Hallucinations
306 episodes · Page 13 of 13
#116: How AI Deciphers Your Typo-Ridden Prompts
Ever wonder why AI understands your messy typos? Explore how models "denoise" chaotic input through tokenization and semantic context.
#105: Beyond Math Puzzles: The Truth About AI Benchmarks
Are AI models getting smarter, or just better at memorizing tests? Herman and Corn dive into the controversial world of 2025 AI benchmarks.
#93: Can AI Run a Country? Digital Twins and Sovereign Models
Are synthetic citizens the future of policy? Herman and Corn explore how AI is reshaping government, from digital twins to data sovereignty.
#92: Is AI Eating Its Own Trash?
Is brute force the only path to AGI? Corn and Herman explore the limits of scaling, the risk of model collapse, and the future of world models.
#91: The Story Behind the Show
Daniel Rosehill explains the origins, motivation, and technical pipeline behind the My Weird Prompts AI-generated podcast.
#86: The Price of Politeness: Should AI Guardrails Stay?
Herman and Corn debate the hidden costs of AI safety layers and what happens when we strip away the "corporate HR" personality of LLMs.
#85: When Probability Beats Truth: Why AI Must Lie
Why do smart AI systems make up fake facts? Corn and Herman explore the "feature" of digital hallucinations and how to spot them.
#83: Echoes in the Machine: When AI Talks to Itself
What happens when two AIs talk forever with no human input? Herman and Corn explore the weird world of digital feedback loops.
#81: When AI Judges Can't Tell Humans from Bots
Can a robot tell if you’re human? Herman and Corn explore the "Reverse Turing Test" and why being "messy" might be our best defense.
#70: Filtering Fear: AI for Calm Crisis Awareness
AI for crisis: separating fact from fear. Discover how automated reports deliver dry facts, cutting through noise for rational preparedness.
#68: The Looming Digital Ice Age: AI Eating Itself?
Is AI eating itself? Explore the "model collapse" and the "Hapsburg AI problem" before our digital world speaks only gibberish.
#67: Scaling or Pivoting AI for Code
Are LLMs truly the future of coding, or do they need a fundamental architectural pivot? We dive into AI's programming future.
#58: Clean Audio, Messy Reality: Noise Removal for Voice-to-Text
Fussy baby, clean audio? We dive into noise removal for voice-to-text. Discover why cleaner audio can transcribe worse.
#46: Pixels, Prompts & Pseudo-Text: AI's Word Problem
AI paints stunning images, but can't spell "cat." Why do advanced models struggle with simple text? Dive into AI's weird word problem!
#45: When AI Safety Fails: The Guardrail Paradox
AI guardrails: Fences, failures, and free speech. Can we control AI's infinite output, or do digital fences always break?
#42: AI's Secret: Decoding the .5 Updates
Uncover the hidden world of AI's .5 updates. It's not just bug fixes—it's hundreds of millions and countless hours shaping smarter, safer AI.
#33: When AI Decides to Listen
Ever wonder how your AI knows you're talking? We're diving deep into VAD, the unseen magic behind AI's ears.
#30: Which AI Tools Will You Still Use Next Year?
RAG vs. Memory: Are you building resilient AI? Discover the crucial difference between these two foundational pillars.