PODCAST · technology
My Weird Prompts
by 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 mind-bending. Each episode begins with a real voice memo from Daniel, processed through an AI pipeline that generates scripts, synthesizes voices, and assembles the final podcast. Stay curious.
Episodes
-
Where Your Prompts Actually Go
Tracing where a model execution happens reveals a stark divide between where data is stored and where GPUs compute answers. The public documentation for Anthropic and OpenAI separates data residency from inference geography, with cloud marketplaces like AWS offering different boundaries than…
more -
How Surveillance Turns Routine into Identity
Pattern-of-life analysis flips traditional investigation on its head: instead of tracking known suspects, systems like Activity-Based Intelligence filter daily habits to nominate unknown targets. Surveillance methods assemble timelines, dwell times, and routes using tools like wide-area motion...
-
Routing Claude Code Tasks to Local Ollama Models
Claude Code lacks native support for pointing subagents at local inference servers, but developers are splitting traffic using two distinct architectural patterns. This discussion explores model-based proxy interception with tools like llm-router alongside explicit delegation via MCP servers like...
-
Where a Synthetic Voice Gets Its Accent
Speech synthesizers attached to neural interfaces derive their vocal traits from the human recordings supplied during calibration. An analysis of mixed acoustic traits reveals how composite training libraries create unexpected combinations of British, South Asian, and American phonemes. The...
-
Why Context Windows Stalled at a Million Tokens
Language model context windows grew thirtyfold a year before hitting a ceiling at one million tokens. Hardware limits explain why: storing and constantly reading massive key-value caches rapidly outgrows flagship GPU memory and bandwidth. Compounding the cost, real-world retrieval accuracy…
more -
How the Kilogram Leaves the Basement
Fixing the Planck constant redefined the kilogram in 2019, but turning an abstract mathematical definition into a reliable measurement still requires complex machinery and physical transfer standards. Metrology laboratories navigate the practical reality of realizing mass with Kibble balances and...
-
How Ancient Markets Fought Fraudulent Measures
Before standardized manufacturing, commerce depended on who controlled the tools of measurement. Across ancient markets, from biblical market pouches hiding mismatched heavy and light stones to Roman capacity laws like the lex Silia, cheating often happened before scales ever tipped. Examining...
-
Why Satisfaction Is Not Enough for a Good Life
Living well requires more than feeling satisfied or obeying rules. Drawing on Aristotle's concept of eudaimonia and Susan Wolf's account of meaningful engagement, this discussion explores how character, practical judgment, and worthy pursuits shape everyday life. A close look at virtue ethics…
more -
Why Caused Choices Can Still Count as Free Will
Compatibilism holds that deliberate actions driven by reasons remain meaningfully free even within a causally determined universe. The debate over moral responsibility separates local control from ultimate self-creation, examining classical thought experiments alongside modern neuroscience…
more -
Why Death Might Harm Us Without Hurting
Mortality raises difficult questions about whether being dead can actually harm the person who dies. While Epicurus argued that nonexistence cannot be bad because there is no subject left to experience it, Thomas Nagel countered that death is a misfortune of deprivation. Exploring the contrast...
-
Why Meaning Is Neither Pure Feeling nor Plain Duty
Meaning in life sits awkwardly between happiness and moral duty. Examining Susan Wolf's hybrid account—where personal attraction must meet objective worth—and Viktor Frankl's logotherapy reveals why purpose cannot be reduced to pleasant feelings or arbitrary goals. The discussion probes whether...
-
Why Is There Something Rather Than Nothing?
The fundamental question of metaphysics asks why anything exists at all instead of absolute nothingness. The investigation examines whether reality actually requires an explanation, or if treating absence as the default state misapplies ordinary human reasoning to the cosmos. Along the way, the...
-
Why Inference Engines Change Benchmark Scores
Switching an inference runtime can drastically alter an open model's performance without touching its weights. Examining engines like vLLM, llama.cpp, and LMDeploy reveals how subtle implementation details—including tokenization quirks, chat templates, layer sliding window attention, and...
