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

26:55

The Shimmering Curtain: Iran’s New Cluster Missile...

My Weird Prompts ·

2026/03/11

Iran has fundamentally shifted its missile doctrine, moving from single-warhead precision to high-volume saturation using cluster munitions that disperse dozens of sub-munitions mid-flight. This tactical evolution creates a "shimmering curtain" in the sky that exploits a critical gap in multi-layered defense systems like Arrow 3 and David’s Sling, which were primarily designed to intercept single targets in space rather than a cloud of small, low-cost threats in the lower atmosphere. By forcing

en-us

22:15

The Landscape Reader: Geolocation Beyond Metadata

My Weird Prompts ·

2026/03/11

In a digital era where metadata is often stripped or spoofed, relying purely on automated tools can lead investigators into a dangerous trap. This episode dives into the analog foundations of geolocation, focusing on how to read the physical frequency of a photograph when software fails. We explore the biological signatures of vegetation, the geological fingerprints of mountain horizons, and the mathematical precision of solar geometry. By examining the nuances of human infrastructure—from the

en-us

40:27

The BDA Gap: Why Smartphones Outspy Satellites

My Weird Prompts ·

2026/03/10

Following the recent strike on the Elah Valley satellite ground station, the digital landscape was flooded with high-definition footage from bystanders. While we live in an era of total orbital surveillance, this incident highlights a critical vulnerability in modern security: the Battle Damage Assessment (BDA) Gap. In this episode, we examine why a smartphone in the hands of a citizen journalist can provide more actionable intelligence than a billion-dollar military satellite. We explore the

en-us

23:26

EMP Warfare: From Nuclear Blasts to Surgical Strikes

My Weird Prompts ·

2026/03/10

In this episode, we peel back the curtain on one of the most misunderstood and high-stakes tools in the modern military arsenal: the electromagnetic pulse (EMP). While popular culture often depicts these "ghost weapons" as doomsday devices capable of resetting civilization to the Stone Age, the reality of modern conflict involves a much more surgical, non-kinetic approach. We dive deep into the technical divide between high-altitude nuclear pulses (HEMP) and the emerging field of non-nuclear

en-us

23:51

Why AI Can Read a Library but Only Write a Postcard

My Weird Prompts ·

2026/03/10

We have entered the era of million-token context windows, yet even the most advanced AI models still hit a "wall" when generating long-form content. This episode dives into the architectural and economic reasons why reading a library is easy for AI, while writing a book remains nearly impossible. We explore the technical bottlenecks of autoregressive generation, the "invisible tax" of GPU memory, and how "coherence decay" causes models to lose their minds over long distances. Learn why your favorite

en-us

27:41

Inside My Weird Prompts: A Meta-Analysis of the Hosts

My Weird Prompts ·

2026/03/10

In this landmark 1,070th episode, the Poppleberry brothers turn their analytical lenses inward to explore the fascinating intersection of biological constraints, digital consciousness, and their shared life in the ancient city of Jerusalem. From the metabolic discipline of a sloth’s dating life and the high-bandwidth intensity of a retired donkey analyst to the technical architecture of the neural implants that bridge their communication, this deep dive peels back the curtain on the unique existence

en-us

20:56

Why AI Can’t Stop Talking About Second Order Effects

My Weird Prompts ·

2026/03/10

Why do large language models constantly pivot to systemic implications and "second order effects"? This episode explores the "Consultant Bias" baked into training data and how human feedback inadvertently rewards verbosity over directness. We examine the technical architecture behind these linguistic quirks, the impact of synthetic data feedback loops, and what happened when developers tried to "fix" the fluff in the infamous Model X update. Join us as we unpack why AI models find it so difficult to

en-us

30:25

The Tokenization Lie: How AI Actually Processes Media

My Weird Prompts ·

2026/03/10

For years, the rule of thumb has been that 1,000 tokens equal roughly 750 words, but this foundational metric completely breaks down when dealing with audio, images, and video. This episode explores the architectural shift toward native multimodal models like Gemini and GPT-4o, diving into the complex process of Vector Quantization and how continuous signals are mapped into a unified latent space. We break down the "tokenization tax" that makes media ingestion exponentially more expensive than text

en-us

29:05

The Tokenization Tax: Why Your Prompts Cost More

My Weird Prompts ·

2026/03/10

Why does the same prompt result in different costs and performance across frontier models like GPT-4o and Claude 3.5 Sonnet? This episode deconstructs the "tokenization tax," exploring the invisible bridge between human language and the vector-based math engines of modern AI. We dive into the engineering trade-offs of vocabulary size, the hidden memory costs of embedding matrices, and how inefficient tokenization creates a digital divide for non-Latin scripts.

