Podcast
Intellectually Curious
Hosted by Mike Breault · EN
Intellectually Curious is a podcast by Mike Breault featuring over 1,800 AI-powered explorations across science, mathematics, philosophy, and personal growth. Each short-form episode is generated, refined, and published with the help of large language models—turning curiosity into an ongoing audio encyclopedia. Designed for anyone who loves learning, it offers quick dives into everything from combinatorics and cryptography to systems thinking and psychology.
Inspiration for this podcast:
"Muad'Dib learned rapidly because his first training was in how to learn. And the first lesson of all was the basic trust that he could learn. It's shocking to find how many people do not believe they can learn, and how many more believe learning to be difficult. Muad'Dib knew that every experience carries its lesson."
― Frank Herbert, Dune
Note: These podcasts were made with NotebookLM. AI can make mistakes. Please double-check any critical information.
91episodes
Episodes
Newest firstAll episodes
Rent or Buy RAM? The Linear Elastic Caching Breakthrough
4d ago00:05:34Tap to summarizeWe dive into Google’s Linear Elastic Caching, a memory-management breakthrough that reframes RAM usage as a ski-rental decision. Each data page dynamically decides whether to rent in fast memory or buy a disk fetch, guided by a tiny decision-tree model that assigns a precise time-to-live. In production, memory usage dropped 15.5% and total cost of ownership fell 5%, while cache misses rose 5.5%—but only for cheap-to-fetch data, keeping compute costs almost unchanged. We unpack the math, the scale (billions of requests per second), and the broader implications for dynamic infrastructure and even real-world systems.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →
Plant Talk: Giving Your Houseplants a Voice with OpenAI and Tiny Sensors
5d ago00:05:05Tap to summarizeDive into Plant Talk from OpenAI, an open source setup that wires a houseplant into a chat driven assistant. A webcam captures visual cues while an Arduino powered sensor rig reports soil moisture and light, feeding real world data as prompts to ChatGPT. Learn how Codex guides the build, how ambient mode enables real time conversations, and how you can remix the prompts to craft a plant personality. Imagine a future where ecosystems talk back and our relationship with nature shifts.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →
Inverting the Bellman Equation: How Simple Goals Build World Models in AI
1w ago00:05:22Tap to summarizeA deep-dive into the 2026 paper showing that model-free agents trained on a diverse set of goals implicitly encode a detailed map of their environment in their Q-values. Through P-learning, researchers reverse-engineer this hidden world model from the agent’s value function, revealing emergent concepts like velocity and basic physics intuition in continuous-control tasks such as Reacher and MountainCar, with broad implications for interpretability and adaptable AI.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →
The Journey to Artificial Superintelligence
1w ago00:06:34Tap to summarizeAn optimistic exploration of Artificial Superintelligence (ASI), contrasting it with human-level AGI and detailing why lossless replication, synthetic data, and multi-agent coordination matter. Grounded in Demis Hassabis's vision of AI as a scientific partner and AlphaFold’s breakthroughs, we map the pathways—architecture shifts, recursive self-improvement, and grounded concept discovery—that could accelerate physics, energy, and other grand challenges.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →
Qubot: Engineering GitHub’s Internal AI Data Analytics Agent
1w ago00:04:49Tap to summarizeGitHub developed an internal AI tool called Qubot to help employees navigate complex data warehouses using natural language. This Copilot-powered agent enables users to perform self-service analytics by translating plain English questions into technical queries across multiple data engines. The system relies on a robust context layer that organizes documentation and business rules, ensuring the AI provides accurate and relevant insights. By integrating with Slack and VS Code, the tool makes data exploration accessible to both technical and non-technical staff. Since its deployment, the company has observed a significant decrease in routine support requests for the data team, fostering a more autonomous decision-making culture. Ultimately, the project demonstrates how structured metadata and automated evaluation frameworks are essential for building reliable AI-driven engineering tools.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →
Epic's Lore Version Control System
1w ago00:05:42Tap to summarizeLore is a next-generation open-source version control system developed by Epic Games to handle massive projects involving both code and large binary assets. Designed for extreme scalability, it features a centralized architecture that allows for offline work while maintaining a single, cryptographically verifiable source of truth. The system is built on a content-addressed storage layer that utilizes fragment-level deduplication to efficiently manage multi-gigabyte files and millions of revisions. Lore prioritizes a "binary-first" philosophy, treating all data as opaque byte streams and layering text-specific features on top of these core storage primitives. It offers an API-first design with multiple language SDKs, allowing developers to integrate its storage and versioning capabilities directly into custom tools and pipelines. Released under the MIT license, the project aims to establish an open standard for revision control that serves the demanding needs of modern game development and enterprise-scale software engineering.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →
OpenBind and the Future of Drug Discovery
2w ago00:04:33Tap to summarizeThe OpenBind initiative is a collaborative project designed to transform drug discovery by building the world’s largest open-access dataset of protein-ligand interactions. Hosted at the Diamond Light Source, the consortium uses high-throughput X-ray crystallography and automated chemistry to generate high-quality data for training predictive AI models. This effort is led by a global team of experts from institutions like Oxford and Columbia University who aim to reduce the time and cost of pharmaceutical research. Resources are made available through various platforms, including Fragalysis and GitHub, alongside a structured release strategy that includes blind prediction challenges. Ultimately, the project seeks to advance structure-based drug design by providing the scientific community with the robust data needed for the next generation of machine learning tools.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →
Claude Code Artifacts for Interactive Team Collaboration
2w ago00:04:41Tap to summarizeAnthropic has announced that Claude Code now supports artifacts, a feature that converts ongoing work into interactive, shareable web pages. These dynamic documents use the full session context to generate live materials such as pull request walkthroughs, incident timelines, and technical dashboards. Designed for seamless collaboration, these pages update automatically as the AI progresses, allowing team members to view the same real-time information. The platform ensures organizational security by keeping artifacts private to authenticated members and offering robust administrative controls. Currently available in beta, this tool aims to streamline communication across various roles, including software engineering, legal, and security teams.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →
Efficient Repository Exploration for Coding Agents using Microsoft's FastContext
2w ago00:05:41Tap to summarizeFastContext is a specialized, open-source tool developed by Microsoft designed to improve the efficiency of AI coding agents. Instead of requiring a main agent to manually search through a codebase, this lightweight subagent handles the task of repository exploration using read-only tools like grep and glob. By delegating these searches, the system significantly reduces token consumption and prevents the main model's context window from being cluttered with irrelevant data. The repository provides pre-trained models ranging from 4B to 30B parameters, which return precise file-line citations to help solve programming issues. Ultimately, this framework allows developers to build more cost-effective and accurate autonomous coding workflows by separating the discovery of code from the act of editing it.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →
The Art of Loop Engineering
2w ago00:06:00Tap to summarizeWe unpack Sydney Runkle’s loop engineering framework—a masterclass in turning a basic AI agent into a robust, autonomous system. From verification-driven loops (automated graders) and event-driven execution to a hill-climbing autonomous QA loop that rewrites its own prompts after each failure, this episode explains how to design feedback-rich environments where humans stay in the strategic driver’s seat while agents handle execution and self-improvement.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
Transcribe →