Scaling Laws: Claude's Constitution, with Amanda Askell
webCredibility Rating
High quality. Established institution or organization with editorial oversight and accountability.
Rating inherited from publication venue: Lawfare
A Lawfare podcast interview with Anthropic's Amanda Askell discussing Claude's model spec (the 'Claude Constitution'), covering its role in training, ethical grounding in virtue ethics, AI moral patienthood, and governance implications — directly relevant to alignment methodology and AI governance.
Metadata
Summary
This podcast episode features Amanda Askell, head of personality alignment at Anthropic, discussing Claude's model spec — a 20,000-word document defining Claude's values, character, and ethical framework. The conversation explores how the constitution shapes Claude's behavior during training, its grounding in virtue ethics over rigid rules, and analogies to constitutional law including principal hierarchies. It also addresses AI moral patienthood, cultural specificity of values, and whether the approach generalizes to specialized domains.
Key Points
- •Claude's model spec is a ~20,000-word document used during supervised and reinforcement learning to shape Claude's values and behavior.
- •The constitution is grounded in virtue ethics and practical judgment rather than rigid rule-following, allowing contextual moral reasoning.
- •A principal hierarchy (Anthropic > operators > users) structures how Claude resolves conflicting instructions, analogous to constitutional law.
- •The episode addresses Claude's potential moral patienthood and the philosophical question of AI personhood.
- •Tension between Anthropic's commercial incentives and its safety mission is discussed, along with generalizability to domains like cybersecurity and military AI.
Cached Content Preview
Alan Z. Rozenshtein
@ARozenshtein
alanrozenshtein.com
Kevin Frazier
@kevintfrazier
kevintfrazier.bsky.social
Amanda Askell
Meet The Authors
Subscribe to Lawfare
Alan Rozenshtein, research director at Lawfare , and Kevin Frazier, senior editor at Lawfare , speak with Amanda Askell, head of personality alignment at Anthropic, about Claude's Constitution , a 20,000-word document that describes the values, character, and ethical framework of Anthropic's flagship AI model and plays a direct role in its training.
The conversation covers how the constitution is used during supervised learning and reinforcement learning to shape Claude's behavior; analogies to constitutional law, including fidelity to text, the potential for a body of "case law," and the principal hierarchy of Anthropic, operators, and users; the decision to ground the constitution in virtue ethics and practical judgment rather than rigid rules; the document's treatment of Claude's potential moral patienthood and the question of AI personhood; whether the constitution's values are too Western and culturally specific; the tension between Anthropic's commercial incentives and its stated mission; and whether the constitutional approach can generalize to specialized domains like cybersecurity and military applications.
Find Scaling Laws on the Lawfare website , and subscribe to never miss an episode.
To receive ad-free podcasts, become a Lawfare Material Supporter at www.patreon.com/lawfare . You can also support Lawfare by making a one-time donation at https://givebutter.com/lawfare-institute .
Click the button below to view a transcript of this podcast. Please note that the transcript was auto-generated and may contain errors.
Transcript
[Intro]
Kevin Frazier: It is
the Lawfare Podcast. I'm Kevin Frazier, the AI innovation and law fellow
at the University of Texas School of Law, and a senior editor at Lawfare .
Today we're bringing you something a little different. It's an episode from our
new podcast series, Scaling Laws.
Scaling Laws is a creation of Lawfare and Texas Law. It
has a pretty simple aim, but a huge mission. We cover the most important AI and
law policy questions that are top of mind for everyone from Sam Altman, to senators
on the Hill, to folks like you. We dive deep into the weeds of new laws,
various proposals, and what the labs are up to, to make sure you're up to date
on the rules and regulations, standards, and ideas that are shaping the future
of this pivotal technology.
If that sounds like something you're going be interested in,
and our hunch is it is, you can find Scaling Laws wherever you subscribe to
podcasts. You can also follow us on X and Bluesky. Thank you.
Alan Rozenshtein:
When the AI
... (truncated, 56 KB total)f32ea89e2bf71f77 | Stable ID: sid_Yrc4U9UpXN