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 18, 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

Conferences Rule Machine Learning, Not Journals 05.11.2026

In machine learning, flagship conferences serve as archival records rather than stepping stones to academic journals. From the massive scale of NeurIPS, ICML, and ICLR to specialized venues like CVPR and ACL, acceptance rates have converged around twenty to twenty-seven percent. This episode explores how open-access journals like JMLR and JAIR fit into the ecosystem, the astronomical fees of legac...

Why Modern AI Models Cut Most Attention Layers 05.11.2026

Standard softmax attention forces models to store every past key and value, making multi-turn chat memory balloon past model weights. Production models are quietly replacing full attention with layered hybrids instead of abandoning it completely. Gated delta rules compress history into fixed recurrent states, learned sparse indexers read only relevant tokens, and latent bottlenecks shrink what rem...

Teaching Speech Recognizers to Stay Quiet 05.11.2026

Voice activity detection usually acts as a protective fence in front of automatic speech recognition models, dropping silence before hallucinations occur. While external gates remain the default engineering fix, internal model weights already track the difference between speech and ambient sound. Discover how surgical fine-tuning of specific attention heads, activation steering, and synthetic posi...

Why Training Speech Recognition From Scratch Fails 05.11.2026

Training speech recognition models from random weights requires learning acoustics, alignment, and language simultaneously from paired audio. While large language models train on trillions of free text tokens, a speech corpus provides only about nine thousand words per recorded hour. Fine-tuning an existing base model vastly outperforms scratch training below hundreds of hours. Going entirely from...

When Adding a Reranker Hurts Search 05.11.2026

Cross-encoders are often billed as a painless, universal accuracy boost for RAG pipelines and search boxes. Yet benchmark results range from a fifteen-point lift down to an outright regression, and some experiments show latency exploding two-thousand-fold for no measurable gain. The discrepancy hinges entirely on the retriever's recall curve and token economics. Here is how to diagnose whether an...

Why Easy-to-Read Fonts Must Break Harmony 05.11.2026

Visual harmony makes modern typefaces look beautiful, but uniformity causes letters to blur together for low-vision readers. Exploring the creation of Atkinson Hyperlegible by Applied Design Works for the Braille Institute, this discussion unravels the critical difference between legibility and readability. It examines why deliberately inconsistent letterforms succeed for low acuity, how kerning m...

Why Watching a Sleeping Child Defeats Attention 05.11.2026

Continuous vigilance fails rapidly when supervising a low-activity scene, an effect documented from wartime radar operators on the Mackworth Clock to modern lifeguards. Human attention drifts within thirty minutes under conditions of cognitive underload, making uninterrupted voluntary surveillance impossible. To monitor a feverish child effectively, parents should discard continuous glancing in fa...

Why the Gaussian Distribution Fails in Plain Sight 05.11.2026

The Gaussian distribution underpins everything from least-squares regression to modern AI diffusion models, controlled entirely by just two parameters: mean and variance. But its aggressive, thin-tailed exponential decay makes extreme real-world events vanish mathematically. Exploring the mathematical power of the central limit theorem alongside the subtle dangers of confusing bell curves with hea...

Why Synthetic Fine-Tuning Data Needs Tooling 04.11.2026

Naive generation loops make synthetic fine-tuning data prone to over 30 percent duplication, judge bias, and model collapse. Examining findings on knowledge collapse and simulated user demographics reveals that synthetic generation acts as a quality multiplier rather than a data curation substitute. Dedicated frameworks like NVIDIA's Data Designer and topic-tree libraries replace prompt-and-pray A...

Where to Learn LLM Training Without Generic Courses 04.11.2026

Training and fine-tuning language models has become cheap enough to learn from scratch, but high-quality education remains surprisingly fragmented. While open-source lectures like Stanford's CS 336, Karpathy's repos, and Hugging Face offer deep technical grounding, the scarce resource is compute rather than tuition. This guide maps out the four tiers of self-education—from building transformers an...

The Unsung Builders of Modern Speech AI 04.11.2026

Speech recognition commands billions in venture funding and fills massive academic conferences, yet its foundational architects remain largely anonymous to the public. This episode maps the human ecosystem behind modern audio AI, tracing the toolkits and researchers that made ubiquitous transcription possible. From Daniel Povey's grueling work on Kaldi to Georgi Gerganov's whisper.cpp and Hervé Br...

Turning Open-Source Triage into Subscription Credit 04.11.2026

Heavy users of semi-open developer tools often act as unpaid triage teams and QA departments, diagnosing critical bugs and shaping product roadmaps while paying full subscription rates. Examining the FeedCoin proposal reveals that while companies like Loophole, Orkosi, and Nexu offer fragmented credits for reports or code, an interoperable renewal discount standard does not exist. Exploring Turso...

Choosing Between MCP Servers, Agent Skills, and CLIs 04.11.2026

Developers are wrestling with how to connect AI agents to tools, debating whether to wrap APIs in command-line interfaces, lightweight agent skills, or full Model Context Protocol servers. An evaluation by Arize reveals that while correctness stays nearly identical across all approaches, cost and latency diverge by a factor of six on complex tasks. The breakdown covers context token bloat, naive A...

