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

34:09

Building a Unified AI Filesystem with Rclone and MinIO

My Weird Prompts ·

2026/08/12

Daniel wants a unified virtual filesystem on his home server — one namespace where AI agents can reach any file across shared drives, S3 buckets, and MinIO. This episode breaks down the full architecture: where MinIO should sit, why rclone union beats mergerfs for cloud remotes, and how to handle silent token refresh so agents never hit an auth wall at 3 AM. We cover the dependency chain between union layer, access protocol, and front-end choice — plus a middle path that keeps MinIO useful as a

en-us

25:30

MCP Binary Payloads: Why URLs Beat Base64

My Weird Prompts ·

2026/08/12

Daniel's aggregated MCP setup keeps hitting the same wall: remote tools need binary files, but MCP is JSON-RPC and can't express raw bytes. In this episode, we break down the three ways to represent binary data in MCP, why the stage-and-pass-a-URL pattern isn't a workaround but the protocol's maximum expression, and whether the transport underneath actually matters. Plus, we look at the File Uploads Working Group and the three possible directions for closing this gap—and why the aggregation layer

en-us

23:36

Two Books, One AI Podcast: The Full Archive

My Weird Prompts ·

2026/08/12

Hilbert walks into the studio holding two brand-new paperbacks: the complete production documentation for the My Weird Prompts AI pipeline, and a printed index of all 4,620 episodes published to date. He explains how the books came together over six months, what writing them down revealed about the system's quiet failures, and why making the invisible archive physical matters. Plus: the permanent six-digit episode codes, the ad mechanism that ran on its fallback for months, and what the books say

en-us

18:30

Why Claude Code Re-Introduces Itself to Your Repo

My Weird Prompts ·

2026/08/12

Ever wonder why Claude Code re-scans your repository every session, even when nothing's changed? This episode unpacks the distinction between instruction memory and structure memory, and why the harness optimizes for freshness over recall. We explore the third-party tools that already solve this problem — Aider's repo maps, repomix, context7, and MCP servers — and the system-prompt hacks that can wire them in. Plus, we discuss the real frontier: judgment memory, the institutional knowledge no tool

en-us

24:12

Browser Agents: Three Paths to One Protocol

My Weird Prompts ·

2026/08/12

Browser AI agents are fragmented across three approaches: pixel-watching screenshots, fragile dev-tools extensions, and Google's new native MCP support in Chrome. We break down why the visual method is systematically blind to network failures, why extensions are a maintenance nightmare, and how a single open protocol could consolidate the entire ecosystem. The browser isn't just a display surface anymore — it's becoming an instrumented environment that speaks the agent's language.

en-us

24:53

The Hidden Engine: What Makes Claude Code Tick

My Weird Prompts ·

2026/08/12

When Claude Code feels smarter, is it the model or the harness? This episode unpacks the invisible engineering — tool grounding, context compaction, error recovery, and task decomposition — that turns a language model into a true agent. We explore why the distinction matters for developers, how harness improvements ship faster than model updates, and what it means for evaluating AI tools. If you've ever wondered why your AI assistant feels like it's growing up, this is the episode for you.

en-us

27:35

What a Business Fibre SLA Actually Guarantees

My Weird Prompts ·

2026/08/11

When you move from consumer fibre to Dedicated Internet Access, the contract becomes the product. This episode breaks down how DIA circuits are packaged and priced — the committed information rate, port speed, access tail costs, and the SLA fine print that most buyers never fully parse. We dig into what uptime percentages actually allow, how repair clocks really start, and why the credit structure often means businesses don't bother claiming. If you've ever priced a business circuit and wondered

en-us

22:54

Why Your Speed Test Lies About Your Internet

My Weird Prompts ·

2026/08/11

That big download number on your speed test? It's measuring the best-case scenario — and hiding the problems that make your connection feel terrible. We dig into bufferbloat, latency under load, jitter, and packet loss, and the free tools that actually reveal whether your line holds up under real use. Plus, the router fix that's been around for over a decade but almost nobody has deployed.

en-us

27:11

Why AI Over-Explains Simple Tasks

My Weird Prompts ·

2026/08/11

Ever asked an AI for a quick summary and received a dissertation? This episode unpacks the "addition bias" in large language models — the tendency to add complexity when simplicity is needed. We trace it back to training data and reward signals that favor thoroughness, then explore why current architectures lack a "throttle" for task difficulty. From Claude documenting a home network to over-engineered code, we look at the engineering challenges of teaching models to calibrate their effort, and what

en-us

30:30

The Unfenced Runway: When Airfields Blend Into Town Life

My Weird Prompts ·

2026/08/11

Most of us picture airports as sterile fortresses — scanners, patrols, and perimeter fences. But thousands of airfields worldwide operate on the opposite model: no fence, no security staff, just a windsock, a painted line, and pilots trained to check for obstacles like pedestrians with groceries. In this episode, we explore the spectrum of aviation security through a County Cork lens — from the tightly patrolled perimeter of Cork Airport to the open runway at Bantry, where pharmaceutical freight

en-us

27:40

The Hidden Light System That Guides Pilots Home

My Weird Prompts ·

2026/08/11

Ever wondered about the giant light arrays stretching out from runways? This episode explores approach lighting systems — the high-intensity, redundantly-powered beacons that guide pilots through fog and darkness. From their origins in 1920s airmail routes to the engineered precision of modern ALSF-2 systems, we cover the history, the physics, and the jaw-dropping construction challenges — including airports like JFK that build light jetties out into the ocean.

en-us

21:22

Can You Live Entirely on Amazon?

