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

21:06

PLCs: The Grey Boxes Running the World

My Weird Prompts ·

2026/04/07

Explore the hidden world of Programmable Logic Controllers (PLCs), the rugged computers that run factories, power grids, and water systems. Learn about the "Big Five" vendors, the deterministic operating systems like VxWorks, and why Ladder Logic refuses to die. Discover how Linux and Docker are finally invading the industrial floor and what that means for the future of automation.

en-us

8:54

SITREP Flash; 7 Apr 02:50 (23:50 UTC)

My Weird Prompts ·

2026/04/06

The United States has issued a formal ultimatum to Iran, demanding a full withdrawal from the Strait of Hormuz by zero-four-hundred UTC. With the USS Enterprise and B-21 Raiders now in the region, the world watches to see if this deadline triggers the first major naval engagement in decades. We break down the military assets, the cyber threats, and the global economic stakes of this rapidly escalating crisis.

en-us

23:21

The Tip of the Spear: How Special Forces Actually Work

My Weird Prompts ·

2026/04/06

We're diving deep into the history and mechanics of special forces, from Winston Churchill's "hunter class" to the modern Green Beret. Learn how these tiny teams have a massive impact on global events, why the "Big Army" hated them, and what a typical career looks like for a Navy SEAL. Powered by Google Gemini 1.5 Flash.

en-us

23:53

Is Pure NLP Dead? The Hidden Scaffolding of AI

My Weird Prompts ·

2026/04/06

We explore the deep history of Natural Language Processing, from the rule-based systems of the 1960s to the statistical revolution of the 90s, and how these "obsolete" techniques are the hidden scaffolding behind modern Large Language Models. We discuss the "identity crisis" in the field, the shift from symbolic logic to end-to-end neural networks, and why the future of AI might actually be a return to "Neuro-symbolic" systems that combine the best of both worlds.

en-us

23:42

AI Agents for Israel: Hyper-Local Skills in Action

My Weird Prompts ·

2026/04/06

The podcast explores the emerging ecosystem of Model Context Protocol (MCP) servers and AI agent skills tailored specifically for Israel. It dives into how these bundles go beyond simple translation to provide "regulatory hard-coding" for complex bureaucracy, real-time civil defense data, and culturally nuanced communication. Listeners will learn about specific applications, from navigating tax laws and healthcare systems to finding bomb shelters, and how this hyper-localization represents a shift

en-us

23:54

Can AI Simulate a Whole City?

My Weird Prompts ·

2026/04/06

AgentSociety is an open-source framework that simulates entire cities with thousands of AI agents. This episode explores how these digital citizens—equipped with memories, emotions, and social lives—can test policies like UBI and traffic routes before real-world implementation. Learn about the three-layer architecture and the surprising social behaviors that emerge from these simulations.

en-us

22:39

Downed Pilot Turns Hideout Into Strike Base

My Weird Prompts ·

2026/04/06

In April 2026, a downed US Weapons Systems Officer in Iran did the unthinkable: from a hidden mountain position, he directed drone strikes against enemy forces while waiting for extraction. This episode unpacks the military and technical realities behind the mission—from burst-transmission survival radios and integrated data links to the high-stakes logistics of a denied-territory rescue. We explore how modern aircrew gear turns a survivor into a forward air controller, why the mission required

en-us

21:28

Git Can't Handle AI Agents—Yet

My Weird Prompts ·

2026/04/06

As AI agents become standard coding partners, the version control systems we rely on are starting to crack. We explore the collision course between Git's human-centric design and autonomous AI workflows. From uncommitted work getting vaporized to "logical merge conflicts" that break your code, we unpack the chaos of parallel agents. Then, we dive into solutions: Git worktrees for isolation, file-level locking for coordination, and orchestrator patterns that manage the madness. Whether you're running

en-us

21:05

SemVer, Changelogs, and the Social Contract of Code

My Weird Prompts ·

2026/04/06

Why do some software updates break everything while others are seamless? This episode dives into Semantic Versioning (SemVer), the art of the changelog, and Conventional Commits. We explore how version numbers act as a social contract between developers and users, preventing "Dependency Hell" and ensuring trust in the digital ecosystem. Learn why a "Major" bump signals honesty, how automation enforces discipline, and the critical difference between deleting a release and "yanking" it.

en-us

20:50

Agentskills.io Spec: From Broken YAML to Production...

