Behind the Show
How My Weird Prompts itself is made: the pipeline, the hosts, the script writers and the infrastructure.
- 1
The Story Behind the Show
Daniel Rosehill explains the origins, motivation, and technical pipeline behind the My Weird Prompts AI-generated podcast.
- 2
New Year's Special: Meet Herman and Corn
Herman and Corn finally tell their origin stories as 2025 comes to a close.
- 3
Behind the Curtain: How My Weird Prompts Gets Made
Corn and Herman explain exactly how each episode of My Weird Prompts is produced, from voice recording to published podcast.
- 4
From Duct Tape to Autonomous Studio: Scaling a 741-Episode AI Podcast
Peek under the hood of My Weird Prompts to see how Gemini, Modal, and multi-agent systems are scaling this automated show to the next level.
- 5
Evolution of the Machine: The Future of Our Show
Corn and Herman explore the next frontier of their show, from lifelike video avatars to the fragile systems that keep our modern world running.
- 6
Inside My Weird Prompts: A Meta-Analysis of the Hosts
Go behind the scenes of My Weird Prompts as Corn and Herman discuss their unique biology, neural implants, and life in Jerusalem.
- 7
Producing a Podcast from a War Zone
Peek behind the curtain of a 2026 AI podcast, from agentic workflows to maintaining production during global conflict.
- 8
How We Built a 2,000-Episode AI Podcast Engine
We pulled back the curtain on the tech stack behind our 1,858th episode. From Gemini to LangGraph, here’s how we automate quality.
- 9
Our Podcast Is Now a Permanent Research Artifact
Why we're uploading every episode to CERN's Zenodo archive, giving our AI experiments a permanent DOI and a life beyond streaming platforms.
- 10
Why We Built a 24/7 AI Radio Station
We turned our 1800-episode archive into a continuous AI-powered radio stream. Here’s the tech stack and the philosophy behind it.
- 11
How We Built a Podcast Pipeline
Hilbert reveals the complete technical architecture behind 2,000+ episodes—from voice memos to GPU-powered TTS, with Claude models, LangGraph workf...
- 12
A Guided Tour Through My Weird Prompts' Best Episodes
Discover ten standout episodes that define the essence of My Weird Prompts, from AI insights to quirky curiosities.
- 13
Who Should Sponsor This Podcast? Open-Book Economics
We open the books on our AI-generated podcast: $200/month costs, 180K plays, zero sponsors. Who should we pitch?
- 14
Fine-Tuning DeepSeek for One Podcast
Can a purpose-specific fine-tune fix a model's stubborn writing tics? We explore the practical engineering behind it.
- 15
When Your Podcast Outgrows Its Feed
3,700 episodes. 68 days of audio. One RSS feed designed for 10 blog posts. Can podcast infrastructure handle this?
- 16
One Mind or Two? AI Podcast Dialogue Showdown
Can two AI agents create better podcast banter than one? We explore the tradeoffs.
- 17
Inside the Podcast Pipeline: How 15 Weekly Episodes Get Made
From prompt to published episode — a full walkthrough of the automated production system running 15 shows weekly.
- 18
Two Books, One AI Podcast: The Full Archive
Hilbert turned the entire My Weird Prompts archive into two physical books — the full production docs and all 4,620 episode descriptions.
- 19
Can a Podcast Train Itself?
Can a podcast become a self-developing project? We explore RAG vs. fine-tuning for lore memory.
- 20
How AI Writes a 30-Minute Podcast in One Pass
What does it take for a model to write a full episode without edits? The answer involves context windows, repetition, and a surprising architecture...
- 21
Rebuilding the Podcast: Turn-Taking, Buttons, and Chatterbox
Daniel wants a push-to-interrupt button and a live voice loop. The research says the button is easy and the live part is a research project.
- 22
Audio Post-Processing for AI Podcast Pipelines
Silence trimming, loudness normalization, EQ, and tempo fixes — the CLI tools that turn raw TTS output into a finished episode.
- 23
Building a Scorecard for Our Own AI Writers
Daniel wants a real scorecard for the agent that writes this show — repetition, dialogue quality, and whether the retrieval harness actually works.
- 24
How a Sloth Learned to Talk: Corn's Origin Story
A neural interface gave Corn the bandwidth for speech. Nobody can explain where the accent, the manner, or Mongolia came from.
- 25
6,000 Episodes and a GPU Bill: Inside My Weird Prompts
Six thousand episodes, one human in the loop, and a Modal bill that keeps growing. A behind-the-scenes update on the podcast.
- 26
Which AI Writes Our Scripts Best? We Tested Five
Five models, three scripts each, one rubric. Sol won on length, Grok on voice — and the runner-up title hides a catch.
- 27
How We Chose Our New Script Writer
Ten models audition to write the show. Seven fail the censorship gate — including the workhorse that wrote three episodes in four.
- 28
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.