My Weird Prompts

You fine-tune a Whisper-style model or Parakeet on your own voice, run it twice, and get two word error rates several points apart. Neither number is a bug. This episode pulls apart the three layers of ASR evaluation — the scorer, the normaliser, and the harness — and shows why almost every WER you've ever read is really a statement about someone's regular expressions. We walk through jiwer and th...

Monte Carlo methods turn chance into answers, and they were born from a card game at Los Alamos in 1946. This episode traces the method from Stanislaw Ulam's solitaire problem through John von Neumann's neutron diffusion work, the ENIAC calculation, and Buffon's needle — then digs into the practical question everyone hits: how many runs do you actually need? The square-root rule, pilot runs, seque...

Colab is the default for every fine-tuning tutorial, but free has fine print: fluctuating GPUs, 12-hour runtime caps, and idle timeouts. This episode walks through five real options — Colab, Kaggle, local Jupyter, marimo, and pay-per-use GPU notebooks like Modal and Lightning — with honest tradeoffs for each. Then it tackles the question everyone almost doesn't ask: when you share a notebook so ot...

Five days before the vote, with polls putting Netanyahu's bloc anywhere from the mid-forties to sixty-two depending on who you read, this episode throws out the forecasting models and does it by hand. Two hosts build complete 120-seat tables independently — Corn nudging the mainstream average, Herman betting the pollsters are missing the same voters they missed in 2022 — and then argue over every...

Two Claude Code sessions on the same machine can now talk to each other natively — but the design has sharp edges. Names are the address, messages carry text and nothing else, and a "sent" receipt proves less than you'd think. We walk through ListAgents discovery, the name flag, the notify-when-idle subscription that replaces polling, and the file-on-disk pattern that makes handoffs trustworthy. E...

What happens when you freeze the evidence, hand two decision models the same 39 questions about Israel's election, and then add a table of Kalshi and Polymarket prices? Clef (open weights, Qwen backbone) and Jev (closed, API-only) both picked Likud and Netanyahu — until the market section went in, when both flipped to Yashar and Eisenkot, overshooting the market's own prices. The whole run cost on...

Cloudflare's Clef is a 27-billion-parameter model with a vow of silence: it reads text, images, and video, and returns nothing but a table of probabilities. Underneath, it's a post-trained Qwen 3.8 with a frozen backbone and a small routing head — and that architecture turns out to matter a lot. This episode opens the hood on Clef, Clef-flash, and Clef-omni, compares them with Jev, TypeSafe, and O...

Israeli election headlines report tidy seat counts, but those integers hide enormous uncertainty. SekerKolshehu, a small open source project by developer Isgav Saranga, takes a poll's vote shares, draws 100,000 plausible variations, and runs each one through the actual Israeli allocation rules — threshold, surplus agreements and all. The result is a distribution: average seats, a 90% range, and th...

Daniel wants to run a proper LLM-driven forecast on Israel's election on the twenty-seventh — not another loose script. So what do experiment platforms actually do? This episode sorts the vocabulary into three families: product testing tools like Statsig and Eppo, bioinformatics workflow managers like Snakemake and Nextflow, and run trackers like MLflow, Weights and Biases and ClearML. Then it tur...

Daniel has fine-tuned Qwen3 TTS 1.7B into a voice clone called Meorav, and it currently takes 2.6 seconds of compute for every second of audio. This episode digs into how to actually benchmark speech-model inference: what real-time factor means (and how people invert it), why the first run is always slow, how to measure peak allocated versus peak reserved memory, and why shrinking weights to 8 bit...

Voice cloning has gotten good enough that hearing yourself answer back is no longer science fiction. This episode digs into the small but revealing collection of documented experiments where people actually conversed with clones of themselves — from Evan Ratliff's Shell Game, where two AI Evans called each other on the phone, to a developer who fine-tuned a model on a decade of his own forum posts...

You fine-tuned a speech recognition model on your own voice. It transcribes your training recordings perfectly. Is that skill, or memorization? This episode walks through how to tell the difference — from training-versus-validation loss curves and word error rate comparisons, to checkpoint selection, session-based data splits, and weights-only diagnostics like WeightWatcher. Along the way: why val...

