{
  "id": 16736588,
  "title": "Titanic Séance: ask the 891 passengers what the night would have done to you",
  "url": "https://urgent.news/2026/10/27/titanic-seance-ask-the-891-passengers-what-the-night-would-have-done",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-27T10:55:44.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/khushi886987/titanic-seance-ask-the-891-passengers-what-the-night-would-have-done-to-you-5c5j"
  },
  "original_language": "en",
  "account": "In April 1912, the web application Titanic Séance invites users to imagine themselves as one of the 891 passengers aboard the ill-fated ship. By entering details such as ticket class, age, traveling companions, and boarding location, the app uses a TabPFN-3.5 model trained on the passenger data to predict the likelihood of survival. Users can then hear from a real passenger whose information most closely matches their own, as spoken by the Gemma 4 language model. This interactive experience was developed as part of the DEV Hacktoberfest 2026 Ghost in the Machine challenge. The app's creators have put significant effort into ensuring accuracy and empathy in the responses, carefully selecting which personal details the AI can share and teaching the model to avoid inventing false memories.",
  "summary": "Titanic Séance is a small web app where you tell the spirits who you would have been in April 1912: which ticket you held, how old you were, who you travelled with, and where you boarded. Two things happen. First, a TabPFN-3.5 model trained on the 891 passengers whose fate is recorded gives you your chance of surviving the night, plus a few what-ifs (\"if you had been travelling alone\", \"if you…",
  "key_points": [
    "Titanic Séance lets users experience life on the ill-fated ship",
    "AI predicts survival chances based on passenger details",
    "Gemma 4 language model voices real passengers"
  ],
  "editors_take": "By combining historical passenger data with predictive modeling and generative voice, this application transforms archival records into an immersive, empathetic tool for exploring individual fates during the maritime disaster.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}