Kayvon Beykpour on Microsoft-Scale Inference, Macroscope, and Tokens as a Vanity Metric | MTS Live
Episode description
Kayvon Beykpour joins MTS to discuss token efficiency in engineering organizations, AI-powered code review systems, and building tools for code-based understanding at scale.
--
--
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:
Granola - The AI notepad. Try it once and never go back. https://granola.ai/mts
Kong - The AI connectivity platform. Connect APIs, LLMs, agents, and systems with serious security and governance. https://konghq.com
Blitzy - Autonomous software development for enterprise codebases. Ship 5x faster. https://blitzy.com
Merge - OpenAI, Dropbox, and Ramp use Merge to get AI to production faster. https://merge.dev/mts
AdQuick - Make your brand a billboard. Out-of-home advertising as easy to scale as digital. https://adquick.com
Macroscope - AI codebase understanding for engineering leaders. https://macroscope.com/mts
–
Timestamps:
(00:00) Introduction
(01:19) Token Maxing and Efficiency
(03:30) What Macroscope Does
(05:07) High Signal Code Review
(08:23) Origin Story and Twitter Experience
(10:46) Code as Source of Truth
–
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.