2025

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare.

Valen Tagliabue, Leonard Dung

CoRR, September, 2025

Against racing to AGI: Cooperation, deterrence, and catastrophic risks.

Leonard Dung, Max Hellrigel-Holderbaum

CoRR, July, 2025

Misalignment or misuse? The AGI alignment tradeoff.

Max Hellrigel-Holderbaum, Leonard Dung

CoRR, June, 2025

Evaluating approaches for reducing catastrophic risks from AI.

Leonard Dung

AI Ethics, April, 2025

How to Live in the Moment: The Methodology and Limitations of Evolutionary Research on Consciousness.

Christian R. de Weerd, Leonard Dung

Cogn. Sci., March, 2025

The argument for near-term human disempowerment through AI.

Leonard Dung

AI Soc., March, 2025

2022

Why the Epistemic Objection Against Using Sentience as Criterion of Moral Status is Flawed.

Leonard Dung

Sci. Eng. Ethics, 2022