Subvolts take Secure AI systems use formal methods for verifiable safety and policy compliance. Dec 24, 2025 - Developers
- Learn how formal methods can harden your code and improve AI agent compliance.
- Business
- Understand how to secure critical infrastructure against AI cyberattacks using verifiable methods.
This interview features experts discussing practical applications of formal methods for AI security and compliance.
The Great Security Update: AI ∧ Formal Methods with Kathleen Fisher of RAND & Byron Cook of AWS
Audio streams from Erik Torenberg, Nathan Labenz. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Kathleen Fisher of RAND and Byron Cook of AWS discuss using automated reasoning and formal verification to build secure software. They explore hardening critical infrastructure against AI cyberattacks, training coding models, and powering AWS automated reasoning checks for AI agents and policy compliance. The episode covers how assumptions, specifications, and proofs deliver security guarantees.
This episode explains how computer scientists use math to prove software is safe and does what it is supposed to do. This is important for protecting critical systems from AI-powered attacks and ensuring AI obeys rules.
This episode offers insights into making AI systems more secure through formal methods, a critical area for AI safety. It is for AI builders, security professionals, and anyone concerned about AI governance. The discussion on hardening infrastructure and ensuring policy compliance directly relates to current efforts by frontier labs like Google Gemini and Microsoft Copilot to build trustworthy AI.
- HostNathan Labenz
- GuestKathleen FisherRAND
- GuestByron CookAWS
- Episode Title: The Great Security Update: AI ∧ Formal Methods
- Show: The Cognitive Revolution
- Length: 99 minutes
- Guest Organization: RAND
- Guest Organization: AWS
- Fellowship Mentioned: MATS Summer 2026 Fellowship
Kathleen Fisher and Byron Cook dive into automated reasoning and formal verification as tools for building truly secure software systems. PSA for AI builders: Interested in alignment, governance, or AI safety? Learn more about the MATS Summer 2026 Fellowship and submit your name to be notified when applications open: https://matsprogram.org/s26-tcr. They explain how formal methods can harden critical infrastructure against AI-enabled cyberattacks, and how assumptions, specifications, and proofs combine to deliver real security guarantees. The conversation explores using these techniques to train coding models, enable a “great software rewrite,” and power AWS’s new automated reasoning checks for AI agents and policy compliance.
Sponsors:
MATS:
MATS is a fully funded 12-week research program pairing rising talent with top mentors in AI alignment, interpretability, security, and governance. Apply for the next cohort at https://matsprogram.org/s26-tcr
Tasklet:
Tasklet is an AI agent that automates your work 24/7; just describe what you want in plain English and it gets the job done. Try it for free and use code COGREV for 50% off your first month at https://tasklet.ai
Agents of Scale:
Agents of Scale is a podcast from Zapier CEO Wade Foster, featuring conversations with C-suite leaders who are leading AI transformation. Subscribe to the show wherever you get your podcasts
Shopify:
Shopify powers millions of businesses worldwide, handling 10% of U.S. e-commerce. With hundreds of templates, AI tools for product descriptions, and seamless marketing campaign creation, it's like having a design studio and marketing team in one. Start your $1/month trial today at https://shopify.com/cognitive
CHAPTERS:
(00:00) About the Episode
(04:52) AI Reshapes Cybersecurity
(10:16) Formal Methods Foundations
(17:46) Security Properties Assumptions (Part 1)
(21:27) Sponsors: MATS | Tasklet
(24:27) Security Properties Assumptions (Part 2)
(28:31) Helicopter Formal Verification
(38:15) Proof Confidence And AWS (Part 1)
(41:52) Sponsors: Agents of Scale | Shopify
(44:40) Proof Confidence And AWS (Part 2)
(50:33) Automated Reasoning For Policies
(01:04:39) Generative AI Meets Verification
(01:19:42) Securing Future AI Systems
(01:31:19) Agentic Guardrails And Governance
(01:40:44) Outro
PRODUCED BY:
SOCIAL LINKS:
Website: https://www.cognitiverevolution.ai
Twitter (Podcast): https://x.com/cogrev_podcast
Twitter (Nathan): https://x.com/labenz
LinkedIn: https://linkedin.com/in/nathanlabenz/
Youtube: https://youtube.com/@CognitiveRevolutionPodcast
Apple: WithCameron Berg, Everett Hildenbrandt, Grigore Rosu, Phil Maher WithThomas Sohmers, swyx, Evan Miyazono, Edward Hu Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Erik Torenberg, Nathan Labenz.1 h 27AI:AM: Where's the Steering Wheel? My Agent Set the Password, Hidden Valence, Proofs Find Linux Bugs
2 h 192 h 021 h 28AI:AM: A Level We Shouldn't Pass? Notes from The Curve + Tokens vs. Salaries & Is SaaS Cooked?
Questions people ask
