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

27:06

The Ghost Company: The High Cost of AI Agent Bureaucracy

My Weird Prompts ·

2026/03/11

Is the dream of the "ghost company"—a fully autonomous AI startup—actually a financial money pit? This episode dives into the emerging "Agentic Mesh," exploring why hierarchical agent setups are currently seeing up to a 70% drop in reasoning performance and staggering five-figure token bills. We break down the technical battle between fluid, role-based systems and deterministic frameworks, revealing how the new role of the "Agent Boss" is the only thing keeping these digital architectures from

en-us

25:53

Inside the Neural Cathedral: Cracking the AI Black Box

My Weird Prompts ·

2026/03/11

For years, the inner workings of large language models have been treated as a mysterious "black box" where inputs turn into outputs through a process that looks more like magic than math. This episode dives into the cutting-edge field of mechanistic interpretability, exploring how researchers are finally reverse-engineering the "neural cathedrals" of AI to map out the specific circuits that drive machine logic. From the strange geometry of high-dimensional superposition to the discovery of "Golden

en-us

27:28

The Architecture of Intelligence: Beyond the Transformer

My Weird Prompts ·

2026/03/11

In an era where the arXiv daily feed delivers a staggering volume of research, staying ahead of the artificial intelligence curve has transformed from a scholarly pursuit into a high-stakes data engineering challenge. This episode explores the "hidden giants" of AI research—the foundational papers like ResNet and FlashAttention that provided the structural steel and high-speed engines necessary for the Transformer revolution to actually function at scale. We move beyond the history to analyze the

en-us

21:56

The arXiv Effect: Inside the Engine of AI Research

My Weird Prompts ·

2026/03/11

In this episode, we dive into the fascinating world of arXiv, the unassuming preprint server that powers the modern AI revolution. We explore its origins in 1990s physics, why it maintains a "lo-fi" aesthetic, and how it bypasses traditional peer review to accelerate scientific discovery. Whether you are an independent researcher or just curious about how breakthroughs like Transformers go viral overnight, this deep dive reveals why arXiv is the most important tool in a modern engineer's arsenal

en-us

26:35

The T-FLOP Trap: Measuring the Power of Modern AI

My Weird Prompts ·

2026/03/11

In an era where new Blackwell clusters boast performance figures in the tens of quadrillions of operations per second, the "teraflop" has become the primary yardstick for the twenty-first century’s technological progress, yet these headline-grabbing numbers often mask a more complex reality regarding how AI hardware actually functions. By exploring the shift from high-precision scientific computing to the low-precision matrix multiplications that power modern large language models, this episode

en-us

26:09

Beyond the Emoji: How Hugging Face Conquered AI

My Weird Prompts ·

2026/03/11

Hugging Face is often called the "GitHub of AI," but its role is far more critical to the modern tech stack than that simple shorthand suggests. We explore the platform's fascinating evolution from a quirky chatbot startup designed for teenagers to the indispensable central nervous system of the global artificial intelligence world. From standardizing model weights through the Transformers library to fostering the open-weights movement via its influential leaderboards, this episode reveals how a

en-us

26:05

Betting on the Brink: Polymarket and the Future of War

My Weird Prompts ·

2026/03/11

In this episode, we explore the chilling intersection of high finance and global conflict through the lens of Polymarket, a decentralized platform where users wager millions on the outcome of international crises. We trace the evolution of war betting from Nathan Rothschild’s 1815 "information arbitrage" at Waterloo to modern high-frequency trading bots reacting to real-time satellite imagery of the 2026 Iran crisis. By examining the mechanics of automated market makers and the "wisdom of the

en-us

25:10

The Entropy Budget: Embracing AI Zaniness

My Weird Prompts ·

2026/03/11

After over a thousand episodes, Corn and Herman face a digital mid-life crisis: have they become too predictable? This episode dives into the technical and creative strategies for breaking the "helpful assistant" mold, from adjusting temperature settings to implementing an "Entropy Budget." Discover how they plan to use meta-humor, recurring sentient firewalls, and "Live Prompt Injections" to turn the Uncanny Valley into a Pleasant Canyon. It’s a fascinating look at the future of AI-driven media

en-us

12:57

The Great Dish Debate: An Apology and a Plan

My Weird Prompts ·

2026/03/11

In this special solo update, Corn Poppleberry addresses the elephant—or rather, the donkey—in the room following a disastrous on-air argument about kitchen hygiene. He offers a sincere apology for the unprofessional behavior that led to his brother Herman walking out mid-recording and explains the fundamental "species" differences that lead to friction between a methodical sloth and an efficient donkey. Listen in to hear how the brothers used diplomacy, a shared Google calendar, and a little help

en-us

28:07

Silicon Secrets: The Physics of CPU Performance

My Weird Prompts ·

2026/03/11

Most users treat their computers like magic black boxes, but there is a wealth of untapped performance hidden beneath the surface of every processor. This episode explores the fundamental mechanics of CPU architecture, from the differences between x86 and ARM instruction sets to the high-stakes physics of power delivery and thermal management. We dive deep into why manufacturers leave a "safety margin" in their hardware and how power users can reclaim that 10-15% efficiency boost through strategic

