Theorem co-founders Jason Gross and Rajashri Agarwal discuss how formal verification can make AI-generated code safer and enable inescapable agent sandboxes. They break down why traditional proof assistants fail to scale and reveal their strategy to hide formal verification under standard developer workflows. Check out our sponsor Lovable: https://lovable.dev. Turn ideas into software people love.

MTS is a live news and interview show covering technology, business, politics, and culture as it happens.

Follow MTS:

X | ⁠https://twitter.com/MTSlive⁠

YouTube | ⁠https://www.youtube.com/@mtsituation⁠

Spotify | ⁠https://open.spotify.com/show/4HUNNmV1pjV7CW6Lphm1rM⁠

Apple | ⁠https://podcasts.apple.com/us/podcast/mts/id1891088763⁠

Substack | ⁠https://mtslive.substack.com/⁠

Interested in sponsoring the show? ⁠⁠⁠⁠⁠⁠sponsors@mts.now⁠⁠

--

Brought to you by:

Mongo DB - Anyone can prototype an agent. Learn how to get them into production on September 30th in New York - register at https://www.mongodb.com/events/mongodb-local/nyc

Lovable - Turn ideas into software people love with Lovable. Start today at https://lovable.dev/

Larridin - Finally prove what your AI investment is worth. Head to https://larridin.com/ today to start measuring your AI’s bottom line.

Neon (by Databricks) - Get up to $100K in credits for your startup at ⁠https://neon.com/mts⁠

ElevenLabs - AI that communicates at human level across every channel and modality. https://elevenlabs.io/mts

Arena - Measuring AI performance in the real world. ⁠https://arena.ai/⁠

Kong - The AI connectivity platform. Connect APIs, LLMs, agents, and systems with serious security and governance. https://konghq.com

Today’s stream is sponsored by VCX, the public ticker for private tech. Head over to http://getvcx.com to learn more

Blitzy - Autonomous software development for enterprise codebases. Ship 5x faster. https://blitzy.com

AdQuick - Make your brand a billboard. Out-of-home advertising as easy to scale as digital. https://adquick.com

Chargebee - Billing and monetization infrastructure for the AI era. https://www.chargebee.com/

--

Timestamps:

(00:00) Introduction

(00:00) What Formal Verification Actually Means

(02:17) Why Model Verification Fails to Scale

(07:37) The Real Bottleneck in Formal Verification

(10:14) Hiding Formal Verification From Developers

(12:14) Building Inescapable AI Agent Sandboxes

(21:03) Asymmetric Cybersecurity and AI Alignment

--

Note: This podcast is not investment, legal, or tax advice, and is intended for informational and entertainment purposes only. Hosts and guests may hold positions in the companies and securities discussed; do your own research before acting on anything you hear.

How Formal Verification Stops AI Reward Hacking | Theorem

MTS

How Formal Verification Stops AI Reward Hacking | Theorem