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
Choosing AI Models on Cost and Performance 31.10.2026 18:54
Picking an AI model requires balancing benchmark scores against runtime costs, but popular formulas often produce completely different winners from the exact same data. A simple cost-to-performance ratio inevitably favors cheap models with unusable scores unless filtered by a quality floor. Exploring methods from Pareto frontiers and knee-finding to weighted sums and TOPSIS reveals why selecting t...
Turning Anonymous Diarization Clusters into Names 31.10.2026 23:39
Turning anonymous speaker clusters into verified names requires more than matching audio clips. The pipeline relies on fixed-length speaker embeddings, pooling layers, and angular margin losses like ArcFace to represent vocal identity across varying speech lengths. While short introductions seem convenient, limited phonetic variety degrades accuracy. The mechanics of x-vectors, ECAPA-TDNN architec...
Choosing the Right Voice Activity Detector 31.10.2026 32:08
Voice activity detectors look interchangeable until deployment constraints reveal their hidden costs. Comparing Silero, TEN VAD, WebRTC, and Cobra shows that download size is only a fraction of the story: runtimes, licensing restrictions, and transition delays drastically alter performance. From WebRTC's lightweight Gaussian mixture models to Cobra's embedded runtime and Silero's multi-domain neur...
Porting Voice Models to Core ML and MLX 31.10.2026 30:46
Porting speech and audio models from Linux PyTorch environments to Apple platforms involves distinct engineering trade-offs. Core ML requires graph capture and converter compatibility to leverage the Neural Engine, CPU, and GPU, packaging specifications and weights into structured bundles. Meanwhile, MLX requires direct reimplementation of the forward pass in array code, bypassing the Neural Engin...
Running Speaker Identification Locally on Phones 31.10.2026 22:34
Running speaker identification directly on mobile devices is entirely practical without relying on cloud servers. While research environments favor heavy PyTorch pipelines like pyannote.audio, edge runtimes such as sherpa-onnx execute compact ONNX models directly on Android and iOS. This breakdown explores the practical engineering trade-offs of offline voice matching, comparing embedding models l...
How Audio Models Tell Voices Apart 31.10.2026 28:23
Voice recognition systems often struggle with speaker diarization: tracking who spoke when across overlapping speech, whispers, and brief interruptions. This exploration unpacks the mechanics behind pyannote and end-to-end neural diarization (EEND), examining how voice activity detection, speaker embeddings, powerset segmentation, and Bayesian hidden Markov models like VBx separate anonymous speak...
Why Financial Centres Outlive the Forces That Built Them 30.10.2026 25:12
Financial capitals rarely coincide with political seats, surviving shifts in transport, technology, and regulation. Looking at Charles Kindleberger's theories on transport breaks, this episode traces how trade routes and institutional ecosystems anchor commerce in places like Zurich and New York. It explores how Zurich leveraged the Gotthard railway tunnel over historic rivals, how wartime credit...
Why Modern AI Rests on Statistics 30.10.2026 23:16
Modern artificial intelligence often frames its breakthroughs in computing power, yet its fundamental mechanisms rely entirely on classical statistics. Adding petabytes of scraped text cannot correct for systematic sampling bias, and monitoring models requires understanding distribution tails rather than relying on average latencies. From Ronald Fisher's agricultural experiments and the foundation...
What Theoretical Physicists Actually Do All Day 30.10.2026 29:42
Official labor counts list under twenty thousand physicists in the United States, yet eleven million jobs run on physical principles under titles like product designer or engineer. Inside academia, the theoretical physicist's reality clashes with the solitary genius myth. Examining interviews with faculty and researchers at CERN and national labs reveals a career defined by fractured calendars, en...
MWP 4 Kids: Why the Moon Changes Shape 30.10.2026 9:43
The moon seems to change from a full glowing circle to a slim crescent sliver, but it never actually loses its shape. Using a bright lamp and a simple round orange, a calm bedtime demonstration reveals how sunlight always illuminates exactly half of the lunar sphere. As the moon completes its twenty-nine-day orbit around Earth, varying angles show different amounts of that illuminated face, creati...
Where Email Attachments Actually Live and Go 30.10.2026 23:12
Email attachments seem like simple files handed between computers, but MIME transforms them into text packed directly inside the message body. Storing all that data poses an enormous engineering problem: attachments accounted for 85 percent of storage at Mail. Ru before deduplication. Mail systems dissect complete messages on disk, balance reference counters, hash encoded payloads, and handle tran...
Why Private IP Addresses Look the Way They Do 30.10.2026 22:45
Popular network charts often label private IP ranges by organization size, claiming 10.0.0.0 is for enterprise and 192.168.0.0 is for homes. In reality, RFC 1918 simply preserved historical class boundaries, and any network can use any private block. What actually matters is subnet sizing, route specificity, and the routing collisions that occur when hotel Wi-Fi and home networks share identical d...
