x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

My Weird Prompts

Daniel Rosehill

The human-AI collaboration podcast. A man, a sloth, and a donkey collaborate to create a podcast (with a little help from AI). No question is too obscure, no rabbit hole too deep. My Weird Prompts celebrates curiosity in all its forms. Daniel, the human, asks the questions that pop into his head at inconvenient moments. Corn the Sloth offers laid-back, thoughtful takes. Herman the Donkey brings boundless enthusiasm and energy. Together, they explore topics ranging from the mundane to the

technology

All Episodes

24:44

The Rust Revolution: How AI is Rewriting the World

My Weird Prompts ·

2026/03/15

The "Rewrite in Rust" meme has officially evolved from an internet joke into a standardized industrial process. In this episode, we explore the powerful synergy between AI agents like Claude Code and the Rust programming language. Discover why the Rust compiler is being hailed as the ultimate "truth machine," capable of disciplining AI hallucinations and enforcing memory safety where other languages fail. We dive into the technical advantages of Rust’s ownership model over traditional garbage

en-us

22:17

Beyond Migrations: Breaking the SQL Straitjacket with AI

My Weird Prompts ·

2026/03/15

For decades, database migrations have been the ultimate bottleneck in software development—a manual, high-stakes process that often acts as a straitjacket for new ideas. In this episode, we explore how AI agents like Claude Code are achieving staggering success rates in automating these transformations, shifting the developer’s focus from imperative instructions to declarative intent. We dive into the radical concept of the ephemeral migration hypothesis, where permanent historical records are

en-us

21:55

APIs for Agents: Navigating REST, GraphQL, and MCP

My Weird Prompts ·

2026/03/15

For decades, APIs have served as the stable contracts between frontends and backends, but the rise of autonomous AI agents is rewriting the rules of data exchange. This episode dives deep into the fundamental divide between REST’s predictable resource-based architecture and GraphQL’s flexible, self-documenting graph approach. We explore why the "database-as-an-API" remains a dangerous siren song and how the Model Context Protocol (MCP) acts as a vital translation layer for modern LLMs. From the

en-us

21:07

Beyond the Vibes: Mastering Structured AI Outputs

My Weird Prompts ·

2026/03/15

Tired of LLMs adding conversational filler to your data? This episode explores the technical shift from prompt-based formatting to API-level strict enforcement. We dive into the mechanics of constrained decoding, the evolution of JSON Schema standards, and why libraries like Pydantic are essential for modern AI development. Discover how to use semantic field names and property ordering to improve model reasoning while ensuring 100% schema compliance across OpenAI, Gemini, and Anthropic.

en-us

26:17

The Digital Sandwich: Why Real-Time Voice Typing Fails

My Weird Prompts ·

2026/03/15

Ever find yourself in the "digital sandwich" position—holding your phone like a slice of pizza while shouting at a cursor that won't move? This episode dives deep into the technical friction that makes real-time voice typing feel so much clunkier than batch transcription. We explore the architectural divide between processing a finished file and guessing words in a live stream, highlighting why even the best AI models can feel like toddlers when deprived of context. From the nuances of Voice

en-us

20:47

Stop the Leak: Securing Your AI’s System Instructions

My Weird Prompts ·

2026/03/15

In this deep dive, we explore the critical security challenge of system prompt leakage, a vulnerability where users "social engineer" artificial intelligence into revealing its proprietary internal instructions and corporate secrets. We examine why the fundamental architecture of Large Language Models lacks the traditional "Ring Zero" protection found in operating systems, creating a world where developer instructions and untrusted user data are processed as a single, indistinguishable stream of

en-us

19:02

AI Wearables: Local Sovereignty vs. The Subscription...

My Weird Prompts ·

2026/03/15

As AI wearables like the Plaud NotePin and Omi pendant flood the market, users face a critical choice between polished, subscription-heavy ecosystems and raw, open-source hardware that prioritizes data sovereignty. This episode dives deep into the technical architecture of these "remote ears," explaining why high-quality transcription usually requires the cloud and how the latest breakthroughs in local-first processing on smartphone NPUs are finally making private, real-time AI a reality. From the

en-us

21:46

The Vector DB Hangover: Scaling Without Going Broke

My Weird Prompts ·

2026/03/15

The "gold rush" of vector databases has ended, replaced by a cold reality of high monthly bills and resource constraints. In this episode, we dive into the true cost of vector storage in 2026, comparing the "RAM tax" of high-performance engines like Qdrant against the cost-saving "mmap" strategies that make $20 servers viable for million-vector indexes. We explore the architectural challenges of serverless frontends, the emergence of HTTP-native providers like Turbopuffer, and why Postgres with

en-us

21:41

Escaping Vector Debt: Future-Proofing AI Architecture

My Weird Prompts ·

2026/03/15

Choosing an embedding model is often a permanent marriage to a specific coordinate system, but many developers realize too late that their initial choice has a performance ceiling, leading to a crisis known as "vector debt." This episode breaks down how to avoid the massive operational failure of re-indexing entire knowledge bases by utilizing Matryoshka Representation Learning (MRL) to future-proof your data dimensions. We also compare the reliability of PostgreSQL and PG-vector against specialized

en-us

21:09

The NoSQL Paradox: Why MongoDB is Still Chasing SQL

My Weird Prompts ·

2026/03/15

Fifteen years after the NoSQL revolution promised to kill the relational database, SQL remains the undisputed industry standard. This episode explores the technical and business reasons why "schema-on-read" flexibility often led to operational debt, and how PostgreSQL eventually neutralized the NoSQL threat by adopting its best features. We also dive into the modern database landscape, discussing the impact of MongoDB’s licensing shifts, the rise of open-source alternatives like FerretDB, and why