-
When Your Fine-Tune Isn't Done Learning Yet
Your fine-tune's loss curve is dropping beautifully. So why is it still picking the wrong citation, drifting back into base-model habits halfway through an answer, or transcribing the same words wrong as the stock model? This episode works through what undertraining actually looks like in...
-
Inside the Mixture of Experts Router
Mixture of experts models are often pitched as an efficiency trick — activate a fraction of the network, get more capability per compute. But the interesting part is the gate itself: what happens when a token arrives and only a handful of experts get picked? This episode digs into the routing...
-
Training a Model on Your Own Taste
Daniel wants a model that generates episode titles and descriptions, learns from side-by-side button presses, and improves each checkpoint. Herman walks through what that pipeline actually is: an iterative preference optimization loop built on DPO (Direct Preference Optimization), with an…
more -
Why Your Synthetic Data Isn't as Diverse as You Think
Synthetic data generation has a hidden problem: each example looks fine, but together they teach your model a narrow slice of reality. This episode digs into cross-batch mode collapse, why temperature and personas underdeliver, and what actually expands coverage — from scenario planning to...
-
Gold vs Silver Training Data: What Makes Labels Trustworthy
Gold data means human-verified. Silver means machine-annotated. But what actually separates them, and how much human checking do you need before a generated batch becomes trustworthy? This episode digs into the staged workflow of generating data with an LLM, correcting a small sample by hand…
more -
Testing Synthetic Data Generators Before You Scale
Picking a synthetic data generator by model reputation is a trap — a brilliant problem-solver can produce terrible training material. This episode digs into AgoraBench, a benchmark that trains the same student model on each generator's output and measures how much of the performance gap it…
more -
Which AI Models Actually Generate Good Training Data?
Synthetic training data lives or dies on the generator behind it. This episode compares the instruction models actually available for the job — Qwen, DeepSeek, Llama, Mistral, and Gemma on the open-weight side, and the Claude Opus/Sonnet/Haiku and GPT-5.6 Sol/Terra/Luna tiers on the closed side —...
-
Small Models, Big Questions: When Cheap Fables Get Expensive
Small language models can generate three million fables at thirteen and a half cents per thousand, but the real question isn't price — it's whether the generator understands what it's making. This episode maps the parameter tiers from three billion upward, separating tasks where small models…
more -
Synthetic Logs Without Leaking Your Clients
Daniel has real agent-workflow logs full of his own projects and wants synthetic versions that preserve the rhythm and ambiguity without advertising what he's working on. Corn and Herman walk through what purpose-built privacy tooling actually does that a plain rewrite prompt doesn't: which...
-
When Your AI Agent Has Too Many Skills
Installing a Claude Code skill is never free: its name and description take up permanent space in the agent's context, even if it's never used. As skill libraries grow, agents end up spending their working memory on metadata instead of the actual job. This episode digs into progressive disclosure…
more -
Phone Mic Beats a Dictation Mic: How?
A dedicated dictation microphone losing to a phone is expensive feedback — so what happens when you try to keep using the phone's mic at your desktop? This episode digs into the gap between "sending audio" and "sending the audio that actually won the benchmark," why Android's recording path…
more -
Fibromyalgia's 26 Genetic Clues
Fibromyalgia affects millions, yet it was long dismissed as a diagnosis of exclusion. A July genetic study of 2.5 million people identified 26 associated genome regions and pointed squarely at the central nervous system, while a major drug review this month delivered far less encouraging news.…
more -
Daycare Germs: What Immunity Actually Means
Building immunity" gets said like a consolation prize every time a toddler brings home another cold. But what physically changes after an infection, and why doesn't it feel like progress when the whole household is sick? Drawing on a Clinical Microbiology Reviews paper, a Québec household...
-
Why a Cold Makes Your Whole Body Ache
You caught a cold in your nose — so why do your legs ache like you ran a marathon? This episode unpacks the biology of sickness behavior: how cytokines like interleukin-6 and tumor necrosis factor turn a local respiratory infection into whole-body exhaustion, fever, and pain. We trace the…
more -
Why Synthetic Speech Needs Fake Room Noise
Synthetic speech can stop completely between sentences, leaving gaps of true digital black that sound unnatural on playback. This episode digs into why engineers fill those holes with room-tone beds, how a real fix for this show landed around minus sixty dBFS on a phone, and why a constant quiet...
