fr

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...

N'hésitez pas à visiter le site du podcast et à soutenir son créateur : myweirdprompts.com

Auteur

Daniel Rosehill

Catégorie

Technology

Site du podcast

myweirdprompts.com

Dernier épisode

20 nov. 2026

Où écouter ?

Les podcasts dans l'appli Replaio Radio Bientôt disponible

Les podcasts arrivent très bientôt dans l'appli. Installe-la dès maintenant et découvre en avant-première une toute nouvelle façon de vivre les podcasts

Télécharger sur Google Play Installe-la gratuitement Android 10 M+ de téléchargements · note de 4,7+ iOS bientôt

Épisodes

A Quantum Chip, a Toy Truck, and a Wild Giant Anteater 19.11.2026

An explanation of how a speaking anteater got his voice turns into a debate over the no-communication theorem, which proves quantum entanglement cannot carry a message without an ordinary classical channel. From there, the conversation moves to a weekend trip to Serra da Canastra National Park in Brazil to spot a wild giant anteater, how wild anteaters use marked trees as a slow message board, and...

Arabic's Closest Living Relative Is Hebrew 18.11.2026

Comparative linguistics upends geography in the Semitic language family. Using shared innovations rather than shared retentions, the Hetzron model dissolves the old South Semitic branch and places Arabic in Central Semitic alongside Hebrew, Aramaic, and Ancient South Arabian. Despite sharing three-consonant roots like K-T-B and the genitive chain construction, Hebrew and Arabic speakers still cann...

Polishing AI Voices Without Erasing Character 18.11.2026

Heavy speech-enhancement models often strip away vocal character, sanding down rasp and breath until distinct voices sound alike. Fixing two Chatterbox-trained AI voices required the opposite approach: a tiny equaliser cut to remove low-mid mud, followed by Resemble AI's resemble-enhance to resynthesise a missing 7.5 to 11 kilohertz band. For about a dollar of compute, the targeted two-step recipe...

Training a $10 Model for Hebrew Speaker Gender 18.11.2026

Hebrew bakes a speaker's gender into first-person verbs and adjectives, sometimes changing the letters and sometimes only the unwritten vowels. This episode examines a $10 work-in-progress pipeline built to solve that gap for text-to-speech. Using 17,725 sentences generated by Claude Sonnet and filtered by Dicta's morphological analyser, a LoRA fine-tune on Gemma 4 E4B was trained in 32 minutes on...

Training a Ten-Dollar Model for Gendered Hebrew 18.11.2026

Hebrew bakes the speaker's gender into verbs and adjectives, yet unpointed text leaves out the vowels that tell a man's 'ani rotse' from a woman's 'ani rotsa.' That gap trips up language learners and breaks voice agents, including a 135-hertz male voice judged female 71% of the time. To fix it, Daniel spent about ten dollars training two small models on Claude-generated sentences gated by Dicta's...

Blind-Testing 26 Hebrew Text-to-Speech Models 18.11.2026

Twenty-six text-to-speech models went into a blind bake-off across sixty runs to find a reliable Hebrew pronunciation coach, and twenty-three runs failed at screening. Testing sentences both with and without nikud vowel points reveals how much models guess, from Kokoro Hebrew reading 'book' as 'barber' to Zonos 3 Mini falling back to English. The episode explores why Hebrew's missing vowels, sylla...

Setting Limits on Long-Distance Grandparent Visits 18.11.2026

Long-distance grandparenting often leads to longer, more intense visits—sometimes one to six months—which can create "hypercopresence" for the visiting or hosting spouse. Exploring research on transnational families, marital conflict, and couple communication, this discussion unpacks why there is no cultural script for in-law visit length. It covers why couples silently absorb visit-related stress...

Replacing System Beeps With 46 Voice Clips 17.11.2026

Forty-six spoken alerts replace generic system beeps in Herman Poppleberry Desktop Sounds and the companion Herman Announcer Android APK. Built on an existing voice clone refined with resemble-enhance and loudness normalisation, the free Creative Commons release installs as a freedesktop sound theme for KDE Plasma and GNOME, pairs with a background watcher for events like VPN connections and mic m...