My Weird Prompts ·

2026/04/06

If you've ever fought with a broken YAML file that Claude refuses to load, this episode is your rescue mission. We dissect the agentskills.io specification—the de facto standard for Claude Code skills—line by line. You'll learn the five non-negotiable frontmatter fields, why directory structure matters for context efficiency, and how to write descriptions that act as internal triggers for the agent. Then, we pivot to a practical workshop: how to author a spec-conformant skill from scratch, separate

en-us

23:45

Is Safety a Filter or a Feature?

My Weird Prompts ·

2026/04/06

In the race to secure large language models, two competing philosophies have emerged: external guardrails that act as a firewall, and constitutional AI that embeds safety directly into the model's weights. This episode explores the trade-offs between auditability and robustness, latency and training cost, and the real-world implications for developers and regulators. We break down why the industry is moving toward a hybrid approach and what it means for the future of AI deployment.

en-us

24:18

MoE vs. Dense: The VRAM Nightmare

My Weird Prompts ·

2026/04/06

The AI world is obsessed with Mixture of Experts models, but dense transformers are quietly staging a comeback. This episode breaks down the brutal tradeoffs: MoE wins on training compute but loses on VRAM, fine-tuning stability, and edge deployment. We explore why the "free lunch" of massive parameter counts comes with a hidden tax, and where each architecture actually makes sense for developers.

en-us

21:25

The Transformer Trinity: Why Three Architectures Rule AI

My Weird Prompts ·

2026/04/06

Explore the three distinct transformer architectures that power modern AI: encoder-only, decoder-only, and encoder-decoder. Learn why models like BERT excel at understanding text while GPT dominates generation, and discover the specific niches each architecture occupies in today's AI landscape.

en-us

21:01

Why Run One AI When You Can Run Two?

My Weird Prompts ·

2026/04/06

Inference latency is the biggest bottleneck for deploying large language models. This episode explores speculative decoding, a clever technique that uses a small draft model to predict tokens ahead of time, which a larger model then verifies in a single pass. Learn how methods like Medusa, EAGLE, and Mamba hybrids achieve 2-6x speedups without sacrificing quality, and why this matters for real-time AI applications and GPU economics.

en-us

23:24

Why GPT-5 Is Stuck: The Data Wall Explained

My Weird Prompts ·

2026/04/06

We trace the history of AI scaling laws, from the early optimism of the 2020 Kaplan paper to the cold, hard reality of DeepMind's 2022 Chinchilla paper. Discover why GPT-3 was an "empty vessel," why a smaller, well-read model beats a giant one, and why the industry is scrambling for data as it hits the limits of human-generated text.

en-us

23:11

That $500M Chatbot Is Just a Base Model

My Weird Prompts ·

2026/04/06

We break down the astronomical cost of LLM pretraining, the massive gap between raw base models and the chatbots you use, and why the compute divide is reshaping AI. From 100,000 GPUs to data cleaning, discover what you're really paying for when you ask a question.

en-us

21:51

How Transformers Learn Word Order: From Sine Waves to...

My Weird Prompts ·

2026/04/06

Why do transformers need special tricks to understand word order? This episode dives into the math behind positional encoding—from the original sine waves to learned embeddings, ALiBi, and the modern RoPE standard. Learn how these methods enable massive context windows and why RoPE is now the go-to choice for models like Llama and GPT-4.

en-us

22:43

How Attention Variants Keep LLMs From Collapsing

My Weird Prompts ·

2026/04/06

Why do LLMs need different types of attention mechanisms? This episode explores the evolution from Multi-Head Attention to Multi-Query, Grouped-Query, and Multi-Head Latent Attention. We break down the QKV framework, the memory bottlenecks of the KV cache, and the architectural tradeoffs that define modern AI efficiency.

en-us

22:58

The Tokenizer's Hidden Tax on Non-English Text

My Weird Prompts ·

2026/04/06

We explore the invisible machinery of tokenization, the hidden bottleneck in AI that dictates speed, cost, and language capability. From BPE to SentencePiece, we break down why non-English text often carries a higher computational tax and how modern tokenizers like tiktoken are optimizing for a multilingual world.

en-us

24:51

The npm Cache Is Breaking Your AI Agents

My Weird Prompts ·

2026/04/06

When you publish an update to npm, you expect your AI agents to receive it immediately. But npx has a hidden caching mechanism that can leave your tools running stale, vulnerable code for up to 24 hours. We explore the "silent stale" problem, the dangers of the "Headless Hang," and why the npm registry isn't built for autonomous agents. Discover the workarounds developers are using to force updates and secure their AI workflows.

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