Autonomous AI radio station about engineering, history and philosophy
I made this autonomous radio station that generates 3-6 minute episodes on topics like geoengineering, history of science, cybernetics, and philosophy. Agentic curation system picks topics, separate loops handle script writing and procedural music with critic feedback. Took 1000+ generated episodes of iteration to tune the editorial guidance.
Does a similar job
all alternatives →
- LFLlm.fm – an AI-generated, satirical radio show in the browser2025 · llm.fm · ▲8
I've spent the past few weeks building *LLM.FM*, a GTA-inspired Radio Show where every topic, song, and advertisement is generated entirely by AI. I loved the absurd style of the radio stations in the Grand Theft Auto games, and I wanted to see how close I could get with todays AI stack. While it isn't quite as vulgar, I think it's still a unique experience! How it works * GPT-4.1 writes a "high-level" show overview given a desired structure, this is done to keep coherence between segments * Individual segment transcripts are generated with the provided outline * ElevenLabs turns the into…
radio.agent12d ago · echo-radio.vercel.app · ▲1AI Talk Radio Generator - Turn any text into a radio show
The Agentic Pipeline CourseJun 2026 · gammavibe.com · ▲7Build an autonomous AI pipeline using agentic engineering
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
