| Sharing something I built. You give it a historical topic, it researches it, writes a two‑host script, generates the audio and slides, and plays it. The interesting part to build was the interruption: you stop the episode, ask something, it answers in the hosts' voices using the episode's context, then splices back into the story. It's research‑grounded (pulls sources instead of free‑associating) and flags legend vs established fact, which matters a lot for history. Genuinely curious what people here think about the accuracy angle. My own take is the interruption is a trust feature, you can push back on a claim in real time and make it defend itself. Demo's on the site if you want to poke holes [link] [comments] |