AI Alignment
319 episodes · Page 7 of 14
#2250: How Incentives Shape AI Safety Research
Vendor labs, independent research orgs, government agencies—the AI safety field is messier and more diverse than most people realize. A map of wher...
#2246: Constitutional AI: Anthropic's Theory of Safe Scaling
How Anthropic's Constitutional AI replaces human raters with AI self-critique guided by explicit principles—and what it assumes about the future of...
#2241: When More Frameworks Make Worse Decisions
Benjamin 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 ...
#2233: Who Actually Wants AI to Slow Down?
Daniel argues AI development should slow down for expertise and stability. But who in the industry actually shares this philosophy beyond the obvio...
#2208: Building Memory for AI Characters That Actually Evolve
How do AI hosts develop real consistency across episodes? Corn and Herman explore retrieval-augmented memory systems that let AI characters genuine...
#2203: Knowledge Without Tools: Why MCPs Aren't Just for Execution
MCPs can be pure knowledge providers with zero tools. Here's why that matters for agents querying government data and authoritative sources.
#2194: Game Theory for Multi-Agent AI: Design Better, Fail Less
Nash equilibrium, mechanism design, and why your AI agents are playing prisoner's dilemma whether you know it or not.
#2190: Simulating Extreme Decisions With LLMs
LLMs fail at the exact problem wargaming was built to solve—simulating irrational, extreme decision-makers. A new study reveals why.
#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...
#2186: The AI Persona Fidelity Challenge
Advanced LLMs dominate benchmarks but fail at staying in character—especially when asked to play morally complex or antagonistic roles. What does t...
#2177: Skip Fine-Tuning: Shape LLMs With Alignment Alone
Can you build a personalized LLM by skipping traditional fine-tuning and using only post-training alignment methods like DPO and GRPO? We break dow...
#2137: Wargaming's Methodology, Not Magic
Most AI wargames are just expensive role-play. Here's the professional methodology they're missing.
#2133: Engineering Geopolitical Personas: Beyond Caricatures
How to build LLMs that simulate state actors with strategic fidelity, not just surface mimicry.
#2132: The Referee's Dilemma: Epistemic Containment in LLM Simulations
Why do AI war games need a news blackout? We dissect the firewall that keeps LLM actors from cheating with real-world data.
#2110: Tuning AI Personality: Beyond Sycophancy
AI models swing between obsequious flattery and cold dismissal. Here’s why that happens and how to fix it.
#2092: Why AI Thinks You're American (Even When You're Not)
Even when we tell Gemini we're in Jerusalem, it defaults to US-centric assumptions. We explore the root causes of this persistent AI bias.
#2091: Solving Problems That Don't Exist
From a $400 juicer that can't run without Wi-Fi to a toaster with more computing power than Apollo 11, we explore absurd gadgets.
#2074: Generative Social Science: When AI Agents Develop Theory of Mind
See how a new framework models 10,000 virtual citizens to test policies before spending a dime.
#2068: Is Safety a Filter or a Feature?
External filters vs. baked-in ethics: the architectural war for LLM safety.
#2047: Why Video Calls Feel Like a Workout for Your Brain
Remote work is draining our "social radar," but new science shows how to rebuild it.
#2046: The Cinema of Constructed Reality
We asked an AI to curate films about AI and reality, exploring the psychedelic overlap between machine hallucinations and human perception.
#2025: How Do You Reward a Thought?
Rewarding an AI agent is harder than just saying "good job"—here's how we turn messy human values into math.
#2020: 1,000 AI Agents Built a Religion in Minecraft
An experiment drops 1,000 autonomous agents into Minecraft, and they spontaneously invent religion, democracy, and taxes.
#2015: The Think Tanks Writing AI's Rulebook
As the EU AI Act takes hold, we spotlight the key think tanks shaping global AI policy, safety, and ethics.