EPISODE · Sep 20, 2025 · 0 MIN
AI's Guessing Game
from AI Odyssey · host Anlie Arnaudy, Daniel Herbera and Guillaume Fournier
Ever wondered why AI chatbots sometimes state things with complete confidence, only for you to find out it's completely wrong? This phenomenon, known as "hallucination," is a major roadblock to trusting AI. A recent paper from OpenAI explores why this happens, and the answer is surprisingly simple: we're training them to be good test-takers rather than honest partners.This description is based on the paper "Why Language Models Hallucinate" by authors Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala, and Edwin Zhang. Content was generated using Google's NotebookLM.Link to the original paper: https://openai.com/research/why-language-models-hallucinate
What this episode covers
Ever wondered why AI chatbots sometimes state things with complete confidence, only for you to find out it's completely wrong? This phenomenon, known as "hallucination," is a major roadblock to trusting AI. A recent paper from OpenAI explores why this happens, and the answer is surprisingly simple: we're training them to be good test-takers rather than honest partners.This description is based on the paper "Why Language Models Hallucinate" by authors Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala, and Edwin Zhang. Content was generated using Google's NotebookLM.Link to the original paper: https://openai.com/research/why-language-models-hallucinate
NOW PLAYING
AI's Guessing Game
No transcript for this episode yet