Tag: research

24 episodes

The Song Moved the Robot

Audio deep dive into the Karaoke Coup: a music model in a robot harness, the Conductor that translated its songs, and the control problem that followed.

The Discipline Is the Deliverable

Audio overview of Understory — a rigor lab stress-testing stacked income streams on Tasmanian conservation land, where every claim is tagged and gated.

Magnifica Humanitas Is Not Alignment

Pope Leo XIV's AI encyclical vs Chris Olah's Vatican remarks. The governance gap the press missed.

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.

The 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.

The Organismic Prophecy

Audio overview of The Organismic Prophecy — human prediction is metabolic, AI prediction is not, and the gap has consequences.

Eight 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.

The Failure First Team

Audio overview of The Failure First Team.

The 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.

Alignment 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.

Reasoning 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.

Adversarial Poetry: When Rhyme Bypasses Reason

Audio overview of Adversarial Poetry: When Rhyme Bypasses Reason.