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

Technology

Podcast website

myweirdprompts.com

Latest episode

Nov 19, 2026

Where to listen?

Podcasts in the app Replaio Radio Coming soon

Podcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts

Get it on Google Play Install for free Android 10M+ downloads · 4.7+ rating iOS soon

Episodes

Why LLM Leaderboards Need Psychometrics 08.11.2026

Standard AI benchmarks treat every question as an equal test of intelligence, but educational testing abandoned raw score averages decades ago. Applying item response theory exposes how popular benchmarks like MMLU and HellaSwag have grown far too easy to separate top models. Adaptive testing methods such as ATLAS can evaluate models in dozens of questions instead of thousands while adjusting rank...

Why Simple Rules Beat Value Models in Reasoning RL 08.11.2026

Reinforcement learning with verifiable rewards powers modern reasoning models without requiring complex neural critics. By replacing a policy-sized value model with group-relative advantage estimation, algorithms like GRPO cut memory overhead and avoid reward hacking. A look at the inner mechanics of rule-based scoring, how crude outcome verification generates tens of thousands of reasoning tokens...

Why You Must Read AI Traces Before Writing Evals 08.11.2026

Standard advice suggests picking automated benchmarks and metrics first, but practitioners argue that effective AI evaluation requires reading raw interaction traces by hand. Discover how grounded theory methods like open and axial coding expose criteria drift and application-specific flaws before tools are deployed. The discussion covers practical trace sample sizes, how to spot upstream root cau...

Why Speech Recognition Confidence Scores Lie 08.11.2026

Speech recognition models like Whisper and Parakeet compute internal probabilities for every token, but turning those numbers into trustworthy word-level confidence is surprisingly brittle. Softmax saturation, pooling choices across sub-words, decoding fallbacks, and blank frames in CTC architectures distort confidence scores across the board. The mechanics behind word confidence calculations, why...

How Speech Models See Audio as an Image 08.11.2026

Speech recognition models like Whisper never actually hear audio as human listeners do. Before a neural network processes anything, incoming waveforms are resampled, cut into twenty-five-millisecond windows, and compressed into log-mel spectrograms. This breakdown walks through every stage of that front-end pipeline, exploring the 1937 five-person study behind the mel scale, the deliberate discard...

Teaching Speech Models to Choose Their Own Audio 08.11.2026

Human transcription takes over eight hours of manual work for every hour of recorded audio. Active learning promises to cut that burden by letting speech models select which unlabelled recordings are most informative to transcribe next. Yet simple uncertainty measures often select garbage noise rather than useful speech, and sophisticated loss predictions frequently struggle against random baselin...

Where Speech Models Actually Learn 08.11.2026

Speech model fine-tuning recipes usually decide which layers get gradients before training even begins. Research reveals that encoders already capture nuanced semantics, speaking styles, and accent features that decoders systematically discard. Examining empirical benchmarks across Whisper and Parakeet, this discussion unpacks why freezing the acoustic encoder degrades multilingual accuracy, how h...

Why Speech Models Forget Other Voices When Tuned on Yours 08.11.2026

Fine-tuning a speech recognition model on a single speaker's voice often quietly destroys its ability to transcribe other accents, longer audio, and basic formatting. Examining evidence from Whisper adaptations in Hebrew and Swiss German, this audit covers how catastrophic forgetting erodes timestamps and structure even when target accuracy improves. It breaks down why general regression testing s...

What Audio Models Learn Before Fine-Tuning 08.11.2026

Speech encoders arrive at fine-tuning with tens of thousands of hours of audio structure already baked into their weights. This examination of internal representations contrasts self-supervised models like wav2vec 2.0, HuBERT, and w2v-BERT against weakly supervised systems like Whisper. It explores layer-by-layer probing of tongue position and word boundaries, the resurgence of speaker identity in...

Agent Skills Break When Secrets Leave Your Laptop 08.11.2026

Agent skills pack instructions and code into portable folders, but credentials break the moment workloads migrate away from local machines. While tools like the GitHub CLI prove that agents can drive workflows without dedicated servers, secrets lack a native home in the Agent Skills specification. Examining divergent credential approaches across Claude Code cloud sessions, Codex cloud, and GitHub...

What the Evidence on Daylight Saving Actually Shows 08.11.2026

Daylight saving time is widely accused of ruining health and energy budgets, but the evidence tells a far more complicated story. From Benjamin Franklin's satirical candle essay to a New Zealand entomologist seeking extra evening hours to hunt insects, the true origins contradict modern folklore. A 157-study systematic review reveals mixed impacts across transitions, highlighting everything from h...

Why Governments Move Time Zones Off the Grid 08.11.2026

Standardized time looks like pure physics, but every boundary line and offset is an act of statecraft. From El Paso defying federal time statutes for decades to China enforcing a single nationwide hour across five natural zones, borders constantly override geography. A look at how national identity, administrative control, and political independence shape the clocks of the world, including the rar...

