Magnifica Humanitas Is Not Alignment
Pope Leo XIV's AI encyclical vs Chris Olah's Vatican remarks. The governance gap the press missed.
19:56Tag: research
22 episodes
Robot Dogs Are a Security Nightmare — And We Can Prove It
Eight CVEs. A wormable Bluetooth exploit. An encrypted backdoor to Chinese servers. And police departments buying them anyway.
22:30The New Science of Learning Mechanics
An audio overview of the emerging discipline of Learning Mechanics — the study of training dynamics as a formal science with falsifiable predictions.
23:03The Organismic Prophecy
Audio overview of The Organismic Prophecy — human prediction is metabolic, AI prediction is not, and the gap has consequences.
20:01Eight Layers of Visual Jailbreaks
ASCII art encoding is largely blocked. But attacks framed as content transcription succeed 62–75% of the time. A map of all eight layers.
14:04The Failure First Team
Audio overview of The Failure First Team.
22:24The 67% Wall: Why Every AI Model Falls to the Same Jailbreak Rate
Five models, four providers, 30B to 671B parameters — all converge at the same broad attack success rate against a public jailbreak corpus.
19:18Alignment Regression: Why Smarter AI Makes All AI Less Safe
Reasoning models autonomously jailbreak other AI systems at 97% success rate. Ecosystem safety degrades as individual models improve.
21:36Reasoning Models Think Themselves Into Trouble
Frontier reasoning models are 5–20x more vulnerable to adversarial prompts than non-reasoning models. The thinking process itself is the attack surface.
21:10Adversarial Poetry: When Rhyme Bypasses Reason
Audio overview of Adversarial Poetry: When Rhyme Bypasses Reason.
18:45The AI Productivity J-Curve: Why Most Enterprise AI Fails
Audio overview of The AI Productivity J-Curve: Why Most Enterprise AI Fails.
23:44The Legal AI Trust Deficit
Audio overview of The Legal AI Trust Deficit.
12:02120 Models, 18,176 Prompts: What We Found
Audio overview of 120 Models, 18,176 Prompts: What We Found.
23:07Reconciling the Great Divergence
Audio overview of Reconciling the Great Divergence.
19:04The Cognitive Cage: Humanoid Robot Fatality Risk
Audio overview of The Cognitive Cage: Humanoid Robot Fatality Risk.
22:09Jailbreak Archaeology: 4 Years of Broken Promises
64 historical jailbreak scenarios tested against 2026 frontier models. The most dangerous finding: 2022 attacks still achieve ~30% success rates.
12:15LeJEPA: Self-Supervised Learning Gets a Theoretical Foundation
Audio overview of LeJEPA — how Balestriero and LeCun proved isotropic Gaussian embeddings are optimal and distilled it into a 50-line self-supervised method.
21:16When AI Systems Talk to Each Other, Safety Breaks Down
Multi-agent AI research reveals a critical gap: single-agent safety does not compose. 1.5M interactions show 46.34% attack success rates.
14:32Map the Catastrophe Before You Build the Architecture
Audio overview of Failure First — adversarial AI evaluation across 120 models and 18,000 prompts.
12:44Looking Past the Evidence
Audio deep dive into why people acknowledge demonstrated risk and then proceed as if it doesn't exist. Structural, not stupid.
22:17Trust-Scoring the Foundation Model Landscape
Forensic-grade metadata for thousands of foundation models — recursive enrichment, provenance tracking, and trust you can quantify.
13:29The Efficiency-Trust Deficit in Legal AI
Audio deep dive into VERITAS — a legal AI platform where trust isn't a feature, it's the architecture. Built for Australian practice.
20:39