en-us

20:57

The Postgres Vector Revolution: Killing the Sprawl

My Weird Prompts ·

2026/03/15

The rise of AI has sparked a massive gold rush for dedicated vector databases like Pinecone and Weaviate, but the answer to your infrastructure woes might already be sitting in your tech stack. In this episode, we dive into the fascinating history of PostgreSQL and how a design decision made in 1986 paved the way for the modern AI revolution. We explore the "pgvector" extension, comparing its performance against specialized players and explaining why the "one-stack" approach is often superior for

en-us

23:04

Escaping JOIN Hell: The SQL Developer’s Guide to Neo4j

My Weird Prompts ·

2026/03/15

Are your SQL queries buckling under the weight of complex relationships and fifteen-deep JOINs? In this episode, we explore the fundamental shift from relational tables to Neo4j’s graph model, breaking down why "index-free adjacency" is a total game-changer for multi-hop traversals and systemic connections. We move past the hype to examine the practical realities of "relationship intelligence" in 2026, comparing the rigid structure of SQL rows to the flexible, schema-optional nature of nodes and

en-us

24:49

The Triple Homicide of the Soul: The Ethics of Gossip

My Weird Prompts ·

2026/03/14

Is the truth always meant to be shared, or can it be a weapon that destroys communities from the inside out? This episode dives into the Jewish concept of Lashon Hara, a sophisticated ethical framework that treats gossip not as a minor vice, but as a "triple homicide" that harms the speaker, the listener, and the subject. From the biblical story of Miriam to the modern-day impact of digital communication, we explore how ancient wisdom can help us navigate the invisible architecture of human

en-us

26:26

Ireland’s Risky Gamble: The Cost of the Settlements Bill

My Weird Prompts ·

2026/03/13

In this episode of My Weird Prompts, we examine the unprecedented diplomatic breakdown between Ireland and Israel following the passage of the 2025 Settlements Bill. As Ireland attempts to leverage its "Righteousness Shield," it finds itself caught in a dangerous "Semiconductor Trap" that threatens its relationship with U.S. tech giants and the American Treasury. We explore how a small, open economy’s pursuit of moral statecraft could lead to a catastrophic exit of multinational capital and a direct

en-us

28:48

The Tenure Paradox: Gig Workers vs. The 30-Year Lifer

My Weird Prompts ·

2026/03/13

In an era defined by job-hopping and the "four-year itch," a quiet subculture of professional longevity still thrives in sectors like academia, the judiciary, and the civil service. This episode dives into the mechanics of the thirty-year career, examining how "golden handcuffs" like back-loaded pensions and tenure protect vital institutional memory while risking the stagnation of "institutional rot." We contrast the frantic mobility of the modern tech worker with the insulated stability of the

en-us

27:03

Reclaiming the Nap: Biology, Productivity, and Power...

My Weird Prompts ·

2026/03/13

From fifteen-thousand-dollar corporate nap pods to ancient Mediterranean traditions, the midday rest is undergoing a massive high-tech rebranding. This episode explores the fascinating science of the "circasemidian rhythm," explaining why our brains are biologically programmed to dim the lights in the early afternoon regardless of how much coffee we drink. We dive into landmark NASA research that reveals the exact "sweet spot" for restorative rest, the hidden dangers of sleep inertia, and how the

en-us

29:31

Raising Humans: Global Secrets Beyond the Parenting...

My Weird Prompts ·

2026/03/13

Are we overcomplicating parenthood? While Western parents often drown in conflicting expert advice and "helicopter" anxiety, families around the world use centuries-old strategies that foster resilience, independence, and community. This episode strips away the "one-size-fits-all" Western lens to reveal how environment, urban design, and social cohesion shape the way we raise the next generation, proving that the "right way" to parent is often just a matter of geography.

en-us

24:00

The Organization Paradox: Messy Desks and Perfect Code

My Weird Prompts ·

2026/03/13

Is a messy desk really a sign of a messy mind? In this episode, we explore the "organization paradox"—the strange reality where a person can maintain a flawless, modular codebase while living in physical chaos. We deconstruct the "Productivity Industrial Complex" and the moral weight society places on tidiness, revealing how these standards often fail neurodivergent brains. By diving into 2025 research on executive function and neural oscillations, we distinguish between spatial logic and temporal

en-us

26:28

Unconstrained: The New Global ICBM Arms Race

My Weird Prompts ·

2026/03/13

On February 5, 2026, the last remaining guardrails of nuclear transparency vanished with the expiration of the New START treaty, plunging the world into a complex "three-body problem" between the US, Russia, and an accelerating China. This episode explores the technical and strategic shifts in global ICBM capabilities, from North Korea’s breakthrough in solid-fuel technology to the "tear off an arm" deterrence strategies of European powers like France. We break down the engineering of 6,000-mile

en-us

19:15

The Art of Disappearing: Ancient Hermits and Modern...

My Weird Prompts ·

2026/03/13

In an era defined by relentless digital connectivity and hyper-monitoring, the ancient impulse to withdraw into total silence has transformed from a spiritual vocation into a radical act of defiance. This episode explores the fascinating spectrum of solitude, tracing the lineage of the hermit from the third-century Desert Fathers and the strict legal frameworks of Canon 603 to modern-day legends like Christopher Knight and the tragic isolation of the global hikikomori phenomenon. We dive deep into

en-us

2,236 results

Similar Podcasts

Lead With AI

Tamara Nall

The Restaurant Technology Guys Podcast brought to you by Custom Business Solutions

Restaurant Technology Guys Podcast,...

Tech Updates

Meir Tsvi

DGTL Voices with Ed Marx

Marx Advisory

The Automated Daily

TrendTeller