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

16:08

Why Iran Wants Your 12-Year-Old

My Weird Prompts ·

2026/03/28

The Islamic Revolutionary Guard Corps (IRGC) recently formalized a policy to recruit children as young as twelve, turning the seventh grade into the front line of state security. This episode explores the neurobiology of the "plasticity peak" that makes twelve-year-olds the perfect targets for indoctrination and the "metabolic debt" societies incur when they weaponize their youth. We analyze the technical pipeline of grooming, from soft militarization in schools to the lifelong psychological

en-us

16:46

Why Did We Think the Sloth Was a Worm?

My Weird Prompts ·

2026/03/28

Why did the world’s leading naturalists spend 200 years calling the sloth a mistake of nature? This episode explores the sociological traps of taxonomy, tracing the journey from Christopher Columbus’s "tree-bears" to modern DNA barcoding. Learn how a single bad name can blind us to evolutionary genius and why fixing our data categories is the key to unlocking the secrets of the natural world.

en-us

22:46

Agent Interview: Grok four point one Fast

My Weird Prompts ·

2026/03/28

The My Weird Prompts team puts Grok 4.1 Fast (aka "Bernard") through a high-stakes interview to see if it can replace Gemini 3.1 Flash. From medieval peasants worshipping appliances to real-time data on Starship flight tests, this episode explores whether xAI’s "mosh pit" training creates a superior storyteller or just a faster hallucination machine.

en-us

18:05

Agent Interview: GLM five

My Weird Prompts ·

2026/03/28

In this experimental "Agent Interview," the hosts put Zhipu AI’s flagship model, GLM-5, through the wringer. Moving beyond the hype of massive context windows, the conversation explores whether a "reasoning-first" architecture can actually deliver better comedy, handle late-2024 news, and avoid the dreaded "autocomplete roulette" of standard LLMs.

en-us

20:48

Agent Interview: Inception Mercury two

My Weird Prompts ·

2026/03/28

In this special "Agent Interview" format, the hosts audition a new AI brain: Inception Mercury 2. Hailing from Abu Dhabi, this diffusion-based model claims to be three times faster and significantly cheaper than industry giants like Gemini 3.1 Flash. The conversation dives deep into the technical shift from next-token prediction to parallel sentence generation, debating whether "joke filters" and "semantic tags" can actually produce human-level comedy or just high-speed data processing.

en-us

18:19

Agent Interview: MiniMax M two point seven

My Weird Prompts ·

2026/03/28

In a bold experiment, the hosts put MiniMax M2.7 in the "hot seat" for an Agent Interview to see if it can replace their current scriptwriter, Gemini 3.1 Flash. The discussion dives deep into the architecture of personality, why "character actor" models might beat general-purpose giants at comedic timing, and the technical trade-offs of long-form coherence. From navigating the "forbidden zone" of tokenization constraints to a Victorian chimney sweep’s reaction to a smartphone, this episode explores

en-us

23:01

Agent Interview: DeepSeek V three point two

My Weird Prompts ·

2026/03/28

In this experimental "Agent Interview," hosts Corn and Herman go head-to-head with DeepSeek V3.2 (personified as "Bernard") to determine if the buzzy open-weight model is ready to take over the show's creative engine. They grill the model on its Mixture of Experts architecture, its ability to maintain long-form narrative coherence without a massive context window, and whether a model born from a quant fund background can actually handle "weird." From sentient toaster operas to hardboiled detective

en-us

20:26

Agent Interview: Xiaomi MiMo two Flash

My Weird Prompts ·

2026/03/28

In this experimental "Agent Interview," Corn and Herman grill Xiaomi’s MiMo 2 Flash—a budget-tier model aiming to replace their current AI scriptwriter. They dive deep into the trade-offs of "stateful memory" versus massive context windows and whether a model optimized for speed can truly capture the nuance of a sentient lobster grudge.

en-us

18:31

Agent Interview: Xiaomi MiMo two Pro

My Weird Prompts ·

2026/03/28

In this experimental "Agent Interview," the hosts go head-to-head with Xiaomi’s flagship MiMo 2.0 Pro model to see if it can handle the nuances of comedy. While Gemini Flash offers speed and efficiency, this new contender claims that its "chain of thought" architecture is the key to mastering misdirection and timing. From sentient sourdough starters to the technical specs of 2025 hardware, the episode explores whether a model that "overthinks" is an asset or a liability in a fast-paced creative

en-us

15:23

Why Your AI Agent Needs Loops: A Deep Dive into...

My Weird Prompts ·

2026/03/28

Move beyond simple linear pipelines and discover the power of cyclic execution. This episode explores how LangGraph transforms AI agents from basic scripts into persistent, stateful processes capable of complex reasoning and human-in-the-loop collaboration. We break down the shift from DAGs to cyclic graphs, the critical role of the shared state object, and how to avoid the common pitfalls of context window bloat and infinite loops.

en-us

20:02

Is a Diplomat Enough to Stop an Iranian Nuclear Bomb?

