Concept · 10 episode(s)

Hallucination

Definition

Hallucination is when a language model confidently produces content that is factually false or fabricated — nonexistent citations, invented APIs, made-up history. It’s the most user-visible failure mode of LLMs and a major frontier problem for any deployment where being wrong is expensive.

Episodes covering this

072
A Robot Made Graphene Without Help, And Caught Itself Hallucinating
Shi, Zheng, Juan et al. · Princeton University·29 min·May 23, 2026
070
When Models Know the Answer But Say the Wrong Thing Anyway
Yeom, Sok, Kim et al. · Graduate School of Data Science·22 min·May 22, 2026
069
When Smarter Models Forecast Worse: The Hidden Failure Mode in LLM Predictions
Merrill, Lee, Karger · Forecasting Research Institute / UC Berkeley·30 min·May 22, 2026
067
An AI Just Solved a 1996 Erdős Problem—and the Simplest Agent Won
Tsoukalas, Kovsharov, Shirobokov et al. · Google DeepMind·31 min·May 22, 2026
062
Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety
Zhang, Zheng, Yang · Shenzhen University·24 min·May 20, 2026
059
Firefly's Inversion: Building Verified Tool-Call Training Data by Working Backward
Lu, Wang, Lu et al. · Northeastern University·22 min·May 20, 2026
058
Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
Liu, Holz, Ye et al. · University of Chinese Academy of Sciences·32 min·May 19, 2026
043
When 'This Is False' Doesn't Stick: Why Models Learn the Lie Anyway
Mayne, McKinney, Dubiński et al. · University of Oxford·18 min·May 14, 2026
037
Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
Elbadry, Heakl, Zhang et al. · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)·27 min·May 12, 2026
025
The Missing Gradient Term That Predicts Sycophancy in RLHF
Gauthier, Bach, Jordan · Inria·22 min·May 07, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.