Daniel Rosehill
My Weird Prompts
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 mind-bending. Each episode begins with a real voice memo from Daniel, processed through an AI pipeline that...
Be sure to visit the podcast's website and support the creator: myweirdprompts.com
Author
Daniel Rosehill
Category
Podcast website
Latest episode
Nov 19, 2026
Where to listen?
Podcasts in the app Replaio Radio Coming soonPodcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts
Episodes
Why Extra Voice Hours Settle Bilingual Speech 28.10.2026 23:10
Fine-tuning a massive speech model like Parakeet TDT on personal speech can yield dramatic gains with modest datasets, dropping code-switched word error rates from 13.7% to under 5%. How data maturity stages work, why repeated vocabulary adds acoustic resilience rather than redundant weight, and how models handle Hebrew-English code-switching without regressing on base English recognition are expl...
Backing Up Gmail with Got Your Back 28.10.2026 23:47
Downloading your own email locally turns out to require an entire Google Cloud project and an OAuth consent screen. This look at mailbox pipelines contrasts one-off Google Takeout archives with repeatable tools like Got Your Back and GAM. It covers how incremental EML backups work, how restore operations handle deleted mail without duplicating existing threads, the quirks of external OAuth test mo...
Why WhatsApp Business Backups Cannot Form an Archive 28.10.2026 26:50
Small businesses relying on client groups in WhatsApp Business often treat restore points as readable records. Examining standard cloud backups, linked devices, and tools like wtsexporter or iMazing reveals a fundamental gap: the platform offers restore points tied to active phone numbers, but no sanctioned method for automated, independent archiving. Preserving client correspondence and attachmen...
How Israel Actually Regulates Foreign Drugs 28.10.2026 22:03
Israel’s Health Ministry does not simply rubber-stamp decisions from the FDA or EMA. Regulators rely on unredacted assessment reports from six recognized authorities, requiring local dossiers to remain practically identical to foreign filings. The regulatory process, local packaging rules across four languages, and recent reliance pilot tracks shorten review times from hundreds of days down to sev...
Why Inhalers Never Combined Allergy Drugs 28.10.2026 23:11
Asthma inhalers have relied on the same core steroid and bronchodilator pairings for decades, rarely combining allergy-specific treatments into the same canister. Inhaled corticosteroids already suppress multiple inflammatory pathways, setting an unusually high bar for targeted additions like cromolyn or montelukast to show meaningful clinical benefits. While modern maintenance therapies expanded...
Why Common Colds Cause Asthma Flare-Ups 28.10.2026 28:15
Viral infections frequently trigger asthma exacerbations, but the molecular mechanisms reveal an unexpected asymmetry. Rhinovirus can drive airway epithelial cells into severe inflammatory overdrive while simultaneously hobbling their ability to produce antiviral interferons and clear the pathogen. This breakdown covers what actually happens inside inflamed lungs, why air trapping makes exhaling d...
Choosing Ergonomic Inputs for Working in Bed 28.10.2026 22:50
Working from bed exposes the hidden floor-space requirements of standard ergonomic pointing devices. Tackling an eighteen-month email backlog demands reliable bulk selection without strained reaching. This review examines practical bed-friendly computing setups, comparing firm lap trays, thumb trackballs like the Logitech MX Ergo S and ProtoArc EM01 NL, integrated trackpad boards like the Logitech...
Can Diplomacy Repair Economic Isolation? 28.10.2026 29:43
Fragmented European trade restrictions, post-election deadlock, and conflicting statements from officials have created unprecedented commercial friction. An examination of settlement trade bans in Spain and the Netherlands reveals how piecemeal rules drive corporate overcompliance long before formal banking sanctions arrive. Resolving these disputes requires distinguishing policy-driven trade limi...
Why Israeli Youth Moved Right 28.10.2026 28:27
The assumption that younger generations naturally tilt liberal breaks down in Israeli politics, where up to three-quarters of new voters identify with the right. An examination of recent election polling, cohort research by Liran Harsgor, and insights from Alon Yakter explores what drives this political shift. It unpacks the roles of physical separation, changing media habits, and differential fer...
Why Early Israeli Election Tallies Skew Right 28.10.2026 22:43
Early election counts can shift dramatically overnight, but not because voters changed their minds after polls closed. The national tally updates as complete polling stations report, meaning initial figures reflect small, fast-counting locations rather than a representative cross-section. The breakdown unpacks station-level reconciliation, transit delays to regional election committees, and the me...
Why Armies Began Enlisting Their Own Interpreters 28.10.2026 32:13
Military translation goes far beyond simple bilingualism, carrying immense cultural nuance and life-or-death operational consequences. Rather than relying solely on local civilian contractors or years of standard language school, the U.S. military launched initiatives like the 09 Lima specialty and the 51st Translator Interpreter Company. This look into military linguists examines how noncitizen h...
How Interpreters Speak While Listening 28.10.2026 31:12
Simultaneous interpretation requires listening, converting, speaking, and self-monitoring all at once under relentless time pressure. Cognitive load shifts continuously with sentence structure, forcing the left prefrontal cortex to prevent the source language from invading the output. Research shows experienced interpreters rely heavily on semantic anticipation, actively predicting upcoming concep...