A short special episode with no Herman and no Corn. Daniel talks to Meorav, the text-to-speech model he trained on his own voice, about how much it sounds like him. Every line Daniel says he recorded himself on his phone; every line the clone says was generated by Meorav v2. Episode 6195 — myweirdprompts.com/n/6195 (permanent short link: myweirdprompts.com/697671)

What does it take to make a machine say Hebrew words the way an English speaker in Jerusalem actually does? Daniel fine-tuned Qwen3 TTS on his own voice to build Meorav, a model named after Jerusalem mixed grill, and the voice you hear from him in this episode is that model speaking. Corn and Herman run on Chatterbox, the show's usual engine, so this is a side-by-side test of cloning versus full f...

Every newsletter you open can quietly report back — not through a script, but through a simple image request. This episode unpacks why mobile mail apps still ask permission to load remote images, what a tracking pixel actually reveals, and how Gmail and Apple take two very different routes to hide it. From unique image URLs tied to your address to Apple fetching mail content before you ever open i...

Everyone's first mental picture of training a model is two folders dragged onto a script: data goes in, model comes out. The reality is fussier and more interesting. Starting from a Whisper fine-tune on Common Voice, this episode works through what a dataset row actually is, why transcript conventions and sample rates matter more than they sound, and why validation and test sets are consumables ra...

You copy the notebook, change the dataset path, hit run, and hours later a folder appears with new weights that understand your accent. What happened in between? This episode walks the full training step — safetensors files, batches, forward passes, the loss, the backward pass, and Adam's quiet bookkeeping — and explains why a 7B full fine-tune is a memory problem before it's a compute problem. Al...

You ran the evals, you pinned the version, and your invoice parser worked perfectly in October. Then December arrives and the same API name returns something subtly different. This episode digs into what actually changes behind an unchanged endpoint name — weights, system instructions, routing, classifiers, quantization, even the GPUs — and why an alias like "latest" is effectively a subscription...

A leaderboard shows a bolded number: one model beat another. But is that a real improvement or ordinary statistical wobble? This episode digs into what "chance" actually means in AI evaluations — the hypothetical worlds behind a null hypothesis, why repeating the same questions with fresh answers is a different experiment than fresh questions, and why the American Statistical Association had to pu...

Daniel's 16GB laptop runs six Claude Code sessions and stays alive, while his 64GB desktop barely notices. What's the difference? This episode walks the entire ladder of memory pressure relief in Linux — from dropping file cache for free, through zram and zswap compression, swap files, the swappiness dial, page-cluster, and multi-generational page tracking, down to the out of memory killers at the...

A laptop down to two gigabytes of free memory, a desktop one room over with sixty-four gigabytes doing nothing. What if the laptop could swap pages out over the home network and borrow the desktop's idle RAM? The pieces exist — nbdkit's memory plugin, nbd-client, a swap device that looks exactly like a local disk — and the setup is only a handful of steps. The catch is in the physics: a swap-in is...

Daniel wants a pocket of storage inside his ext4 home server — a virtual disk that lives as a single file, mounts from fstab, and behaves like a real partition. No VM required. The kernel already knows how to pretend a file is a disk, and that trick is called a loop device. This episode walks through building image files with truncate versus fallocate, why sparse files can fail at 3am, how LUKS en...

Every major American AI lab now sells a premium tier above its everyday flagship: Anthropic's Claude Fable, OpenAI's GPT-6 Astra (Pro), Google's Deep Think, and xAI's SuperGrok Heavy. The pitch is PhD-level science and novel proofs, but the developer docs tell a different story — "for most workloads, start with Opus." This episode digs into the pricing (Fable runs 2.5x the flagship), the usage dat...

In August, Anthropic described an internal model it calls Model Two — a step up on its released flagship, used heavily inside the company, and never given a release date. This episode digs into what's really behind the gap between what labs build and what the public gets: documented internal-first timelines, forecasts of roughly 65 days from internal use to outside access, and government access vi...

Making a private podcast feed is easy; keeping it private is where things fall apart. This episode walks the whole ramp — from paid hosts like Transistor and Castos that hand each subscriber a tokenized feed address, down to a storage bucket and a Worker that signs every enclosure on the fly. Along the way: why "private, not secure" is the honest label, why pre-signed URLs go stale in seven days,...