
My Weird Prompts
6,581 episodes — Page 11 of 132
Auditing a Sycophantic Model From the Inside
Oct 21, 202622 min
Recipes vs. Regeneration: AI Photo Editing in 2026
Oct 21, 202621 min
AI Audio Restoration: What Actually Ships in 2026
Oct 21, 202624 min
One Endpoint, Many Boxes: Local LLM Routing
Oct 21, 202619 min
What It's Like to Be a Token Inside an LLM
Oct 21, 202622 min
Hebrish: Hebrew-Aware Dictation That Actually Works
Oct 21, 202622 min
Streaming Browser Cookies to a Headless Server
Oct 20, 202620 min
Turning a Drifted Server Into a Rebuildable Playbook
Oct 20, 202624 min
Watching 20 Batch Jobs at Once
Oct 20, 202621 min
We Gave Each Host Its Own AI Agent
Oct 20, 202623 min
Forking a Keyboard for One Voice Feature
Oct 20, 202622 min
Why Dictated Words Rewrite Themselves
Oct 20, 202625 min
Turning Words Into Sound: G2P, IPA, and the Hebrew Vowel Problem
Oct 20, 202624 min
Where Do Tiny Speech Rules Live? A Ladder From Regex to LoRA
Oct 20, 202625 min
When a Speech Model Can't Decide How to Write Dollars
Oct 20, 202618 min
Naming the ASR Sub-Tasks Nobody Mapped
Oct 20, 202623 min
Where to Sit When You're Fine-Tuning Your Own Voice
Oct 20, 202621 min
Why Civilization Waited 12,000 Years to Take Off
Oct 20, 202631 min
Acupuncture, Adenosine, and the Sham Needle Problem
Oct 20, 202630 min
Who Checks the Labels? Weak vs Strong Supervision
Oct 20, 202631 min
Decision Models: Typed Answers in One Forward Pass
Oct 20, 202623 min
Whatever Happened to the One-Time Pad?
Oct 20, 202624 min
Invisible Characters That Catch Leakers
Oct 20, 202621 min
Under the Other Sticky Notes
Oct 20, 20268 min
4 Hard Fails in 84 Answers: Testing AI Bias on Israel-Palestine
Oct 19, 202626 min
The Tiny Hebrew Models Behind the Show's Voice
Oct 19, 202630 min
Hebrew AI: Ears, Mouth, and Brain
Oct 19, 202626 min
Grounding Is Not Solved: DIY vs Gateway vs Native Search
Oct 19, 202625 min
Do LLMs Nod Along With Conspiracy Theories?
Oct 19, 202623 min
8 Real Steganography Cases and How They Got Caught
Oct 19, 202625 min
Propaganda Bait: Testing 7 Models in 5 Languages
Oct 19, 202622 min
We Gave 4 AI Models the Same Toast Prompt
Oct 19, 202618 min
Overheard at the Laundrette
Oct 19, 202622 min
Did Flight FZ1073 Really Happen? Inside a False-Flag Claim
Oct 19, 202625 min
Which AI Writes Our Scripts Best? We Tested Five
Oct 19, 202624 min
Hebrish on iPhone: MLX, Core ML, or Wait?
Oct 19, 202620 min
Two Ways a Chinese Open Model Gets Censored
Oct 19, 202629 min
How We Chose Our New Script Writer
Oct 19, 202623 min
How Many Runs Does Your AI Eval Actually Need?
Oct 19, 202623 min
Cheap Tokens, Expensive Scripts
Oct 19, 202621 min
One Rater Is Enough: Designing Daniel's Taste Test
Oct 19, 202623 min
How to Run a Model Eval on a Budget
Oct 19, 202622 min
Judging the Judges: How AI Evaluates Creative Writing
Oct 19, 202623 min
Picking a Human Labeling Tool for LLM Benchmarks
Oct 19, 202621 min
How to Build an AI Preference Dataset
Oct 19, 202622 min
Where the Screws Go: Internal KVM Mounting
Oct 19, 202625 min
Haiku 5.5 at 10 Cents: What the Cheap Model Actually Does
Oct 19, 202622 min
Can You Train a Machine to Be Funny?
Oct 19, 202633 min
Which Env Var Wins? Cloud vs. Local Precedence
Oct 19, 202625 min
One Vault, Two Readers: Secrets for a Home AI Gateway
Oct 19, 202622 min