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...

Vizitează neapărat site-ul podcastului și susține-i creatorul: myweirdprompts.com

Autor

Daniel Rosehill

Categorie

Technology

Site-ul podcastului

myweirdprompts.com

Cel mai nou episod

20 nov. 2026

Unde asculți?

Podcasturi în aplicație Replaio Radio În curând

Podcasturile ajung în curând în aplicație. Instaleaz-o acum și fii primul care descoperă o abordare complet nouă a podcasturilor

Descarcă din Google Play Instalează gratuit Android 10 mil.+ descărcări · nota 4,7+ iOS în curând

Episoade

Tuning Hilbert Back from the Surreal 27.10.2026

Listeners noticed something strange when Hilbert began ranting about postal ballots for his staircase and committees for shutting down computer graphics cards. This look behind the scenes explains how vague prompting pushed an eccentric character over the edge into pure surrealism. By dialing back the instructions, the show grounds its fictional producer back in ordinary human stubbornness, nested...

Why Election Fraud Requires Your Opponent to Cooperate 27.10.2026

True election security relies less on body cameras and high-tech seals than on procedural tension between political rivals. From hand-counted slips tallied separately by opposing party representatives to the careful ordering of double-envelope ballots, administrative friction is designed to make discrepancies conspicuous. Looking at the mechanics of Israel's twelve thousand polling stations, this...

Choosing Model Precision, Quantization, and Format 27.10.2026

Download menus often present precision, quantization schemes, and file containers in a single list, obscuring how each piece functions. Model selection requires navigating numerical encodings like BF16 and FP8, reduction recipes like AWQ or Q4_K_M, and packaging standards like safetensors and GGUF. Understanding memory bottlenecks, runtime support across engines like vLLM and llama.cpp, and comput...

Why Protein Design Ignores Astronomical Counts 27.10.2026

Generative AI can churn out hundreds of thousands of candidate molecules, but evaluating these numbers requires facing the staggering scale of biological sequence space. Exploring the mathematics behind amino acid arrangements and chemical universes reveals why exhaustive searches are fundamentally impossible. The discussion breaks down how evolutionary reuse, energy landscapes, and automated desi...

Inside China's Mixed-Language AI Models 27.10.2026

Chinese AI looks vastly different beneath the surface of consumer apps. Despite assumptions of isolated linguistic training, domestic models from DeepSeek to CT-LLM rely heavily on multilingual data, English code, and shared international benchmarks. The investigation explores training recipes, the role of domestic compute clusters, and how regional languages like Kazakh and Uyghur fare inside Man...

Why Forgotten Runpod Workloads Keep Billing 27.10.2026

Standard cloud GPU accounts cannot drop into negative debt, but walking away from a running workload still brings costly surprises. This episode breaks down how Runpod handles zero balances, why stopped pods double their volume storage billing rates, and why deprecated CLI flags like stop-after failed to enforce deadlines. Learn how process exits differ from platform terminations and why auto-refi...

What Global Voter Turnout Trends Really Reveal 27.10.2026

Global voter turnout has faced a multi-decade slide, even as individual high-stakes elections still pull massive crowds to the polls. An examination of international voting data untangles why headline rates drop, how registration rules distort national rankings, and why compulsory systems like Australia differ from voluntary high performers like Malta. The discussion also explores post-communist p...

Choosing Between Modal, RunPod, and Vast.ai 27.10.2026

Fine-tuning open-weight models forces a choice between fundamentally different infrastructure models. This comparison examines how Modal, RunPod, and Vast.ai handle the actual mechanics of training runs, from persistent state and environment setups to hidden costs. Key topics include Modal's Python decorators and scale-to-zero billing, RunPod's Pod-based container workflows and Community pricing t...

How Transformers Process Images and Video 27.10.2026

Transformers originally built for language now power visual perception and image generation. Replacing convolutional networks with self-attention requires turning continuous pixels into discrete vector sequences, which Vision Transformers achieve by treating raw image patches like text tokens. Exploring architectures like ViT and Diffusion Transformers (DiT) shows how swapping inductive visual bia...

Why Model APIs Lack Dedicated Few-Shot Fields 27.10.2026

General model APIs treat few-shot demonstrations as raw text or chat messages rather than structured, versionable task artifacts. While specialized models like iAmTime and LoRA Recycle train directly on explicit demonstration structures, frontier LLM platforms rely on unstructured prompts, XML tags, or massive context windows. An examination of in-context learning shows why adding an examples para...

Why DeepMind Systems Live Outside the Gemini API 27.10.2026

Google DeepMind regularly announces breakthrough systems that never appear as simple endpoints in Google AI Studio or the Gemini API. Exploring systems like AlphaEvolve, Co-Scientist, Genie, and AlphaFold reveals why they are kept separate. The restrictions stem from serving costs, workflow requirements, and commercial strategy rather than mere secrecy, requiring specialized cloud setups, research...

How Google DeepMind Absorbed the Gemini App 27.10.2026

Google DeepMind is often treated as an academic research enclave, but recent reorganisations have turned it into Google's core consumer AI division. Tracing the trajectory from the 2023 merger with Google Brain to the October 2024 shift of the Gemini app team under DeepMind leadership, this episode unpacks the corporate reality behind the branding. It examines UK statutory accounts, leadership cha...