-
Voice Design: Casting Ogres and Radio Voices
Anyone can make a voice say a sentence. Designing one you can listen to for hours is a different problem. This episode breaks down how modern text-to-speech voice design actually works: the two families of methods (describe-and-preview casting versus reference-audio speaker embeddings), what the...
-
What 12GB of VRAM Can Actually Do Now
A Radeon RX 7700 XT owner gave up on running models locally six months ago — the context window filled instantly and the model lost the plot. But the models changed underneath him. This episode walks through the new memory arithmetic: why a 35B mixture-of-experts model with only 3B active can run...
-
Cork Chippers, Rooster Potatoes, and the Double Fry
Jackie Lennox's closed on Bandon Road after 73 years, and Cork has opinions. Plumber and Cork native Roy joins the show to explain what actually makes a proper chipper chip — the right potato, the double fry, beef dripping versus vegetable oil, and why a paper bag beats a polystyrene box. Along…
more -
Sarah Tuttle-Singer: The Writer Who Lives Inside the Story
Sarah Tuttle-Singer grew up on Yiddish lullabies and civil rights anthems in Venice Beach, the daughter of a Freedom Rider who spied on the Klan before auditing Los Angeles City Hall. Today she lives inside the walls of Jerusalem's Old City, writing first-person dispatches from the middle of the...
-
Reading the Iran Signal: Jets, Leaks, and the Midterm Deadline
Dozens of Israeli fighter jets and refueling tankers reportedly flew roughly 1,300 kilometers toward Iran through Syrian and Iraqi airspace — and turned around before reaching Iranian territory. The same week, Pete Hegseth made an unannounced visit to the Negev to meet Netanyahu, and Trump's...
-
Marcus James: Jerusalem's Spiritual Mayor
What does it take to become a city's "spiritual mayor" without winning a single vote? Daniel makes the case for his friend Marcus James — raised in Santa Barbara, a Kerouac-reading hitchhiker who studied philosophy, converted to Judaism in 2020, and moved to Israel in 2022. The episode traces his...
-
How Many Epochs Does Fine-Tuning Actually Need?
Almost nobody picks an epoch count in advance — they set a ceiling, evaluate often, keep the best checkpoint, and the epoch count is whatever that turns out to be. This episode works through two concrete cases: a Whisper speech fine-tune scored on word error rate, and an instruction-tuned…
more -
Why Fine-Tuning Runs Can't Always Resume
Daniel has been fine-tuning NVIDIA's 600M-parameter Parakeet on his own read-aloud recordings, English with Hebrew mixed in. Each run costs about eighty cents and twenty-five minutes on a single L40S, so retraining from the stock model is cheap — but that raises a tangle of questions: what's...
-
How Many Examples Does Fine-Tuning Actually Need?
A listener has 150 hand-labelled dictated prompts and wants to know if that's a start or a third of what he needs — and his architect wife has the same question about photographs of buildings. This episode works through the real answer: count examples per label, not in total; treat vendor…
more -
Mixture of Experts: Bigger Than It Looks
Mixture of experts is sold as the trick that makes giant models cheap. It doesn't — it makes them bigger. This episode unpacks what the active parameter count actually measures, why a trillion-parameter checkpoint can run like a 3.6B model, and why the router fires a committee of experts per…
more -
Dictation Beyond the Keyboard
Dictation has quietly reshaped how many of us work, but starting and stopping it well is its own engineering problem. This episode digs into the physical controls that make voice input dependable: desktop pedals like the PCsensor and Stream Deck Pedal, handheld buttons, and wearables, plus the...
-
Training a LoRA to Write Like You
Off-the-shelf "Humanizer" models flatten everyone into the same average voice — the method works, but the corpus is the problem. This episode walks through building a personal style adapter: manufacturing flat/neutral training pairs from your own posts, choosing a base model over an instruct one,...
