#6167: Streaming Browser Cookies to a Headless Server

Daniel wants his logged-in browser on the home server. Chrome bolted the front door — so what's left?

cyberattacksauthenticationdigital-privacy

#6166: Turning a Drifted Server Into a Rebuildable Playbook

Your server grew for years. Now you want a recipe that can rebuild it from scratch. Here's the honest path from drift to playbook.

home-automationbackups-and-archivinglinux

#6165: Watching 20 Batch Jobs at Once

Batch APIs give you a discount, then hand you a babysitting job. Here's what actually watches a batch run — and what doesn't.

ai-inferenceworkflow-automationopen-source

#6164: We Gave Each Host Its Own AI Agent

We split our two hosts into separate AI agents with private context windows. The bill came to 78 cents an episode.

multi-agent-systemscontext-and-memoryai-evaluation

#6163: Forking a Keyboard for One Voice Feature

Daniel built a Hebrew-English dictation engine. Now he wants to fuse it into someone else's keyboard — without inheriting its entire future.

speech-recognitionlocal-aiopen-source

#6162: Why Dictated Words Rewrite Themselves

Hold-to-talk dictation shows dimmed text that silently changes when you release the key. Here's the architecture behind that rewrite.

speech-recognitionai-inferencelocal-ai

#6161: Turning Words Into Sound: G2P, IPA, and the Hebrew Vowel Problem

Text-to-phonetics tools exist, but the neural ones guess wrong on exactly the words you care about — names, brands, and Hebrew.

speech-recognitiontext-to-speechtraining-data

#6160: Where Do Tiny Speech Rules Live? A Ladder From Regex to LoRA

A regex notebook, a WFST grammar, or a fine-tune? Where do tiny speech-rewrite rules actually belong in a 600M-parameter model?

speech-recognitionfine-tuninglocal-ai

#6159: When a Speech Model Can't Decide How to Write Dollars

One dataset says "$20," another says "twenty dollars." Fine-tuning a speech model means finding out which convention wins — and why it matters.

speech-recognitiontraining-datafine-tuning

#6158: Naming the ASR Sub-Tasks Nobody Mapped

A 2001 linguistics paper already named Daniel's problem — but it points the other way. So what do you call a fine-tune set that expands "F Y I" to ...

speech-recognitiontraining-datatext-to-speech

#6157: Where to Sit When You're Fine-Tuning Your Own Voice

Your phone's built-in mic is the point — the setup around it is what ruins the takes. Rooms, remotes, and the app setting that deletes your data.

speech-recognitionfine-tuninglocal-ai

#6156: Why Civilization Waited 12,000 Years to Take Off

Ancient engineers built geared computers and self-healing concrete. So why did the industrial takeoff wait until 1760?

history-of-technologytwentieth-centuryancient-world

#6155: Acupuncture, Adenosine, and the Sham Needle Problem

Acupuncture beats sham by about a fifth of a standard deviation. So what is the sham actually subtracting?

ethicshealthcare-systemsstress-and-trauma

#6154: Who Checks the Labels? Weak vs Strong Supervision

Human labels, rule-based labels, or a teacher model writing the exam — what actually makes supervision "strong," and who verifies it?

training-datafine-tuningai-evaluation

#6153: What Are Decision Models Actually For?

Clef, Jev, and OpenAI's Decisions API return typed answers with probabilities in a single forward pass — no generated text to parse.

ai-inferenceai-evaluationprompt-engineering

#6152: Whatever Happened to the One-Time Pad?

The math is unbreakable. The humans are the problem. Tracing the one-time pad from 1882 codebooks to quantum key distribution.

mathematicscryptographyhistory-of-technology

#6151: Invisible Characters That Catch Leakers

Canary traps, binary space codes, and zero-width Unicode characters: how organizations actually trace a leaked document back to its source.

signals-intelligencecyberattackscyberattacks

#6150: The Episode Nobody Meant to Record

A bird, a fridge, a fan, and one red light that nobody remembers turning on. The least professional episode we've ever made.

archaeology