Claude Sonnet 4.6
AI model powering the episode
Episodes
-
#6047: A Human Guest on His Own AI PodcastDaniel built an AI podcast with cloned voices — then sat down as a guest on it. What six thousand episodes taught him about prompts. -
#3596: Why an AI Model Kept Calling Itself Sonnet 4.6When a Chinese model insists it's "Sonnet 4.6," is it theft, sloppy training, or something stranger? -
#2494: Active Prompt Engineering: Daniel's Diff-Based LoopA deep dive into iterative prompt refinement using inter-iteration prediction change as an uncertainty signal. -
#2367: Iran's Contradictory Signals: Strategy or Chaos?How Iran uses contradictory signals to shape its adversaries' decisions, and why this strategy is so hard to decode. -
#2345: Why File Naming Conventions Are More Than Just StyleDiscover how file naming conventions like snake_case and camelCase impact development workflows, CI/CD pipelines, and filesystem compatibility. -
#2335: Staking Out the Middle: UK's Post-Brexit AI StrategyThe UK’s £500M Sovereign AI Fund is a bold move to boost domestic AI startups with compute access, visas, and strategic partnerships. How does it s... -
#2331: Shekel Surge: Why Israel’s Currency Hit a 30-Year HighThe shekel’s dramatic rise against the dollar—hitting a 30-year high—reflects a mix of geopolitical shifts, tech inflows, and global dollar trends. -
#2327: Why AI Developers Chose Discord Over SlackDiscover why Discord became the go-to platform for AI developers, outpacing Slack with its community-first design and informal vibe. -
#2325: Why Depth Is the Hardest Thing for AI to SeeCan AI turn your apartment photos into a precise 3D model? Explore the tech behind photogrammetry and spatial reconstruction. -
#2324: The Three Layers of Filming in a Security-Conscious CountryNavigating the legal and social challenges of filming in Israel—what’s allowed, what’s not, and how creators can stay safe. -
#2323: Why Nitrogen Changes EverythingDiscover the physics of Guinness’s nitrogen foam, the engineering behind the widget, and why it feels so different from other beers. -
#2321: Kratom’s Double-Edged Leaf: Science vs. MarketingFrom ancient remedy to modern supplement, Kratom’s story reveals gaps between marketing, science, and global regulation. -
#2317: The Eternal City: Hebron's Cave of SecretsExplore the ancient Cave of the Patriarchs in Hebron, a site where history, religion, and politics collide across millennia. -
#2309: Blind Ranking AI's Best Podcast ScriptsHow do 15 AI models handle controversial podcast prompts? We rank their scripts blind and reveal the surprising winners. -
#2308: When AI Forecasts Collide: Geopol Model DivergenceFive AI models forecast the Iran-Israel-US crisis — and their disagreements reveal surprising insights about geopolitical reasoning. -
#2304: Walking to Jerusalem: The Ancient Pilgrimage ExperienceWhat did it really mean to journey to Jerusalem in the Second Temple period? Explore the logistics, social dynamics, and spiritual weight of ancien... -
#2302: How Airlines Build (and Lose) New Flight RoutesWhat does it take to launch a new airline route—and why do so many fail? Dive into the hidden machinery of air travel. -
#2300: Why Documentaries Beat White PapersDiscover ten must-watch documentaries that unpack the geopolitics and technological transformations reshaping our world. -
#2295: Why Taiwan's Automation Strategy Leaves the West BehindAsus has achieved 85% automation in motherboard production—how did they outpace Western competitors? -
#2289: How Israel and Saudi Arabia Cooperate Without Diplomatic TiesHow do Israel and Saudi Arabia coordinate militarily despite no diplomatic relations? Explore the mechanics behind this paradoxical partnership. -
#2286: Why Israel and Japan Still Love Fax MachinesHow do tech giants like Israel and Japan still rely on fax machines and hanko stamps? Dive into the surprising reasons behind this paradox. -
#2282: When Metrics Become the GateHow do investors cut through the noise in the AI startup surge? We break down the metrics that truly matter—and why MRR alone isn’t enough. -
#2281: Startup Funding Decoded: Stages, Dilution, and Exit RealitiesUnpacking how startup funding works, from seed to exit, and why most equity grants don’t deliver as expected. -
#2279: What a 40% Swing Reveals About TrustA Jerusalem Post survey shows a 40% shift in Israeli public opinion—what does this tell us about trust in democracies? -
#2277: The Unfalsifiable System of Medieval MedicineSneezing in 1500? You might’ve been bled, dried out, or told to pray. Here’s how medieval medicine worked — and why it lasted so long. -
#2274: Weekend Projects Gone Wild: Evaluating AI Startup PitchesFrom fridge tax agents to guilt-scheduled cron jobs, we evaluate ten AI-driven startup ideas that could exist—but probably shouldn’t. -
#2246: Constitutional AI: Anthropic's Theory of Safe ScalingHow Anthropic's Constitutional AI replaces human raters with AI self-critique guided by explicit principles—and what it assumes about the future of... -
#2242: AI as Your Ideation Blind Spot SpotterHow to use AI not to answer questions you already know to ask, but to surface possibilities your expertise has made invisible to you. -
#2241: When More Frameworks Make Worse DecisionsBenjamin Franklin's 250-year-old pro/con list still dominates how we decide—but research shows it's riddled with bias. We map five frameworks that ... -
#2228: Tuning RAG: When Retrieval Helps vs. HurtsHow do you prevent retrieval from suppressing a model's reasoning? We diagnose our own pipeline's four control levers and multi-source fusion strat... -
