Iason Gabriel: Value Alignment and the Ethics of Advanced AI Systems

Episode 143
I spoke with Iason Gabriel (iasongabriel.com) about:
* Value alignment
* Technology and worldmaking
* How AI systems affect individuals and the social world
Iason is a philosopher and Senior Staff Research Scientist at Google DeepMind. His work focuses on the ethics of artificial intelligence, including questions about AI value alignment (link.springer.com/article/10.1007/s11023-020-0…), distributive justice (direct.mit.edu/daed/article/151/2/218/110610/T…), language ethics (arxiv.org/abs/2209.00731) and human rights (arxiv.org/abs/2210.02667).
You can find him on his website (iasongabriel.com) and Twitter (x.com/IasonGabriel)/X.
Find me on Twitter (twitter.com/spaniel_bashir) (or LinkedIn (linkedin.com/in/daniel-bashir) if you want…) for updates, and reach me at editor@thegradient.pub for feedback, ideas, guest suggestions.
Outline
* (00:00) Intro
* (01:18) Iason’s intellectual development
* (04:28) Aligning language models with human values, democratic civility and agonism
* (08:20) Overlapping consensus, differing norms, procedures for identifying norms
* (13:27) Rawls’ theory of justice, the justificatory and stability problems
* (19:18) Aligning LLMs and cooperation, speech acts, justification and discourse norms, literacy
* (23:45) Actor Network Theory and alignment
* (27:25) Value alignment and Iason’s starting points
* (33:10) The Ethics of Advanced AI Assistants, AI’s impacts on social processes and users, personalization
* (37:50) AGI systems and social power
* (39:00) Displays of care and compassion, Machine Love (Joel Lehman)
* (41:30) Virtue ethics, morality and language, virtue in AI systems vs. MacIntyre’s conception in After Virtue
* (45:00) The Challenge of Value Alignment
* (45:25) Technologists as worldmakers
* (51:30) Technological determinism, collective action problems
* (55:25) Iason’s goals with his work
* (58:32) Outro
Links
Papers:
* AI, Values, and Alignment (link.springer.com/article/10.1007/s11023-020-0…) (2020)
* Aligning LMs with Human Values (link.springer.com/article/10.1007/s13347-023-0…) (2023)
* Toward a Theory of Justice for AI (watermark02.silverchair.com/daed_a_01911.pdf?t…) (2023)
* The Ethics of Advanced AI Assistants (arxiv.org/abs/2404.16244) (2024)
* A matter of principle? AI alignment as the fair treatment of claims (link.springer.com/article/10.1007/s11098-025-0…) (2025)

Get full access to The Gradient at thegradientpub.substack.com/subscribe?utm_medi…