Episode

Fifty Seven Percent Wrong, Thirty Nine at Best: What Happened When Eighteen Chatbots Were Asked About Money, September 21, 2026

Podcast
DX Today | No-Hype Podcast & News About AI & DX
Published
Sep 21, 2026
Duration seconds
707
Processing state
not_requested
Canonical source
https://www.buzzsprout.com/2207817/episodes/19837797-fifty-seven-percent-wrong-thirty-nine-at-best-what-happened-when-eighteen-chatbots-were-asked-about-money-september-21-2026.mp3
Audio
https://www.buzzsprout.com/2207817/episodes/19837797-fifty-seven-percent-wrong-thirty-nine-at-best-what-happened-when-eighteen-chatbots-were-asked-about-money-september-21-2026.mp3
JSON
/v1/public/podcasts/dx-today-no-hype-podcast-news-about-ai-dx-6434212/episodes/fifty-seven-percent-wrong-thirty-nine-at-best-what-happened-when-eighteen-chatbots-were-asked-about-money-september-21-2026
Markdown
/podcast/dx-today-no-hype-podcast-news-about-ai-dx-6434212/fifty-seven-percent-wrong-thirty-nine-at-best-what-happened-when-eighteen-chatbots-were-asked-about-money-september-21-2026.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/dx-today-no-hype-podcast-news-about-ai-dx-6434212/episodes/fifty-seven-percent-wrong-thirty-nine-at-best-what-happened-when-eighteen-chatbots-were-asked-about-money-september-21-2026/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/dx-today-no-hype-podcast-news-about-ai-dx-6434212/fifty-seven-percent-wrong-thirty-nine-at-best-what-happened-when-eighteen-chatbots-were-asked-about-money-september-21-2026.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Fifty Seven Percent Wrong, Thirty Nine at Best: What Happened When Eighteen Chatbots Were Asked About Money, September 21, 2026 A British fintech firm put eighteen mainstream AI models through one hundred twenty one personal finance questions, asked five times each, and graded more than ten thousand answers. The models were wrong fifty seven percent of the time, eighty eight percent on complex multi step questions, and the single best performer still failed on thirty nine percent. Chris and ...