hallucination

also referred to as: hallucinations

3 statements across 3 episodes · 3 bullish · 0 bearish · 3 people on the record · first statement Nov 22, 2025 by Matthias Wagner · across every show →

Everything said about hallucination, oldest first

Nov 22, 2025 positive
Insight
Wagner: Task-specific knowledge injection effectively reduces LLM hallucinations
“The way to, like, get them to behave the way we want them to behave is just with context engineering and injecting the right knowledge for the right kind of tasks they're doing. And that's incredibly effective, right? That reduces hallucinations, that makes th…”
Matthias Wagner Nov 22, 2025 ▶ 16:25 ⚡️ Building the AI Hardware Engineer with Matthias Wagner, Co-founder of Flux
Feb 5, 2026 positive
Assertion Supported
Deng: Models internally represent uncertainty preceding hallucinatory behavior
“We've seen that models internally have some awareness of like uncertainty or some sort of like user pleasing behavior that leads to hallucinatory behavior.”
Myra Deng Feb 5, 2026 ▶ 27:50 Goodfire AI’s Bet: Interpretability as the Next Frontier of Model Design — Myra Deng & Mark Bissell
Jun 30, 2026 positive
Insight
Edunov: Predicting molecular poses is necessary to validate drug discovery models
“Yes, it's an abstraction, but it's a very useful abstraction. It helps us to build up confidence that a particular model output is actually valid. Whether you did not just straight up hallucinate at something, because yes, ultimately what matters is binding af…”
Sergei Yudinov Jun 30, 2026 ▶ 45:18 🔬 "The Most Innovative Diffusion Research Is Happening in Drug Discovery, Not Image Generation"
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.