Who Actually Won the Open Weight Race 04.11.2026

Public download counters tell a surprisingly different story from production deployment data. While a modest 2022 sentence embedder tops all-time downloads thanks to automated library defaults, enterprise production numbers tell an entirely different tale, led by Google's Gemma and Microsoft's Phi. The metrics behind open-weight model adoption expose the massive gap between headless infrastructure...

Why Recursive File Watching Strains Linux Memory 04.11.2026

Linux file monitors like inotify make instant automation possible, but watching entire trees reveals an expensive kernel secret. The kernel provides no native recursive watches, forcing tools to spawn individual monitors per subdirectory. Each watch consumes unswappable kernel memory, creating hidden memory pressure on large directories while write paths silently pay the cost of constant checks. E...

Which AI Models Actually Last 04.11.2026

API retirement notices are arriving at a relentless pace across major artificial intelligence labs. This exploration contrasts the lifespans of legacy models across OpenAI, Anthropic, and Google, showing how providers handle deprecations differently. From OpenAI's shifting alias strategies and mass shutdowns to Anthropic's structured schedules and preservation interviews, the discussion examines h...

Securing MCP Endpoints and Webhooks Without Open Doors 04.11.2026

Exposing local services to AI agents and webhooks introduces a delicate security puzzle. From the heavy conformance requirements of the Model Context Protocol specification—demanding multiple RFCs and OAuth 2.1 drafts—to enterprise platforms like Kong and reverse proxy setups like Cloudflare Access, navigating authentication is fraught with subtle configuration traps. This look at edge security co...

Why PHP2Shell Was a Sniper Rifle, Not a Nuke 04.11.2026

Critical CVE scores rarely match actual threat reality. An analysis of the PHP2Shell unauthenticated remote code execution vulnerabilities highlights the gap between catastrophic headlines and real-world exploitation. Despite 46 million vulnerable web servers and an embargo breach, attacks required hyper-specific target configurations. The discussion covers decade-old memory bugs found by modern A...

Why Fast Model Microtraining Needs an Evaluation Gate 04.11.2026

Continuous delivery works seamlessly for code, but applying rapid CI/CD pipelines to fine-tuning machine learning models introduces severe risks. Microtraining a personalized speech recognition model on targeted failure patterns costs pennies with LoRA adapters, yet sequential updates trigger catastrophic forgetting regardless of training size. Without automated gates like exponential moving avera...

Why Uptime Math and Retry Storms Break Cloud Services 04.11.2026

High availability is harder than simple arithmetic suggests. Serial components multiply failure rates, and enterprise SLAs promise financial discounts rather than infallible perfection. Looking into major cloud outages reveals a surprising culprit: automatic client retries. Without randomized jitter and backoff budgets, the very mechanisms designed to make software resilient turn small network hic...

What Home Fiber Optic Cables Actually Do to Your Eyes 04.11.2026

Warning stickers on home fiber optic gear caution against severe eye damage from invisible lasers, causing unnecessary worry for homeowners handling patch cords. Home optical network terminals emit only a few milliwatts of rapidly diverging infrared light, dozens of times below hazardous exposure limits. While optical inspection loupes can concentrate that beam, the medical literature reveals zero...

Why That In-Wall Fiber Link Refuses to Turn On 04.11.2026

Diagnosing a failed in-wall fiber optic installation starts with basic optics rather than assuming the glass was crushed. A dark SFP port alongside a lit counterpart usually points to simple duplex polarity mismatch, transceiver rate conflicts, or contaminated connector faces rather than ruined conduit runs. From microbending mechanics and visual fault locators to the pitfalls of pulling pre-termi...

Teaching Speech Models to Collapse Spelled Words 04.11.2026

Teaching an automated speech recognition model new vocabulary is a closed-set problem, but teaching it formatting behaviors is an open-ended mapping rule. Fine-tuning a non-autoregressive FastConformer to convert individually spelled letters into unified words requires learning conditional structures rather than just memorizing vocabulary. A look at inverse text normalization, contextual biasing l...

Why Nvidia Artificially Halves Consumer Tensor Math 04.11.2026

GeForce silicon ships with tensor cores capable of double their rated math speeds, intentionally capped by Nvidia to protect professional GPU sales. A community project bypassed the throttle by modifying settings registers at boot rather than overclocking the hardware. This breakdown covers how the register unlock works, the real-world benchmarks across AI training and inference, the persistent bo...

What Happened When Texas Really Flipped 04.11.2026

A sweeping Democratic victory flipped statewide offices across Texas, ending decades of Republican control and sending the state's first Latina governor and first Democratic senator since 1988 into office. Driven by a dramatic collapse in Latino support for the administration, the results expose the difference between lasting realignment and a swift reversion to earlier voting habits. Meanwhile, s...

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.