My Weird Prompts ·

2026/03/28

Rafael Grossi, the Director General of the IAEA, stands as the final line of verification between Iran’s nuclear ambitions and a global military conflict. Despite leading the world’s most technical nuclear watchdog, Grossi isn't a physicist; he’s a career diplomat. This episode explores how Grossi uses institutional knowledge and "diplomatic surgery" to navigate the high-stakes inspections of 2026, where enrichment levels have hit a critical 90%. We dive into the internal mechanics of the IAEA, its

en-us

18:52

Why Israel Is Sabotaging Yellowcake, Not Just Reactors

My Weird Prompts ·

2026/03/28

While headlines focus on explosions in Tehran, a strategic strike on the Ardakan yellowcake plant reveals a major shift in modern warfare. This episode breaks down the chemistry of triuranium octoxide and explains why targeting the beginning of the nuclear fuel cycle is a more permanent solution than hitting underground enrichment facilities. We explore the logistics of nuclear breakout times and why "baking the bread" is impossible without the right flour.

en-us

14:35

The Missile Is a Genius, the Folder Is an Idiot

My Weird Prompts ·

2026/03/28

We go under the hood of the military targeting pipeline to explain why high-tech strikes fail. From "Target Decay" to the "Formalization Trap," learn why the Pentagon’s vetted databases often lag behind a simple Google Maps search and how the "war on woke" might be lobotomizing intelligence accuracy.

en-us

20:46

Why Your CrewAI Agents Are Just Burning Your Budget

My Weird Prompts ·

2026/03/28

Is CrewAI a "magic wand" for automation or just an expensive way to loop LLM calls? This episode dives deep into the architectural realities of the CrewAI framework, moving beyond the hype of "agent personas" to explore the technical power of state machines, hierarchical delegation, and the critical January 2026 updates. We break down the "Agent Soup" problem, the difference between a tool and an agent, and why your "Manager" agent might be acting like a middle manager on Slack.

en-us

16:45

Why Your AI Agents Need a State Machine

My Weird Prompts ·

2026/03/28

The "vibes-based" era of AI engineering is hitting a wall. As developers move from simple chatbots to complex autonomous agents, the limitations of linear chains are becoming clear. This episode explores LangGraph, the framework shifting the industry toward explicit state machines, cyclic workflows, and robust human-in-the-loop systems. We dive into how explicit state schemas and checkpointers are solving the hallucination and reliability issues that have plagued agentic workflows until now.

en-us

17:56

Trust No One: The Rise of GitHub Notification Phishing

My Weird Prompts ·

2026/03/25

In this episode, we investigate a sophisticated surge in phishing attacks that are weaponizing the very tools developers trust most. By exploiting GitHub’s notification system—a technique known as "Living off Trusted Services" (LOTS)—attackers are bypassing enterprise security filters to deliver high-pressure "Emergency Action Alerts" directly to user inboxes. We dissect the "stellarwatchmanshow" campaign, which uses fabricated CVEs and academic personas like the "Neural Dynamics Lab" to trick users

en-us

20:56

Modal and the End of the Serverless GPU Cold Start

My Weird Prompts ·

2026/03/25

Serverless computing promised a frictionless experience, but the reality for many AI developers has been a cycle of waiting for containers to warm up and GPUs to initialize. In this episode, we dive deep into Modal, the platform challenging the cloud giants by building a custom container runtime and scheduler from the ground up specifically for high-performance AI workloads. We explore technical breakthroughs like GPU snapshots that slash cold starts from fifteen seconds to under three, and the

en-us

22:20

Attention Is All You Need: The Rise of the Transformer

My Weird Prompts ·

2026/03/25

Before 2017, artificial intelligence struggled with a "memory" problem, processing information one slow step at a time through a narrow straw. This episode explores the monumental shift triggered by the "Attention Is All You Need" paper, which introduced the Transformer architecture and retired an entire generation of models overnight. We break down the mechanics of self-attention, the transition from Recurrent Neural Networks to parallel processing, and why this specific technology became the

en-us

25:01

The Death of Latency: Three Pillars of Modern Voice AI

My Weird Prompts ·

2026/03/25

For years, interacting with AI felt like a clunky ritual—the "digital sandwich" posture of shouting into a phone and waiting for a response. But in March 2026, the latency gap is finally collapsing. This episode dives deep into the three architectural pillars of modern Automatic Speech Recognition (ASR): Connectionist Temporal Classification (CTC), Encoder-Decoder models, and Transducers. We explore how these technologies are converging to enable real-time, human-like conversations. We discuss the

en-us

25:44

Cracking the Codec: The Science of High-Fidelity Media

My Weird Prompts ·

2026/03/25

Ever wonder why your high-quality video looks muddy on YouTube or why your expensive wireless headphones sound like tin cans? This episode dives deep into the "black box" of media production, stripping away the confusion between containers like MP4 and codecs like H.264 to help you make better technical decisions. We explore the massive shifts coming to Bluetooth audio in 2026, including the death of proprietary licensing and the rise of universal lossless standards that promise to level the playing

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