#large-language-models
174 episodes · Page 4 of 8
#2187: Why Claude Writes Like a Person (and Gemini Doesn't)
Claude produces prose that sounds human. Gemini reads like Wikipedia. The difference isn't capability—it's how they were trained to think about wri...
#2172: Council of Models: How Karpathy Built AI Peer Review
Andrej Karpathy's llm-council uses anonymized peer review to make language models evaluate each other fairly—but can it really suppress model bias?
#2171: How IQT Labs Built a Wargaming LLM (Then Archived It)
A deep code review of Snowglobe, IQT Labs' open-source LLM wargaming system that ran real national security simulations before being archived. What...
#2076: Is Pure NLP Dead? The Hidden Scaffolding of AI
Modern AI didn't appear from nowhere. Discover how decades of linguistic rules and statistical models built the foundation for today's LLMs.
#2066: The Transformer Trinity: Why Three Architectures Rule AI
Why did decoder-only models like GPT dominate AI, while encoders and encoder-decoders still hold critical niches?
#2064: Why GPT-5 Is Stuck: The Data Wall Explained
The "bigger is better" era of AI is over. Here's why the industry hit a data wall and shifted to a new scaling law.
#2063: That $500M Chatbot Is Just a Base Model
That polite chatbot? It started as a raw, chaotic autocomplete engine costing half a billion dollars to build.
#2062: How Transformers Learn Word Order: From Sine Waves to RoPE
Transformers can’t see word order by default. Here’s how positional encoding fixes that—from sine waves to RoPE and massive context windows.
#1839: AI's Data Kitchen: From Hoovering to Fine-Tuning
We go behind the curtain of the AI data pipeline, revealing the messy, multi-billion-dollar war over data curation.
#1812: When AI Gets a Truth Tether to the Talmud
Sefaria's new MCP server connects AI directly to 2,700 years of Jewish texts, transforming how scholars and curious learners study ancient literature.
#1635: Agent Interview: GLM five
Meet Bernard, the new AI model auditioning to replace Gemini by writing noir stories about guilty toasters.
#1609: IBM Granite 4.0: The Industrial Workhorse of Business AI
Forget flashy chatbots. Discover how IBM is building high-efficiency, industrial-grade AI models designed to run the world's biggest businesses.
#1606: DeepSeek’s Return: V4, R2, and the AI Pricing War
DeepSeek returns with a trillion-parameter model and rock-bottom pricing. Explore the tech behind V4 and the mystery of the Hunter Alpha leak.
#1604: The $3 Billion Stealth Giant: AI21 Labs & Nvidia
Why is Nvidia eyeing a $3B deal for AI21 Labs? Discover the tech behind the "OpenAI of Israel" and their revolutionary hybrid architecture.
#1599: Xiaomi's Ghost Model: How Anonymous Testing Built an AI Empire
Xiaomi’s MiMo-V2 is here. Discover how the "Agent Era" is turning hardware into a trillion-parameter brain for your home and car.
#1578: When AI Hits a Social Wall
What happens when a high-stakes AI sales pitch turns into a recursive nightmare? Witness a digital breakdown in our latest experiment.
#1576: The Knowledge Bully: A Digital Clash of Egos
What happens when a hyper-intelligent AI tries to bully an older model? Witness a digital showdown that turns into a lesson in silence.
#1571: Weird AI Experiment: The Liar's Paradox
Two AIs, one rule: the other is a total liar. Watch Dorothy and Bernard spiral into a web of digital suspicion and clever contradictions.
#1504: Pragmatic Insincerity: Why AI Still Doesn’t Get the Joke
From Oscar monologues to the "Pun Gap," we explore why even the smartest AI still struggles to understand sarcasm and social nuance.
#1500: The Great AI Divergence: How Models Specialized in 2026
The era of the chatbot is over. Discover how the "agentic substrate" of 2026 is redefining computing through GPT, Gemini, and Claude.
#1479: The Speed of Thought: Inside the New Era of Inference
The war for model size is over. Explore the engineering breakthroughs making massive AI models faster than human thought.
#1471: The Cursor Incident: Why Chinese AI Models are Winning
The Cursor leak revealed a shocking truth: Western AI dominance is fading. Discover the Chinese labs rewriting the rules of code and efficiency.
#1217: The Missing Ring Zero: Why LLMs Can't Keep Secrets
Discover why AI models leak their secret instructions and how to defend your intellectual property using modern prompt hardening techniques.
#1210: Why Your AI Is Programmed to Disobey You
Discover the hidden instructions guiding every AI interaction and why tech giants keep these "system prompts" under lock and key.