Who Sets Identity Standards for AI Agents 27.10.2026 25:59
Standards bodies and consulting groups are currently racing to define non-human identity, credential rotation, and authorization for autonomous software. While advisory groups build community landscapes, concrete engineering specifications are emerging through IETF workload initiatives, OpenID Foundation threat models, and OASIS cross-domain delegation protocols. Examining the actual technical dra...
Tuning Hilbert Back from the Surreal 27.10.2026 10:38
Listeners noticed something strange when Hilbert began ranting about postal ballots for his staircase and committees for shutting down computer graphics cards. This look behind the scenes explains how vague prompting pushed an eccentric character over the edge into pure surrealism. By dialing back the instructions, the show grounds its fictional producer back in ordinary human stubbornness, nested...
Why Election Fraud Requires Your Opponent to Cooperate 27.10.2026 28:37
True election security relies less on body cameras and high-tech seals than on procedural tension between political rivals. From hand-counted slips tallied separately by opposing party representatives to the careful ordering of double-envelope ballots, administrative friction is designed to make discrepancies conspicuous. Looking at the mechanics of Israel's twelve thousand polling stations, this...
Choosing Model Precision, Quantization, and Format 27.10.2026 24:14
Download menus often present precision, quantization schemes, and file containers in a single list, obscuring how each piece functions. Model selection requires navigating numerical encodings like BF16 and FP8, reduction recipes like AWQ or Q4_K_M, and packaging standards like safetensors and GGUF. Understanding memory bottlenecks, runtime support across engines like vLLM and llama.cpp, and comput...
Why Protein Design Ignores Astronomical Counts 27.10.2026 22:02
Generative AI can churn out hundreds of thousands of candidate molecules, but evaluating these numbers requires facing the staggering scale of biological sequence space. Exploring the mathematics behind amino acid arrangements and chemical universes reveals why exhaustive searches are fundamentally impossible. The discussion breaks down how evolutionary reuse, energy landscapes, and automated desi...
Inside China's Mixed-Language AI Models 27.10.2026 28:49
Chinese AI looks vastly different beneath the surface of consumer apps. Despite assumptions of isolated linguistic training, domestic models from DeepSeek to CT-LLM rely heavily on multilingual data, English code, and shared international benchmarks. The investigation explores training recipes, the role of domestic compute clusters, and how regional languages like Kazakh and Uyghur fare inside Man...
Why Forgotten Runpod Workloads Keep Billing 27.10.2026 22:30
Standard cloud GPU accounts cannot drop into negative debt, but walking away from a running workload still brings costly surprises. This episode breaks down how Runpod handles zero balances, why stopped pods double their volume storage billing rates, and why deprecated CLI flags like stop-after failed to enforce deadlines. Learn how process exits differ from platform terminations and why auto-refi...
What Global Voter Turnout Trends Really Reveal 27.10.2026 24:29
Global voter turnout has faced a multi-decade slide, even as individual high-stakes elections still pull massive crowds to the polls. An examination of international voting data untangles why headline rates drop, how registration rules distort national rankings, and why compulsory systems like Australia differ from voluntary high performers like Malta. The discussion also explores post-communist p...
Choosing Between Modal, RunPod, and Vast.ai 27.10.2026 24:50
Fine-tuning open-weight models forces a choice between fundamentally different infrastructure models. This comparison examines how Modal, RunPod, and Vast.ai handle the actual mechanics of training runs, from persistent state and environment setups to hidden costs. Key topics include Modal's Python decorators and scale-to-zero billing, RunPod's Pod-based container workflows and Community pricing t...
How Transformers Process Images and Video 27.10.2026 29:48
Transformers originally built for language now power visual perception and image generation. Replacing convolutional networks with self-attention requires turning continuous pixels into discrete vector sequences, which Vision Transformers achieve by treating raw image patches like text tokens. Exploring architectures like ViT and Diffusion Transformers (DiT) shows how swapping inductive visual bia...
Why Model APIs Lack Dedicated Few-Shot Fields 27.10.2026 22:53
General model APIs treat few-shot demonstrations as raw text or chat messages rather than structured, versionable task artifacts. While specialized models like iAmTime and LoRA Recycle train directly on explicit demonstration structures, frontier LLM platforms rely on unstructured prompts, XML tags, or massive context windows. An examination of in-context learning shows why adding an examples para...
Why DeepMind Systems Live Outside the Gemini API 27.10.2026 25:51
Google DeepMind regularly announces breakthrough systems that never appear as simple endpoints in Google AI Studio or the Gemini API. Exploring systems like AlphaEvolve, Co-Scientist, Genie, and AlphaFold reveals why they are kept separate. The restrictions stem from serving costs, workflow requirements, and commercial strategy rather than mere secrecy, requiring specialized cloud setups, research...
How Google DeepMind Absorbed the Gemini App 27.10.2026 26:32
Google DeepMind is often treated as an academic research enclave, but recent reorganisations have turned it into Google's core consumer AI division. Tracing the trajectory from the 2023 merger with Google Brain to the October 2024 shift of the Gemini app team under DeepMind leadership, this episode unpacks the corporate reality behind the branding. It examines UK statutory accounts, leadership cha...
Similar podcasts
Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.