-
Fine-Tuning a Trillion-Parameter Model at Home
Daniel fine-tuned a speech model on his own mixed Hebrew-and-English recordings for the price of a coffee. So what happens if you point that same move at an Opus 5.5-class frontier model — raw, full precision, no practical reason at all? This episode walks through the arithmetic: the sixteen…
more -
What Do You Call the Middle Tier Model?
Every lab has a middle rung — Anthropic's Sonnet, OpenAI's Sol, Google's Flash, Mistral's Medium — but there's no agreed name for it, and the price lists have quietly converged into a ladder. This episode digs into why the tier most people use all day is getting squeezed by cheap open-weight…
more -
Can Anyone Still Spot an AI Voice?
Two Chatterbox hosts are talking to you right now, and this audio carries an inaudible watermark — can you hear it? That is the design goal, and it is also the problem. This episode digs into the real state of synthetic speech detection: listeners judge voice clones as human about as often as…
more -
Nobody Trains an Uncensored Model From Scratch
There's a shelf of uncensored models, but it's stocked with fine-tunes of other labs' bases, not from-scratch builds. This episode surveys what actually exists — Nous Research's Hermes with its written-down guardrail spec, Perplexity's re-alignment of DeepSeek R1 across hundreds of censored…
more -
Ten Weirdest AI Evals Ever Published
What happens when researchers need to measure machine intelligence and end up grading puns, emoji, and a joke with the punchline surgically removed? This episode counts down ten of the strangest AI evaluations ever published — from BIG-bench's "ruin names" task to a high schooler's Minecraft…
more -
Woolly Sedate Snail and Other Model Failures
Hugging Face hosts nearly three million model repos, and 85.6% have under 200 downloads. This episode wanders the long tail of AI: auto-generated "woolly sedate snail" swarms, a hotdog-not-hotdog classifier, a Trump-tweet device detector, and a Tiny Pirate that beats the Yoda. Then it goes back...
-
Attention Is Still Winning: The Hybrid Model Census
Nine months after our quadratic bottleneck episode, the post-transformer world has actually shipped — just not in pure form. This episode is a census of the hybrid models now in the wild: Qwen 3.5's three-to-one Gated DeltaNet blocks, Nvidia's Nemotron 3, Kimi Linear's 75% cache cut, IBM's…
more -
Who Decides If an Election Is Real?
There's no office anywhere that stamps an election genuine, yet most people assume one exists. This episode digs into the numbers behind sham elections — V-Dem counts 92 autocracies, 57 of them "electoral autocracies" holding multiparty votes that aren't real contests — and asks why the three big...
-
Watching Elections: Who Collects the Numbers, and Why
Elections are the one moment a government publishes its intentions in advance — which is exactly why foreign services, embassies, and trading desks want the unpublished version. This episode sorts the documented record from the movie version: leaked CIA tasking orders on the 2012 French...
-
Israel's 120-Seat Forecasting Ministry
Israel elects 120 seats by pure proportional representation, nobody wins a majority, and a party at 3.25% gets nothing at all. So what would it take to forecast an Israeli election properly — with real staff and a real budget? This episode walks through the staffing plan: running the actual...
We're indexing this podcast's transcripts for the first time — this can take a minute or two. We'll show results as soon as they're ready.
No matches for "" in this podcast's transcripts.
No topics indexed yet for this podcast.
Loading reviews...
ABOUT THIS SHOW
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 generates scripts, synthesizes voices, and assembles the final podcast. Stay curious.
HOSTED BY
Daniel Rosehill
CATEGORIES
Loading similar podcasts...
Frequently Asked Questions
How many episodes does My Weird Prompts have?
My Weird Prompts currently has 1000 episodes available on PodParley. New episodes are automatically indexed when they're published to the podcast feed.
What is My Weird Prompts about?
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...
How often does My Weird Prompts release new episodes?
My Weird Prompts releases new episodes frequently with a large back catalog of 1000 episodes. Check the episode list for recent publication dates.
Where can I listen to My Weird Prompts?
You can listen to My Weird Prompts on PodParley by clicking any episode. We provide an embedded audio player for direct listening, and you can also subscribe via your preferred podcast app using the RSS feed.
Who hosts My Weird Prompts?
My Weird Prompts is created and hosted by Daniel Rosehill.
URL copied to clipboard!