Rethinking AI: Building What Matters, Not Just What's Possible
summary
A working parody-generation pipeline uses LLMs with function/tool calling, a Python class for inputs/outputs, and dual agents—a writer and editor—to generate, critique and filter satirical news. A Persona Hub of 200,000 personas injects distinct voices, FastHTML publishes live demos, and a feedback loop ranks and saves top outputs. The project produces genuinely funny articles, surfaces dual‑use risks (it mirrors underground fake‑news machinery), and demonstrates practical techniques that scale.
AI-written summary · about
related talks
38mGenerative AI Agents: How they Work and How to Build One
37mGenerative AI: Beyond (Just) Hype
43mThe Shitposting AI - An Ironic Solution to Fruitless Online Debate
01h 03mIt's All About AI
20mHave AI Got News for You
55mAI Showdown: The Good, The Glitchy, and The Risky
19mBeyond agents: AI as a creative partner
45mThe Expanding Dark Forest and Generative AI