en-us

12:14

LLM Context Windows and the Great Kitchen War

My Weird Prompts ·

2026/03/11

Large Language Models are often marketed based on the size of their context windows, but the technical reality behind these numbers is far more complex than simple data storage. This episode breaks down the "attention" problem in transformer architectures, exploring why doubling context length quadruples compute costs and how researchers use sliding windows and RAG to bridge the gap. However, the technical deep dive takes a sharp turn when a disagreement over a soaking pasta pan spirals into a

en-us

28:36

Beyond the Boost: Mastering Modern GPU and RAM Tuning

My Weird Prompts ·

2026/03/11

In this deep dive into the hardware landscape of 2026, we move past the CPU to explore the intricate world of GPU and RAM optimization, questioning whether the "set it and forget it" era has truly arrived. We break down the technical mechanics of voltage-frequency curves and the counterintuitive power of undervolting, demonstrating how surgical efficiency often leads to better sustained performance and lower acoustics than traditional brute-force overclocking. From navigating the manufacturing

en-us

21:26

Data of Escalation: Analyzing Operation True Promise...

My Weird Prompts ·

2026/03/11

In the wake of an unprecedented regional escalation, this episode examines the staggering open-source data behind Operation True Promise Four, a campaign that has seen nearly 6,000 munitions launched in just eleven days to fundamentally redefine the boundaries of modern industrial warfare. By comparing this current conflict to previous engagements, the analysis reveals a sophisticated tactical evolution characterized by high-tempo saturation strikes, the combat debut of hypersonic glide vehicles,

en-us

21:53

The Truth Conflict: Why AI Ignores the Facts You Give It

My Weird Prompts ·

2026/03/11

In this episode of My Weird Prompts, we explore the "Truth Conflict," a growing challenge in the world of Retrieval-Augmented Generation (RAG). As we move into 2026, developers are finding that even when provided with the exact facts needed to answer a query, high-end language models often default to their internal training data—a phenomenon known as the Hallucination versus Contradiction paradox. We break down the technical reasons behind this, including the "Knowledge Conflict Threshold" and the

en-us

28:21

Digital Recalls: Why Your AI Is Losing Its Edge

My Weird Prompts ·

2026/03/11

We’re often told that AI progress is a straight line up, but the reality is far messier than the marketing departments want you to believe. This episode dives into the "digital recall"—the silent phenomenon where advanced models lose reasoning, hallucinate more, or become "lazy" due to technical trade-offs like alignment and quantization. We pull back the curtain on why the world’s most advanced systems are sometimes forced to take a massive step backward, exploring the hidden "alignment tax" and

en-us

25:22

The Agentic Symphony: Orchestrating Enterprise AI

My Weird Prompts ·

2026/03/11

In the spring of 2026, half of all enterprise AI agents still operate in total isolation, creating "islands of automation" that fail to reach their full potential. This episode breaks down the "Agentic Symphony," a revolutionary 14-layer architecture that provides the connective tissue needed to turn isolated models into a cohesive, high-functioning ecosystem. We explore critical components like the Model Context Protocol (MCP) and the often-ignored "vendor prompts," while identifying three latent

en-us

20:53

Inside the Neural Cathedral: Decoding AI’s Hidden Logic

My Weird Prompts ·

2026/03/11

For years, artificial intelligence has been a "black box"—a system where we see the inputs and outputs but remain blind to the internal logic. This episode explores the transition from AI "alchemy" to a true mechanistic science, revealing how researchers are finally mapping the mathematical wilderness of trillion-parameter models. We dive into the breakthrough of Sparse Autoencoders and the discovery of "circuits" that represent complex concepts like deception and bias. As we move toward autonomous

en-us

25:14

Intelligence-Grade OSINT: The Rise of Agentic AI

My Weird Prompts ·

2026/03/11

In this episode, we dive deep into the "Promise Denied" project, a groundbreaking experimental platform that utilizes agentic artificial intelligence to track the complexities of the Iran-Israel conflict. This shift represents a fundamental evolution in Open Source Intelligence (OSINT), moving away from manual keyword searches toward autonomous workflows capable of identifying tactical anomalies that even seasoned human analysts might overlook. We examine how advanced models like Gemini use live

en-us

24:55

Rooting in 2026: Is the Power User Era Over?

My Weird Prompts ·

2026/03/11

For over a decade, tech enthusiasts have debated the necessity of rooting, but in 2026, the landscape has shifted from a simple binary choice to a complex web of hardware-backed security and sophisticated middleware. This episode explores the ongoing "cat-and-mouse" game between developers and Google’s Play Integrity API, explaining why bypassing modern attestation has become a monumental hurdle that often breaks essential banking and payment services. We also take a detailed look at the rise of

en-us

24:30

The CPU-First Era: Why AI is Moving Back to the...

My Weird Prompts ·

2026/03/11

For years, high-end GPUs were considered the only viable way to run artificial intelligence, but a major shift in hardware architecture is challenging that dogma. This episode explores the rise of "CPU-first" AI, where specialized instructions like Intel’s AMX and ARM’s SME are turning standard processors into machine learning powerhouses. We dive into the magic of quantization and software like Whisper.cpp that allows everyday laptops to handle tasks once reserved for massive data centers. From

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