Stacking LoRAs Without Weight Interference 17.11.2026

The common two-LoRA limit in image and video tools is a quality ceiling from weight interference, not a software cap. Exploring how a mixing-desk model for AI voice could work, this breakdown covers per-LoRA strength faders, per-layer routing in Wan 2.2, and regional masking in ComfyUI. It also looks at interference fixes like LoRA Switch, X-LoRA, and new voice research including ReStyle-TTS, GLAS...

Updating Speech Models Weekly Without Forgetting 17.11.2026

Frequent, lightweight updates to a speech recognition model require separating list problems from weights problems. Runtime biasing frameworks like BR-ASR handle up to 200,000 custom vocabulary entries without touching model weights. When accents or systematic errors do require training, AWS AI Labs' sequential-editing recipe uses ten epochs at one-tenth the learning rate. To prevent catastrophic...

Why Models Improve by Re-Reading the Same Data 17.11.2026

Repeating the same training data works because each epoch reshuffles mini-batches and takes new gradient descent steps from a different starting point. Exploring multi-epoch training, this discussion covers Muennighoff's four-epoch scaling threshold, grokking's internal reorganization at zero loss, and why under-training is a common fine-tuning trap. It also examines voice LoRA runs on Qwen3-TTS,...

Why Fine-Tuned Models Keep the Same File Size 17.11.2026

After 70 hours of voice fine-tuning, a Parakeet TDT speech model learns new vocabulary while its 2.5-gigabyte safetensors file barely grows. The format is a fixed-size photograph, not a diary: training nudges existing 32-bit floats rather than adding storage, while discarding 10 gigabytes of live optimizer state. That fixed frame also hides catastrophic forgetting, where new accents and words over...

What Actually Lives Under Hugging Face's Audio-to-Audio Tag 17.11.2026

Hugging Face's audio-to-audio pipeline tag groups nearly 1,900 models by input and output shape rather than purpose, putting real-time conversational assistants and tiny noise removers in the same drawer. This breakdown maps the top trending families, from NVIDIA's PersonaPlex and caramel-1 to 9.6-million-parameter speech restorers like RE-USE, speaker separators like kezek-v1 and voxlock, and mul...

How Resemble-Enhance Generates Missing Speech Detail 17.11.2026

An open-source speech model from Resemble AI called resemble-enhance can add 14 decibels of energy to frequencies a muffled recording never contained. Unlike a traditional equalizer or denoiser like DeepFilterNet, its enhancer module uses an IRMAE autoencoder, conditional flow matching, and a UnivNet vocoder to resynthesize clean speech from scratch. The result sounds crisp, with waveform correlat...

Two Ways AI Edits Audio From Plain Instructions 17.11.2026

Instruction-based audio editing promises to change a clip using plain language, but the label hides two completely different approaches. Generative models like Microsoft and CUHK-Shenzhen's AUDIT, StepFun's Step-Audio-EditX, and Tencent's AuK re-synthesise audio, which risks unintended drift in the original take. Meanwhile, parametric systems like Sony AI's LLM2Fx and Northwestern's Text2FX leave...

How Lighthouses Learned to Blink Their Names 17.11.2026

Every lighthouse flashes in its own distinct pattern, turning a simple beam into a readable name at sea. When coloured glass proved too dim—costing up to three-quarters of a lamp's intensity—engineers like Robert Stevenson and John Hopkinson turned to mechanical shutters and angled prisms to create timed darkness for free. From counting flashes with a stopwatch using Bowditch's rules to reading th...

Nostalgia Is a Trait, and Antiques Are Just Taste 17.11.2026

A household dispute over old music and antique furniture opens up forty years of psychology on trait nostalgia and time orientation. Once diagnosed as a literal disease by a 1690s Swiss physician, nostalgia is now understood as a normal, weekly psychological resource linked to openness and attachment security. Drawing on research from Southampton and a 1,392-person consumer study, this episode sep...