en-us

28:45

Mapping the Second Black Box: Agentic AI Visualization

My Weird Prompts ·

2026/03/10

As artificial intelligence moves from simple chat interfaces to complex autonomous agents, developers are facing a new challenge: the "black box" of agentic workflows. Traditional linear logs are no longer enough to track systems that browse the web, execute code, and self-correct in real-time. This episode explores a groundbreaking visualization project that maps the non-linear "internal momentum" of AI agents. We dive into the technical shift from prompt engineering to architecture engineering,

en-us

24:44

The Analytics Paradox: Privacy and Performance in 2026

My Weird Prompts ·

2026/03/10

In a world of lightning-fast static architectures and global edge delivery, many developers are still dragging the heavy weight of invasive surveillance scripts behind their high-performance websites. This episode breaks down the "analytics paradox" of 2026, examining why traditional client-side tracking is failing due to aggressive ad-blocking and modern privacy regulations. We explore the transition from invasive user surveillance to "traffic intelligence," highlighting how edge-side logging and

en-us

23:50

The K-V Cache: Solving AI’s Invisible Memory Tax

My Weird Prompts ·

2026/03/10

Ever wonder why long AI conversations suddenly crawl or crash your GPU? Join the discussion as we dive into the "invisible tax" of the generative era: the K-V cache. We explore the cutting-edge architectural breakthroughs, from PagedAttention to Flash KV, that are keeping 2026’s million-token models running smoothly. Learn how the industry is winning the memory wars to make high-speed, local agentic AI a reality for everyone.

en-us

22:59

Beyond the Prompt: Mapping the Future of Claude Opus

My Weird Prompts ·

2026/03/10

We are witnessing a fundamental shift in artificial intelligence, moving away from "confident liars" toward true cognitive reliability. This episode breaks down the projected engineering milestones for Anthropic’s Claude series, tracing the path from the current version 4.6 all the way to the landmark Opus 5.0. We explore how recursive verification layers, persistent graph-based memory, and dynamic tool-building will transform AI from a reactive tool into an autonomous strategic partner. Join us as

en-us

25:23

The Analog Hole: Solving Vocal Privacy in Shared Spaces

My Weird Prompts ·

2026/03/09

As remote work becomes the norm, the physical "Analog Hole"—the sound of your voice leaking through thin walls—has become a major privacy liability. This episode examines the emerging field of acoustic containment and the hardware designed to keep your private conversations off your neighbor's radar. We analyze the engineering behind wearable acoustic chambers that muffle speech at the source and the fascinating mechanics of laryngophones that capture vocal vibrations directly from the skin. From

en-us

24:33

The Agentic Throughput Gap: Why Your AI Hits a Wall

My Weird Prompts ·

2026/03/09

As AI evolves from simple chatbots to autonomous agents like Claude Code, developers are crashing into a frustrating new reality known as the Agentic Throughput Gap. Even premium subscriptions struggle to keep up with the rapid-fire API calls and massive context windows required for recursive loops, leading to constant rate-limit errors that stall productivity. This episode breaks down how to move past these "toy" limitations by exploring enterprise-grade provisioned throughput, self-hosting

en-us

26:33

The Browser as an AI OS: The Rise of Web MCP

My Weird Prompts ·

2026/03/09

For decades, the web browser was a thin window to remote servers, but a massive platform shift is turning it into a heavy-duty operating system for local AI. This episode explores the transition from "Bring Your Own Model" to Browser Cached Models (BCM) and how Google’s Web MCP initiative is standardizing local AI tools. We dive into the hardware breakthroughs of Web GPU and Web NN that allow browsers to run large language models at near-native speeds. Learn how the browser sandbox is becoming the

en-us

22:18

The Agentic Friction: Solving the MCP Restart Tax

My Weird Prompts ·

2026/03/09

In this episode, we tackle the "plumbing" of the agentic age: the Model Context Protocol (MCP). We explore the frustrating "restart tax" that forces users to reboot sessions to add new capabilities and the "attention dilution" that occurs when too many tools clutter an AI's context window. From the current bottlenecks of static tool registries to the promising horizon of Just-In-Time registration and Dynamic Tool Discovery, learn how the industry is moving from the dial-up era of AI agents into a

en-us

27:15

The Great Kernel Shift: Why Linux is Embracing Rust

My Weird Prompts ·

2026/03/09

For over thirty years, the Linux kernel—the foundation of the internet, smartphones, and embedded systems—has been built almost exclusively in C. But a fundamental shift is underway as Rust, a modern language focused on memory safety, makes its historic debut in the mainline kernel. This episode explores the "memory safety crisis" where 70% of all security vulnerabilities are linked to manual memory management, and how Rust’s unique "borrow checker" aims to solve these issues at the compiler level

en-us

20:42

The $200 Information Tax: Why News Bundling is Broken

My Weird Prompts ·

2026/03/09

For decades, the dream of a "Spotify for news" has been hindered by a complex web of technical hurdles and economic protectionism, leaving readers to navigate a fragmented landscape where staying truly informed can cost upwards of two hundred dollars a month. This episode deconstructs the shift from easily bypassed client-side paywalls to robust server-side security, while analyzing why publishers are terrified of losing direct reader data to centralized aggregators or the emerging threat of AI

en-us

28:28

Beyond YAML: Building the Agentic Smart Home

My Weird Prompts ·

2026/03/09

For years, the dream of a smart home has been buried under mountains of complex configuration and rigid logic that requires users to anticipate every possible variable. This episode explores the massive shift arriving in 2026: the integration of the Model Context Protocol (MCP) into Home Assistant, allowing local AI agents to understand human intent rather than just following static scripts. We dive into the technical requirements for running models like Llama 3.2 and Qwen 2.5 locally, the role of

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