Why Exact Matching Outlasts the Index 27.10.2026

Searching without building a massive index remains surprisingly durable. While modern developer tools often rely on complex indexing, streaming Unix utilities like grep, find, and locate still handle immense workloads by balancing query-time scanning against stale precomputed paths. Exploring Ken Thompson's original 1973 assembly implementation, the Boyer-Moore skipping algorithms behind modern ma...

Training Custom Rerankers for Podcast Search 27.10.2026

Building custom search across a dense podcast archive requires more than off-the-shelf vector retrieval. The real engineering work happens during candidate reranking and data curation. This look at search architecture explores chunking transcripts, navigating the tradeoff between recall ceilings and inference costs, mining hard negatives without accidentally penalizing nuanced matches, and using q...

Why Terminal Fuzzy Finders Forgive Different Mistakes 27.10.2026

Approximate string matching lives between strict regular expressions and semantic retrieval, but different search tools play by entirely different rules. While web search engines rely on edit distances to forgive typos and transpositions, terminal finders like fzf require strict ordered subsequences. This exploration covers how algorithms from Levenshtein, Damerau, Bitap, and Smith-Waterman comput...

Why Semantic Desktop Search Struggles to See Files 27.10.2026

Semantic vector search is finally arriving on operating systems, but finding files locally remains surprisingly tricky. Operating system updates to Apple Spotlight and Windows Search now bring local embedding models to personal computers, yet application boundaries, missing OCR, hardware gates, and cloud placeholders create blind spots. Examining native implementations alongside independent tools...

Blind Testing AI Video Models for Architects 27.10.2026

Evaluating AI video models requires more than skimming glossy vendor demos, especially when an architectural project cannot tolerate shifting walls or warping window mullions. Evaluating tools like GenMedia, media-gen-arena, and GenMediaBenchmark reveals the practical mechanics of running internal blind pairwise comparisons. Rigorous testing demands tracking settings, managing per-clip generation...

Why Fine-Tuning Whisper Won't Stop Duplicated Text 27.10.2026

Speech recognition errors are often blamed on model weights when the real culprit is inference orchestration. Fine-tuning an acoustic model will not fix duplicated phrases caused by chunk merging, fallback temperature schedules, or silence heuristics. By examining Whisper's DecodingOptions, beam search trade-offs, and WhisperX's choice to disable conditioning on previous text, this discussion maps...

Building an AI Rubric to Rank Israeli Parties 27.10.2026

A voter's 42-minute personal recording turns into an explicit voting rubric for Israel's twenty-sixth Knesset election. Using Claude research agents to score platforms against prioritized issues like tenant protections, cost of living, and public services rather than standard headline debates, the experiment yielded surprising party rankings. An examination of the findings reveals a striking polit...

Choosing the Right Audio Annotation Tool 27.10.2026

Turning raw environmental recordings into machine learning datasets requires choosing between lightweight inspection tools and heavyweight crowd platforms. From offline desktop staples like ELAN and Praat to self-hosted frameworks like Label Studio, Potato, and bioacoustic-focused Whombat, each tool handles timeline events differently. The discussion covers tier management for overlapping sounds,...

Finding Recurring Urban Sounds With Four Examples 27.10.2026

Training an audio detector does not always require hundreds of manual annotations. Borrowing methods from bioacoustic few-shot sound event detection, a system can use pretrained audio neural networks to locate recurring noises like train horns from just four or five distinct examples. The discussion covers model-assisted labeling workflows, using prototypical networks on top of PANNs embeddings, a...

Why Dictation Models Steal Other People's Voices 27.10.2026

Speech recognition models can transcribe every word accurately while capturing the wrong person's conversation. Fine-tuning a recognizer on a single voice does not teach it to ignore clean, loud background speech like train platform announcements. Addressing issues in systems like Parakeet requires target-speaker conditioning, diarization-dependent masks, or enrollment embeddings rather than raw a...

Teaching Dictation Models to Ignore Other Voices 27.10.2026

Standard speech recognition will faithfully transcribe clear background announcements into a personal document. Target-speaker automatic speech recognition attempts to fix this by enrolling an authorized user's voice and conditioning the transcription on that acoustic identity. A look at how speaker embeddings, attention conditioning, and architectures like Speaker-Querying Whisper handle interfer...

Why Speech Recognizers Cut Off Hesitant Speakers 27.10.2026

Speech recognition systems routinely cut callers off mid-thought, mistaking a hesitant pause for a finished turn. The mechanics behind endpointing reveal why accurate vocabulary models still fail in emergency dispatch and accessibility tools. Looking at pause frequency, duration, and repair structure across spontaneous speech, older adults, and clinical cohorts shows that human hesitation follows...

When Splitting Serverless Apps Earns Its Keep 27.10.2026

Architectural boundaries often reflect deployment schedules rather than execution limits. On platforms like Modal, grouping web endpoints, background cron jobs, and heavy GPU workers into a single app provides atomic deployments without sharing containers, scaling budgets, or container images. Splitting these workloads into separate apps isolates blast radiuses and decouples release cadences, but...

Ascultă podcastul My Weird Prompts în Replaio

Radio și podcasturi într-o singură aplicație - gratuit și fără înregistrare. Instaleaz-o azi și nu rata lansarea

Descarcă din Google Play

Replaio nu este editorul podcasturilor; numele emisiunilor, coperțile și materialul audio aparțin autorilor lor și sunt distribuite prin fluxuri RSS publice