What Exercise Trials for Depression Actually Show 17.11.2026

Headlines claim exercise treats mild to moderate depression as well as medication or therapy, yet nobody was flipped a coin between a barbell and a prescription. That comparison comes from Noetel's BMJ network meta-analysis, which chained separate trials together mathematically while grading its own confidence arm by arm. Alongside Solmi's umbrella review and an unfixable blinding problem, the lit...

How Sleep Deprivation Temporarily Lifts Depression 17.11.2026

Keeping a severely depressed person awake for a single night can lift their mood within hours, working in roughly half of patients. Yet the effect usually vanishes after the very next sleep—or even a few seconds of microsleep. This episode explores the sixty-year history of clinical sleep deprivation, new 2026 findings on how it resets the brain's molecular clock, and the chronotherapy protocols c...

Brain implants for depression and the two-millimetre gap 17.11.2026

Deep brain stimulation is approved for Parkinson's, tremor, and OCD, yet it remains unapproved for treatment-resistant depression. This look at the science traces Helen Mayberg's work on Area 25, the surprising failures of St. Jude Medical's BROADEN and Medtronic's RECLAIM trials, and a new Canadian sham-controlled study where unstimulated patients initially outperformed active ones. It explores h...

What Psilocybin Depression Trials Actually Show 17.11.2026

Compass Pathways has submitted COMP360 to the FDA after two Phase 3 trials hit their primary endpoints, yet the Week 6 advantage over placebo was just 3.6 MADRS points—half of the Week 1 peak. A look at the clinical evidence for psilocybin in treatment-resistant depression unpacks what the COMP005, COMP006, and EPIsoDE trials actually measured, why expectancy and functional unblinding complicate t...

What Bridges the Gap Before Antidepressants Work 17.11.2026

Antidepressants take weeks to reach full effect, leaving a dangerous stretch when someone is in acute crisis. This conversation examines the global scale of suicide, why suicidal thoughts and actions are driven by separate mechanisms, and the FDA's boxed warning on SSRIs for young people. It also explores what actually bridges those early weeks—from written safety plans and caring contacts to mean...

How Magnetic Pulses Target Depression Circuits 17.11.2026

Transcranial magnetic stimulation uses Faraday's law to induce electric currents in the cortex, aiming at a prefrontal spot anticorrelated with the subgenual cingulate. Rather than simply exciting neurons, TMS reshapes directional network signaling and synaptic plasticity—converging on the same molecular door as ketamine and ECT. Yet the clinical evidence lags behind the mechanism: randomized tria...

No Addictive Personality Type, Just Shared Traits 17.11.2026

Research shows there is no single addictive personality type, yet specific traits and genetics still shape who is most vulnerable. Examining the history of Purdue Pharma's OxyContin marketing alongside clinical data, this discussion unpacks how the five-part UPPS-P impulsivity model separates sensation seeking from emotional urgency. Studies on adolescent alcohol use, pathological gambling, and tw...

How Ketamine Lifts Depression in Hours, Not Weeks 17.11.2026

Ketamine and esketamine (Spravato) broke forty years of psychiatric doctrine by lifting treatment-resistant depression in hours rather than weeks. By blocking NMDA receptors on inhibitory interneurons, the drug triggers a glutamate surge and rapid dendritic spine growth, a process of structural remodelling and metaplasticity. Yet clinical trials show a modest 3.44-point MADRS edge over placebo at...

Écoute le podcast My Weird Prompts sur Replaio

La radio et les podcasts dans une seule appli - gratuite, sans inscription. Installe-la dès aujourd'hui et ne rate pas le lancement

Télécharger sur Google Play

Replaio n'est pas éditeur de podcasts ; les noms des émissions, les visuels et l'audio appartiennent à leurs auteurs et sont diffusés via des flux RSS publics