Crazy Wisdom
Episode #543: The Year of Agents and the Industries Not Ready for Them
- AI & Agents
- Money & Sovereignty
- Crypto & Decentralization
- Crazy Wisdom Podcast
- Mauro Schilman
- Tuki Travel
- CTO
- traveling
- culture
- math
- Olympiads
About this episode
Timestamps
- 00:00Stewart welcomes Mauro Schilman, CTO and Co-founder of Tuki Travel, who shares how traveling since age 15 through high school exchanges opened his mind to cultural similarities and differences.
- 05:00Mauro explains Math Olympiad coaching culture and mentorship, noting LLMs now solve competition-level problems while Terence Tao explores AI assisting frontier unsolved mathematics.
- 10:00Discussion turns to ChatGPT revealing Mauro's birthdate unprompted, exposing opaque application layers, preference tuning, and system prompts hidden within closed models.
- 15:00Mauro argues true open source AI requires full training data, annotation protocols, and alignment processes, not just model weights, while scaling laws appear to be slowing.
- 20:00Hierarchical memory models replace flat vector databases, using three-level retrieval systems improving context accuracy as knowledge management becomes AI's core challenge.
- 25:00Mauro describes travel's fragmented infrastructure of aggregators, bed banks, and intermediaries, explaining Tuki builds agent-ready unification protocols for AI commerce.
- 30:00MCP versus API debate clarifies natural language capability descriptions help agents consume services, while agent-to-agent communication embeds negotiating agents inside supplier systems.
- 35:00Hallucinations and consumer trust block agentic payments, industries must build mistake-resilience into bookings before autonomous agent transactions become viable.
- 40:00Mauro reveals red-green test-driven development methodology where agents write failing tests first then implementations, creating Oracle verification loops dramatically improving code quality.
- 45:00Blockchain's potential for transparent distributed AI training discussed, distinguishing democratization from decentralization while stable coins and regulatory momentum build toward agentic commerce infrastructure.
Key Insights
- Travel broadens perspective by revealing both universal human similarities and deep cultural differences. Mauro Schilman began traveling at fifteen through math olympiad competitions and found that people across the world share fundamental traits while also being shaped in profoundly different ways by their cultures. This tension between sameness and difference is what makes travel meaningful.
- Mathematics transitions from structured problem-solving in olympiads to genuine uncertainty in graduate school and research. Olympiad problems are carefully designed with elegant solutions meant to encourage creative thinking, but once a mathematician enters academia, the answers are unknown and the work becomes navigating that uncertainty.
- AI is now assisting mathematicians at the frontier, not just solving olympiad-level problems. Terence Tao, one of the greatest living mathematicians, has written publicly about how AI tools can help tackle unsolved problems, though the role of AI remains assistive rather than independent at the research level.
- Large language models are not truly transparent even when described as open source. Releasing model weights alone does not reveal the training data, annotation protocols, alignment tuning, or system prompts that shape model behavior. Real openness would require access to the entire pipeline.
- Memory and retrieval remain core unsolved challenges in AI systems. Researchers are moving from flat vector database approaches toward hierarchical memory structures with roughly three layers, which improves retrieval accuracy and reduces how much context gets consumed with each search.
- The travel industry is structurally unprepared for AI agents. A hidden web of bed banks, aggregators, and aggregators of aggregators sits between hotels and consumers, each taking a fee. Tuki Travel is building infrastructure to unify this distribution layer and make it consumable by AI agents through protocols like MCP and emerging agent-to-agent communication standards.
- Test-driven development using a red-green approach significantly improves AI-generated code quality. By asking the model to write failing tests before writing any implementation, developers create a verification oracle that guides the model toward correct solutions and avoids the bias of writing tests that simply confirm existing flawed code.
Episode transcript
Welcome to the Crazy Wisdom Podcast. This podcast is for you. If you have an insane drive to find the truth of things, it's not the good answers that we seek, but the good questions. I interview a range of different guests from many different fields, all with the intention to uncover the simple truths that are hidden in plain sight. Most people don't want to go there. I go there, my guests go there, and you benefit. Please let me know if you enjoy these episodes and as always, subscribe on itunes, Spotify, or wherever you listen to the podcasts.
Welcome to the Crazy Wisdom Podcast. I've got Mauro Shillman here and is the. He is the CTO of Tukey Travel. Welcome to the show.
Oh, I mean, I think the best thing for me is, how it opens your mind to how other people live and think. and I've been traveling since I have 15, years old.
first I was traveling because of the Math Olympiads. Oh, cool. So, yeah, while high school, I think that's what got me in. You know, they promised me that I would travel if I would do this.
Yeah. So, And, yeah, that's where I started meeting people from all around, and I started seeing, you know, they are more similar to me than I thought, but they're also very different in so many ways. And I think that's the great. The great thing about travel.
Your first full transcript is free. After that, an email opens every transcript in the index — a list of readers we can write to, not a guest book.