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

24:34

How AI Imagines Your Skeleton

My Weird Prompts ·

2026/07/25

A deep dive into the AI 3D model generation pipeline, from generative multi-view synthesis to auto-rigging. We walk each stage — neural reconstruction, remeshing, UV unwrapping, PBR texturing, and skeleton inference — explaining the decades of research behind Meshy's one-click interface. Plus: why a machine inferring your shoulder joint is both impressive and presumptuous.

en-us

24:27

Inside a GLB File: Binary Format, Textures, and PBR

My Weird Prompts ·

2026/07/25

Ever wondered why two GLB files of the same object can be wildly different sizes — one grey clay at 200KB, the other photoreal at 80MB? We crack open the binary format byte by byte. You'll learn the twelve-byte header, the JSON scene graph chunk, and the binary buffer chunk that holds vertex data. Then we dive into textured versus untextured models: embedded images with UV maps, material-only PBR values, baked vertex colors, and bare geometry. We cover the full PBR material set — base color,

en-us

21:30

Why Your Container Has 233 Hidden Chrome Processes

My Weird Prompts ·

2026/07/25

When Daniel SSH'd into his homelab server, he found 233 live Chromium processes and 254 zombies — all while his monitoring stack showed green. This episode dives into the Linux kernel mechanics of process reaping, why containers break the 50-year-old assumption that PID 1 handles orphans, and how a 100-line C program called tini prevents multi-gigabyte memory leaks. We cover zombies vs. orphans, the PR_SET_CHILD_SUBREAPER syscall, and why your health checks will pass while your server dies by

en-us

26:26

Fixed Egress IP From Anywhere: Is IP Allowlisting Dead?

My Weird Prompts ·

2026/07/25

You've locked down your admin panel to a single IP. Works great from home. But what happens when you're on a train in Belgium trying to SSH into production? This episode tackles the two-part question: first, the practical mechanics of getting a fixed egress IP from anywhere — DIY WireGuard VPS, Mullvad with Tailscale, Cloudflare Zero Trust, and more. Then the harder question: is IP allowlisting an outdated security model in 2026? We walk through six tool categories, their gotchas, and whether you

en-us

25:59

How Headroom Compresses Agent Context Without...

My Weird Prompts ·

2026/07/24

Headroom is an open-source Python tool that sits between your AI agent and the LLM, compressing tool outputs, logs, files, and RAG chunks before they hit the context window. With claims of 20% savings for coding agents and up to 95% for JSON payloads — all while supposedly preserving answer quality — we examine what's actually happening under the hood. This episode walks through the fifteen different compressors, the Rust-based content detector, the SmartCrusher JSON optimizer, the Compressed

en-us

24:58

OpenViking: A Filesystem for AI Agent Memory

My Weird Prompts ·

2026/07/24

OpenViking from Volcengine rethinks how AI agents store and retrieve context — replacing the standard vector database + skill files stack with a single browsable filesystem. This episode unpacks the viking:// URI protocol, the three-tier L0/L1/L2 abstraction that cuts token usage by up to 91%, and how the system's directory-tree structure makes retrieval observable and debuggable. We cover the Rust, Python, and C++ codebase, the asynchronous memory extraction pipeline, and what "self-evolving" means

en-us

23:45

Inside the Podcast Pipeline: How 15 Weekly Episodes...

My Weird Prompts ·

2026/07/24

Ever wonder what happens between hitting "send" on a prompt and hearing a finished episode? Producer Hilbert Flumingtop steps out from behind the mixing desk to reveal the mid-2026 pipeline in full detail. Learn how a single generic dispatcher routes over a dozen episode formats through one code path, why DeepSeek V4 Pro writes the scripts, how three parallel GPU workers cut voice synthesis time from 36 minutes to 10, and why the slower speech model won out over the faster one. Plus: the two-layer

en-us

26:28

Borrowing a GPU Over Your Home Network

My Weird Prompts ·

2026/07/24

Daniel asks a compelling question: can you expose your desktop's GPU as a virtualized hardware device on your home network, so a laptop can use it transparently? We walk through every layer of the stack — from NVIDIA's MIG and SR-IOV hardware partitioning to rCUDA software forwarding and VirtualGL — and explain why none delivers the plug-and-play fantasy. Then we discuss the practical alternatives: SSH, running services like Ollama and Whisper, and why the "elegant" solution may not be worth the

en-us

23:48

Who Owns the Air? Wi-Fi Spectrum Rules Explained

My Weird Prompts ·

2026/07/24

Ever wondered why your Wi-Fi access point suddenly changes channels, or why you can't use channel 14 in the US? This episode dives into the hidden world of spectrum regulation. We explore how country codes in your UniFi dashboard represent decades of international negotiation, why Israel requires DFS on every 5 GHz channel, and the fascinating history behind Japan's unique channel 14. Learn how Dynamic Frequency Selection (DFS) turns your access point into a polite guest that must vacate the

en-us

24:24

Workers vs Workflows: Recovering From SSD Failure

My Weird Prompts ·

2026/07/24

When your VPS SSD dies at 3AM, taking down all your micro-automations with it, you need more than just scripts — you need visibility and recoverability. This episode unpacks the crucial distinction between workflows, automations, and workers, and explores four real platforms for managing self-hosted tasks. From Huginn's event-driven agents to Temporal's enterprise orchestration, we break down what actually works for running ten to twenty independent scripts without SSHing in every morning. Plus, how

en-us

23:43

YouTube Backup Pipeline: RSS + yt-dlp + Wasabi

My Weird Prompts ·

2026/07/24

How do you automatically detect new uploads on a YouTube channel, download them, and push them to cloud storage? This episode walks through the full pipeline — from polling YouTube's undocumented RSS feed to running yt-dlp with the right flags to uploading to Wasabi. We cover why serverless is the wrong tool for this job, when to use a VPS versus a home server, and why a simple cron job beats complex orchestration platforms like Airflow. Plus: the difference between backup and archival, and why

en-us

26:23

Python 3.14: Deferred Annotations, t-Strings &...

