Subvolts take AI achieves math gold medals using verified proofs, pointing to trustworthy superintelligence by 2030. Feb 18, 2026 - Developers
- Learn about using formal verification and advanced AI techniques for building robust mathematical reasoning systems.
- Business
- Understand how verifiable AI could enhance mission-critical software and lead to more trustworthy AI applications.
This interview details a significant AI achievement in mathematics, potentially paving the way for more reliable and trustworthy AI systems.
Mathematical Superintelligence: Harmonic's Vlad Tenev & Tudor Achim on IMO Gold & Theories of Everything
Audio streams from Erik Torenberg, Nathan Labenz. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Vlad Tenev and Tudor Achim from Harmonic discuss their AI system, Aristotle, which achieves International Mathematical Olympiad gold-medal performance using verified Lean proofs. They detail the architecture behind mathematical superintelligence, including Monte Carlo Tree Search and lemma guessing. The conversation explores how verifiable reasoning could enhance software reliability and lead to trustworthy superintelligent systems by 2030.
This episode explains how an AI system called Aristotle uses special computer proofs to solve hard math problems, like those in a top competition. This could make AI systems more reliable for important tasks and help build safer, smarter AI in the future.
This episode delves into the cutting edge of AI's mathematical capabilities, showcasing a system that uses formal verification for high-stakes problem-solving. It's for AI researchers, developers, and anyone interested in the path to superintelligence. The focus on verifiable reasoning and trustworthy AI connects directly to current efforts in AI safety and reliability across major labs like Anthropic and Google Gemini, who are all exploring ways to make AI systems more robust and dependable.
- HostNathan Labenz
- GuestVlad TenevHarmonic
- GuestTudor AchimHarmonic
- Episode Title: Mathematical Superintelligence: Harmonic's Vlad Tenev & Tudor Achim on IMO Gold & Theories of Everything
- Show: The Cognitive Revolution
- Length: 91 minutes
- AI Performance: International Mathematical Olympiad gold-medal performance
- AI System: Aristotle
- Technology Used: Formally verified Lean proofs, Monte Carlo Tree Search, lemma guessing, specialized geometry modules
Vlad Tenev and Tudor Achim from Harmonic explain how they built Aristotle, an AI system that reaches International Mathematical Olympiad gold-medal performance using formally verified Lean proofs. They unpack the architecture behind mathematical superintelligence, including Monte Carlo Tree Search, lemma guessing, and specialized geometry modules. The conversation explores how verifiable reasoning could harden mission-critical software, reshape mathematical practice, and lead to trustworthy superintelligent systems by 2030.
Nathan uses Granola to uncover blind spots in conversations and AI research. Try it at granola.ai/tcr with code TCR — and if you’re already using it, test his blind spot recipe here: https://bit.ly/granolablindspot
Sponsors:
Claude:
Claude is the AI collaborator that understands your entire workflow, from drafting and research to coding and complex problem-solving. Start tackling bigger problems with Claude and unlock Claude Pro’s full capabilities at https://claude.ai/tcr
Framer:
Framer is an enterprise-grade website builder that lets business teams design, launch, and optimize their.com with AI-powered wireframing, real-time collaboration, and built-in analytics. Start building for free and get 30% off a Framer Pro annual plan at https://framer.com/cognitive
Blitzy:
Blitzy is the autonomous code generation platform that ingests millions of lines of code to accelerate enterprise software development by up to 5x with premium, spec-driven output. Schedule a strategy session with their AI solutions consultants at https://blitzy.com
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
CHAPTERS:
(00:00) About the Episode
(04:58) Math as reasoning (Part 1)
(15:22) Sponsors: Claude | Framer
(18:51) Math as reasoning (Part 2)
(18:51) Inside the Lean language
(27:51) Lean intuition and MathLib (Part 1)
(34:08) Sponsors: Blitzy | Tasklet
(37:08) Lean intuition and MathLib (Part 2)
(38:47) Inside Aristotle's architecture
(48:33) Scope, boundaries, and applications
(54:37) Training, taste, and interpretability
(01:08:18) Formal math and software
(01:16:50) Limits, entropy, and roadmap
(01:25:24) 2030 vision and safety
(01:33:38) Outro
PRODUCED BY:
- Lean proofs
- Tudor Achim
- Computer-verified mathematical steps that guarantee correctness.
- Monte Carlo Tree Search
- Tudor Achim
- A method for making decisions in AI by exploring many possibilities.
- Lemma guessing
- Tudor Achim
- AI predicting useful intermediate steps to solve a larger problem.
1 h 27AI:AM: Where's the Steering Wheel? My Agent Set the Password, Hidden Valence, Proofs Find Linux Bugs
WithCameron Berg, Everett Hildenbrandt, Grigore Rosu, Phil Maher
2 h 192 h 021 h 28AI:AM: A Level We Shouldn't Pass? Notes from The Curve + Tokens vs. Salaries & Is SaaS Cooked?
WithThomas Sohmers, swyx, Evan Miyazono, Edward Hu
Same guests, other shows
58 minAI’s Capital Flywheel: Models, Money, and the Future of Power
WithMartin Casado, Sarah Wang
55 min1 h 04Durable Execution and the Infrastructure Powering AI Agents
WithSamar Abbas
Questions people ask
- What is Aristotle?
- Aristotle is an AI system developed by Harmonic that achieves International Mathematical Olympiad gold-medal performance using formally verified Lean proofs.
- What is Monte Carlo Tree Search?
- Monte Carlo Tree Search is a component of the architecture behind mathematical superintelligence discussed in the episode.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Erik Torenberg, Nathan Labenz.