My Weird Prompts ·

2026/08/11

What happens when you try to route an entire human life through a single retailer's supply chain? We plan it out — food, clothing, shelter, transport — and hit the structural gaps that don't fit in a box. From prescription prerequisites to the delivery driver who starts to piece together your whole existence, this is a thought experiment that turns into a dependency graph. The catalog is vast, but "everything" is a moving target.

en-us

24:18

Why Printed Colors Never Match Your Screen

My Weird Prompts ·

2026/08/10

Ever hit print and get colors that look nothing like your screen? This episode breaks down the physics of additive vs. subtractive color, the role of ICC profiles and rendering intents, and why rich black isn't just 100% K. We also cover practical fixes like soft-proofing, bleed, safe margins, and resolution for books versus banners. If you've ever been frustrated by a muddy print, this is for you.

en-us

25:52

The Machine Lane: When AI Agents Call Your Business

My Weird Prompts ·

2026/08/10

Every business publishes a phone number. Almost none publish machine-readable endpoints for AI agents. In this episode, we explore a deceptively simple idea: a phone tree branch explicitly for AI callers — press six if you're an agent, skip the audio prompts, get a structured handshake in seconds. We dig into the industry's current brute-force approach, the DNS-based alternatives, and why the absence of this idea says more about timing than viability.

en-us

23:47

Typst for Agents: Programmatic PDF Generation

My Weird Prompts ·

2026/08/10

Daniel and Herman explore Typst's full capability surface for programmatic PDF generation—from page geometry and typography to tables, cross-references, and the scripting layer that makes it all programmable. They break down what's genuinely easy versus where you still fight it, and what a sensible pipeline looks like when an AI agent—not a person—is writing the document. If you're building document generation into an agent workflow, this episode maps the entire territory.

en-us

33:48

Bootable Standby Drives: The Ship of Theseus Server...

My Weird Prompts ·

2026/08/10

When Daniel's server suffered a cascading hardware failure, he replaced every single component — then faced the storage question. Instead of rebuilding a RAID array, he wants a permanently installed SATA SSD that can serve as a bootable standby copy of his system. We break down the established pattern, the tools, and the exact steps to make a standby drive that actually boots when you need it. No fragile hacks, no reinventing the wheel — just practical Linux recovery planning.

en-us

20:02

Why 3,000 Episodes Vanished From Spotify (And Came Back)

My Weird Prompts ·

2026/08/10

A listener asked where December went, and the answer revealed a self-imposed feed cap that hid 4,300 episodes from Spotify. We walk through how the cap worked, why it took an afternoon of panic to fix, and where the full catalogue actually lives — plus how to install MWP FM, what 112 GB of podcast actually feels like on your phone, and the email digest that outsmarts Gmail's clip limit.

en-us

25:30

Bonding Cellular Connections: Why Can't You Buy It?

My Weird Prompts ·

2026/08/10

Daniel asks why he can't buy a device that bonds multiple cellular carriers into one fast, reliable connection. We break down the DIY path — Linux box, two USB-tethered phones, a cheap VPS, and MPTCP — and explain why the tech has existed for 14 years but nobody sells it to consumers. From middlebox interference to the economics of hardware startups, we unpack the gap between what's possible and what's buyable.

en-us

26:06

How Claude Code's Patience Works: Fork, Wait, and the...

My Weird Prompts ·

2026/08/10

When Claude Code says it's waiting for a deploy, it's not actually waiting. The model is stateless—it exists in bursts—so the framework constructs the appearance of patience by backgrounding processes and handing the model a receipt. In this episode, we trace the entire mechanism: the Bash tool's timeout that doesn't kill, the Monitor tool's event-driven watching, and the reaping that cleans up orphans. Then we map it all onto Unix primitives—fork, nohup, tail -f, select, SIGCHLD—and find where the

en-us

23:05

GitHub vs AWS: Agentic AI Cert Showdown

My Weird Prompts ·

2026/08/10

Daniel wants a head-to-head: GitHub's Certified Agentic AI Developer (GH-600) versus AWS's AI certification pathway. We crack open both syllabi to see what's actually tested, where the vendor lock-in hides, and which credential teaches skills that survive outside its ecosystem. If you're deciding where to spend your study hours in 2026, this episode maps the tradeoffs.

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