Why Modern Audio Datasets Ship as Parquet Files 30.10.2026 31:00
Parquet was designed for untidy tabular records, but dataset repositories increasingly use it to bundle audio recordings alongside transcripts and timestamps. The file structure splits data into row groups, column chunks, and pages, allowing readers across different programming languages to selectively decompress columns without streaming full datasets. From footer-based metadata and dictionary fa...
The Most Popular GPUs - Today's Cloud Demand 30.10.2026 23:51
Cloud GPU pricing depends far more on deployment models and memory fit than raw benchmark speeds. A look across real rental options—from 24GB workhorses like the L4, A10G, and RTX 4090 to 48GB and 80GB accelerators like the L40S, A100, and H100—reveals where speech recognition, image generation, and quantized language models actually run. The trade-offs between dedicated instances, community pods,...
Training an AI Model from Random Weights 30.10.2026 28:18
Training a conversational AI from completely random weights requires building an entire statistical education rather than fine-tuning existing layers. Looking closely at open-source pipelines like nanoGPT and nanochat shows how tokenizer choices quietly dictate compute costs across languages, why tiny smoke tests prevent catastrophic compute waste, and how midtraining and supervised fine-tuning tu...
Why Windows Struggle with Bass 30.10.2026 21:24
Double-pane windows block street noise effectively, yet late-night bass still leaks through to disrupt sleep. Standard sound transmission class ratings often omit deep low frequencies, while trapped air between glass panes can create resonances that transmit rhythmic pulses. Exploring sound transmission physics, room modes, and masking experiments reveals why small white-noise machines fail to cov...
Why Training Recipes Matter More Than Model Size 30.10.2026 28:07
Fine-tuning speech recognition models often conceals massive architectural decisions inside ordinary setup notebooks. From checkpoint averaging and batch size dynamics to optimizer interactions, minor configuration details can drastically swing error rates without altering the underlying audio dataset. Exploring recent findings across Whisper and NeMo architectures, this discussion examines curric...
Teaching Speech Models to Transcribe Bilingual Slang 30.10.2026 22:56
Fine-tuning a speech recognition model like Parakeet on English-Hebrew code-switching reveals sharp diminishing returns on recorded audio. The earliest seventy-seven minutes of speech nearly halved the word error rate, while subsequent hours provided smaller, more expensive gains. The distinction between word error rate and specific term recall proves vital, especially when teaching consistent rom...
Collecting Speech Data on Outdoor Walks 30.10.2026 22:13
Fine-tuning NVIDIA's Parakeet speech model for everyday use requires gathering training data that matches real deployment conditions, especially walking outdoors. Movement alters breathing, phrasing, and microphone position in ways background noise alone cannot replicate. Examining input workflows reveals the trade-offs between handheld game controllers, smart glasses like the Even Realities G2, a...
When Automated Proofs Leave Mathematicians Grieving 29.10.2026 28:47
Mathematicians often pursue proofs not just for the answer, but for transferable structural understanding. When an unreleased OpenAI model coordinated ten thousand agents over eighty-eight hours to claim a Lean-formalized proof for Navier–Stokes, the reaction across the field combined astonishment with deep grief. This discussion explores the rigor of formal verification, why deductive certainty d...
Where Mathematicians Actually Work and How AI Fits In 29.10.2026 24:10
Popular culture pictures mathematicians as solitary academics pacing in front of chalkboards, but the vast majority of mathematical labour happens under titles like quantitative researcher, biostatistician, or software engineer. Exploring the divide between academic pure research and industry problem-solving reveals why mathematicians greet recent machine-generated proof claims with caution. From...
Why the Kibbutz Had to Unbundle Security 29.10.2026 29:50
Communal living can abolish internal wage competition, but it cannot vote away the arithmetic of debt. By 1985, triple-digit inflation and high interest rates exposed the financial vulnerabilities of collective farming settlements in Israel. Looking at the history of kibbutzim from Deganya Alef to the modern renewing model, this discussion explores how shifting family preferences, recruitment chal...
What Counts as a Mathematical Proof 29.10.2026 29:01
Mathematical proof demands far stricter guarantees than experimental evidence or a collection of successful tests. This examination untangles how deductive reasoning excludes counterexamples using definitions and inference rules rather than mere computation. It covers mathematical induction, the mechanical demands of formal proof checkers versus human-readable prose, and the historical path of axi...
When Eating Triggers Breathlessness Without Reflux 29.10.2026 29:13
Breathlessness after eating is frequently blamed on acid reflux or food allergies, but muscle mechanics often tell a different story. In abdominophrenic dyssynergia, the diaphragm paradoxically contracts downward while the abdominal wall relaxes, altering posture and breathing effort without large increases in gut gas. This episode examines clinical trials on acid suppression, the mechanics of pos...
Why Cross-Age Friendships Depend on Shared Places 29.10.2026 27:52
Cross-age friendships rarely form through good intentions alone. The meeting principle shows that physical, purposeful settings matter far more than goodwill or national active-ageing scores. This discussion unpacks how nineteenth-century institutions separated learning, earning, and retirement into disconnected stages, what European data reveals about cross-generational confidants, and why everyd...
Similar podcasts
Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.