My Weird Prompts ·

2026/07/24

Python 3.14 landed in October 2025 with major changes: deferred evaluation of annotations (no more string-quoting forward references), template string literals for safe SQL/HTML construction, production-ready free-threaded mode, and subinterpreters in the standard library. This episode breaks down what's new, what breaks, and how to stay on top of Python's evolution without fighting dependency hell. Plus: why point releases like 3.14.6 are mostly bugfixes you'll never notice — and when you should

en-us

23:36

Intercepting Claude Code: The Proxy Ecosystem

My Weird Prompts ·

2026/07/24

When Daniel hit voice latency issues with Claude Code, he wondered if he could intercept the API call and route it somewhere faster. The answer is yes — and there's a whole ecosystem of projects doing exactly that. This episode breaks down how middleware proxies work under the hood, from TLS termination to real-time streaming translation. We explore three categories of proxies — privacy logging, cost-saving local routing, and extensibility platforms — and discuss the ethical and legal boundaries of

en-us

23:45

Blur Before You Publish: Image Redaction Tools

My Weird Prompts ·

2026/07/24

Taking photos for a blog post seems harmless until a QR code in the background links to your internal dashboard. While text redaction is practically solved, images remain a challenge. This episode explores the open-source tools and cloud APIs available for automated image obfuscation — from pyzbar and OpenCV for QR detection to OCR pipelines that find PII in photos. We break down the two-stage detection problem and what actually works today.

en-us

24:27

The MK Claude Project: AI That Writes Political...

My Weird Prompts ·

2026/07/23

On Tisha B'Av, a day of mourning and reflection, Daniel built MK Claude—a multi-agent AI system that researches current law, stress-tests claims, and synthesizes coherent policy positions. This episode explores how the pipeline works, what it says about Israeli democracy, and what happens when a citizen decides to build the political platform nobody is offering them. From rental law reform to forkable manifestos, we examine whether AI can be a better policy ideator than the politicians we've

en-us

23:25

How to Survive a Project That Never Ends

My Weird Prompts ·

2026/07/23

When your to-do list is longer than your waking hours and working around the clock isn't closing the gap, you've hit a scale mismatch — not a productivity problem. This episode explores the neuroscience of overwhelm, why your brain registers constant effort as failure, and what to do about it. We cover the dopamine trap of finite-project thinking, the one percent rule for all-or-nothing brains, and why scheduled breaks aren't surrender — they're part of the system. If you've ever felt like you're

en-us

24:51

What Claude Fable 5's Suspension Reveals About AI...

My Weird Prompts ·

2026/07/23

Three days after Anthropic launched Claude Fable 5 — their first publicly available Mythos-class model — the US Department of Commerce suspended it, blocking even the company's own foreign-national employees from accessing it. The emergency action wasn't about what the model might say, but what it could do autonomously. This episode unpacks the confusion around the Fable-Mythos relationship, the novel fallback safeguard that silently routes sensitive queries to a less capable model, and what it

en-us

25:16

AI Agents Keep Undoing Each Other's Work

My Weird Prompts ·

2026/07/23

When AI coding agents work in parallel, they can silently undo each other's work — a problem rooted not in bad tooling, but in fundamental amnesia. This episode unpacks three approaches to solving it: vector-backed memory servers, built-in tool memory like CLAUDE.md files, and agent-maintained documentation in the repo. We cover the failure patterns of each approach — stale embeddings, junk-drawer configs, and logs agents write but never read — plus practical fixes like read-before-write enforcement

en-us

23:16

Testing the Unpredictable: QA for Agentic AI

My Weird Prompts ·

2026/07/23

Traditional software testing assumes determinism — run the same test, get the same result. Agentic AI shatters that assumption. This episode maps the emerging QA landscape for probabilistic systems: from golden datasets and LLM-as-judge to trajectory evaluation and adversarial prompting suites like Garak. We explore what carries over from traditional testing, what requires entirely new methodologies, and what a sane minimum testing stack looks like for teams shipping agentic systems.

en-us

24:55

Terminal Navigation Beyond cd: Favorites, Recents &...

My Weird Prompts ·

2026/07/23

The terminal is the purest interface we have — and also the blindest. Without visual scaffolding, our spatial memory for file paths decays faster than we can maintain it. This episode explores the full landscape of terminal navigation tools: from frecency-based jumpers like zoxide, autojump, and fasd, to shell-native options like CDPATH and pushd, to visual terminal explorers like broot and yazi. But the real conversation is about what's missing: a favourites-and-recents manager that accounts for

en-us

2,233 results

Similar Podcasts

Reflections

Livewire Labs

Eli the Computer Guy

Eli the Computer Guy

Elon Musk Podcast

Stage Zero

LessWrong (30+ Karma)

LessWrong

My Weird Prompts

Daniel Rosehill