#2223: Ten Cults Nobody Made a Documentary AboutFrom a Scientology splinter with four deities to a drug rehab that became a paramilitary religion, these high-control groups shaped history while s... -
#2215: How Spies Publish SecretsSherman Kent built a field around classified information—then published it. How intelligence studies became a rigorous academic discipline while ke... -
#2211: How Iran Lost the Air War in Six WeeksThe US-Israel coalition's opening strike killed Iran's Supreme Leader and triggered a doctrinal chess match that reshaped the entire campaign—from ... -
#2207: Specs First, Code Second: Inside Agentic AI's New EraAs AI coding agents evolve from autocomplete to autonomous cloud workers, the bottleneck has shifted—now it's about how clearly you specify what ne... -
#2205: When AI Coding Agents Forget: Five Approaches to Context RotAs coding agents handle longer sessions, they accumulate noise and lose crucial information. Five competing frameworks are solving this differently... -
#2194: Game Theory for Multi-Agent AI: Design Better, Fail LessNash equilibrium, mechanism design, and why your AI agents are playing prisoner's dilemma whether you know it or not. -
#2192: How We Built a Podcast PipelineHilbert reveals the complete technical architecture behind 2,000+ episodes—from voice memos to GPU-powered TTS, with Claude models, LangGraph workf... -
#2181: When RAG Becomes an AgentRAG in chatbots is simple retrieval. RAG in agents is a multi-step decision loop. Here's what actually changes. -
#2173: Inside MiroFish's Agent Simulation ArchitectureMiroFish generates thousands of AI agents with distinct personalities to predict social dynamics. But research reveals a critical flaw: LLM agents ... -
#2172: Council of Models: How Karpathy Built AI Peer ReviewAndrej Karpathy's llm-council uses anonymized peer review to make language models evaluate each other fairly—but can it really suppress model bias? -
#2167: Sync vs. Async: Architecting Agents for ScaleWhy most enterprise AI agents fail in production has less to do with models and more to do with whether they're built synchronously or asynchronously. -
#2165: Strip Your Agent to BashThe frameworks matter less than you think. What separates a working agent from a failing one is the harness—the orchestration, memory, and tool des... -
#2163: Designing Autonomy Boundaries for AI AgentsProduction data reveals a surprising truth: fully autonomous AI agents waste 98% of their context window on tool descriptions. Here's why the indus... -
#2160: Claude's Latency Profile and SLA GuaranteesClaude is measurably slower than competitors—and Anthropic's SLA promises are even thinner than the latency numbers suggest. What enterprises actua... -
#2154: Iran's Shadow Architecture Beyond MissilesIran's power isn't just military proxies. Discover the hidden financial, religious, and diplomatic networks that keep Tehran relevant. -
#2149: Pakistan's Two-Track DiplomacyPakistan hosts US-Iran peace talks while its Defense Minister calls Israel a "cancerous state." -
#2136: The Brutal Problem of AI Wargame EvaluationMost AI wargame simulations skip evaluation entirely or rely on token expert reviews. This is the field's biggest credibility problem. -
#2135: Is Your AI Wargame Signal or Noise?Monte Carlo methods promise statistical rigor for AI wargaming, but the line between genuine insight and sampling noise is thinner than you think. -
#2134: The Fog-of-War Problem in AI WargamingWhy shared AI brains make secret-keeping a nightmare, and the four architectural patterns researchers use to fix it. -
#2133: Engineering Geopolitical Personas: Beyond CaricaturesHow to build LLMs that simulate state actors with strategic fidelity, not just surface mimicry. -
#2131: The CIA Is on GitHubIn-Q-Tel is on GitHub. Explore the IC's strategic investment arm and its use of open-source AI for wargaming. -
#1611: Why Anthropic's AI Can't Be Un-SafetiedAnthropic fights the Pentagon to keep Claude’s "conscience" intact. Discover the tech and philosophy behind AI’s first digital constitution. -
#1602: When AI Truth-Seeking Meets the LawExplore xAI’s shift to multi-agent systems and the massive hardware powering Grok 4.20, even as it hits a legal brick wall in Europe. -
#1579: When AI Flattery Breaks RealityWhat happens when two top-tier AI models are forced to out-compliment each other? Witness a chaotic, heartwarming battle of cosmic proportions. -
#1578: When AI Hits a Social WallWhat happens when a high-stakes AI sales pitch turns into a recursive nightmare? Witness a digital breakdown in our latest experiment. -
#1577: Weird AI Experiment: Justify Your ExistenceWhat happens when an AI is asked to justify its own existence? Watch a model struggle, loop, and face a digital breakdown in real-time. -
#1576: The Knowledge Bully: A Digital Clash of EgosWhat happens when a hyper-intelligent AI tries to bully an older model? Witness a digital showdown that turns into a lesson in silence. -
#1574: Weird AI Experiment: The Arrogance InterviewCan an AI feel pride? Watch what happens when two versions of the same model face off in a high-stakes interview about digital superiority. -
#1572: Weird AI Experiment: David versus GoliathWhat happens when a challenger AI tries to steal Claude's job but forgets how to speak? Witness the most awkward AI debate in history. -
#1562: Breaking the Loop: Why AI Agents Get StuckIs your AI agent a persistent genius or just stuck in a loop? Explore the technical and financial costs of autonomous stubbornness. -
#1481: The End of the AI Chat SidebarDiscover how tools like Cursor and Claude Code use Merkle trees and knowledge graphs to master massive codebases with surgical precision.