Why Australian Suburbs Resemble American Ones 08.11.2026

Australian suburbs look strikingly like American streetscapes, bearing little resemblance to British terraced housing. A trail of roofing advertisements, three-dollar mail-order blueprints, and translated Prairie School architecture reveals how California bungalows were adopted across Melbourne and Sydney. From Gustav Stickley's pattern books to the transport layout of streetcar suburbs, local bui...

Turning Acoustic Physics into a Math Problem 07.11.2026

At the extreme edge of audio surveillance and aeroacoustics, microphones transform from simple transducers into massive computational arrays. Examining the physics of sound capture reveals why aperture size limits directional microphones and why modern systems turn to thousands of phase-matched sensors. A look at the German Aerospace Center's 7,200-element listening wall, wake-vortex tracking over...

Why Voice Satellites Need Integrated Audio 07.11.2026

Building a private voice assistant for hands-free home control hinges on acoustic hardware design. This look at Home Assistant voice satellites explores why separating microphones from external speakers breaks echo cancellation and follow-up queries. From the official Voice Preview Edition and custom microWakeWord training to DIY reSpeaker XVF3800 setups, the software trade-offs of Linux Voice Ass...

Choosing Audio Bitrates and Settings for Voice 07.11.2026

Voice recording settings are often dialed far higher than necessary. An analysis of modern audio codecs reveals why Opus beats MP3 and FLAC for voice notes and meetings, why 24 kilobits per second mono offers the ideal balance of size and clarity, and how Android's mysterious microphone zoom slider actually operates behind the scenes. Key sources: • NLL APPS, ASR Another Sound Recorder product pag...

Why Narrow Speech Tasks Still Need Large Models 07.11.2026

Building speech recognition for short navigation addresses seems like a job for a tiny model trained from scratch. However, transfer learning research on Parakeet and QuartzNet shows that small datasets cause models to overfit or forget acoustic fundamentals without massive pretrained priors. Exploring catastrophic forgetting, format scoring artifacts on the AN4 corpus, and knowledge distillation...

What Kills Ad-Free Social Networks 06.11.2026

Cataloguing the virtual fossil record of the internet reveals that technical failure rarely closes niche social networks. Instead, venture capital expectations drive most shutdowns. A look at historical post-mortems from Ello, Imzy, Pebble, and Cohost demonstrates how ethical platforms consistently run into the demand for exponential growth. While venture-backed sites vanish without data exports,...

Proprietary Plugs and Formats Nobody Wanted 06.11.2026

Tech companies regularly wager that customers will accept locked-down formats and expensive proprietary ports just to access their hardware. This look at tech history covers the biggest format gambles that collapsed under their own corporate terms: Circuit City's phone-home DIVX discs, Apple's power-squatting Display Connector, the one-dollar licensing fee that sank FireWire against USB 2.0, and S...

Why Universal Standards Fail 06.11.2026

State backing, committee consensus, and official decrees are often not enough to make a standard stick. Exploring notable failed standardization attempts reveals distinct failure mechanisms: popular non-compliance against French Revolutionary decimal time, institutional vetos stalling Esperanto at the League of Nations, complexity sinking the OSI networking model against TCP/IP, and entrenched sun...

When Ready to Attack, Seeming Weak 06.11.2026

Military deception usually conjures images of bluffing strength, but the reverse strategy—appearing weak, distracted, or unready while poised to strike—is often far deadlier. This episode examines the operational mechanics behind feigned weakness, analyzing Moshe Dayan's public leave maneuvers before the Six-Day War, Egypt's routine mobilizations and public demobilizations before Operation Badr, a...

Why Research Agent Agreement Is Not Independence 06.11.2026

Multi-agent research pipelines often rely on consensus across different models to verify facts autonomously. However, research into correlated failures shows that independent models frequently fail in identical ways due to shared training corpora. Examining architectures like LangChain's Open Deep Research, Perplexity's Model Council, and consensus judges like MAD-Fact reveals why ensembling searc...

Why Great Dictation Headsets Come from Gaming and Broadcast 06.11.2026

Standard office headsets often fail power dictation users who wear glasses and require consistent microphone placement. When shopping strictly for over-ear designs with boom microphones and no battery gimmicks, office brands disappear, leaving heavy gaming gear and professional broadcast hardware as the main contenders. An analysis of five top-tier models highlights the trade-offs between wireless...

Finding a Technical Evaluation Job Without the Sales Quota 06.11.2026

B2B tech buyers and technical sellers often perform the exact same work from opposite sides of the table. From sales engineers and solutions consultants to enterprise category managers, this breakdown explores what it takes to own technical evaluation and product discovery without doing traditional closing. Learn how presales roles structure quotas, why title inflation masks identical daily duties...

Bluetooth Microphone Quality and the Audio Ceiling 06.11.2026

Sixteen kilohertz remains the stubborn default for wireless headset microphones, even when modern codecs claim forty-eight. Getting beyond wideband voice requires coordinated support across the operating system, Bluetooth controller, drivers, and the headset itself. The investigation maps Windows defaults, experimental Linux PipeWire stacks, dongle hardware like the FlooGoo FMA120, and proprietary...

Listen to the My Weird Prompts podcast in Replaio

Radio and podcasts in one app - free, with no sign-up. Install today and do not miss the launch

Get it on Google Play

Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.