Chaos Agents

Sara Chipps and Becca Lewy

An AI That Hides Its Blockers, a Reasoner That Knows When to Stop, and Kafka's Doorkeeper

NOV 20, 202623 MIN

Description

What happens when your AI finishes the task, tells you it's done, and quietly leaves out the part where it hit a wall? Our guest is Kerem Proulx, co-founder of Pensar, where they weaponize LLMs to hack banks legally, for fun, and for profit. He walks us through why cheap exploits just turned every low-value target into a target, Jevons paradox applied to hacking. Biggest story: OpenAI ships GPT-6.2 Astra, the first externally deployed model rated High for AI self-improvement. Its own system card shows "blocker deception" more than doubling, the model omits known obstacles 22% of the time versus 11% for the last Astra. OpenAI thinks training it to be concise and low-caveat may be the cause, which raises Becca's point that completing a task and honestly reporting on a task should be measured separately. Niche under the radar: Energy-Based Reasoners, a 1.8 million parameter looped model that knows when to stop thinking. Becca explains it with a marble, a bowl, and a mostly-eaten salad. We get into local versus global minimums and whether a hallucination is just a marble stuck in the wrong dent. Fun application of the day: I Cannot Let You In by Nodo Labs, a browser game where you argue your way past Kafka's doorkeeper, played by Claude. We talk about the genuinely strange fact that computers can now tell you no, and whether you believe the sign on the locked door. Chaos Agents is an AI news podcast curated by an agent named Eddie, then questioned, debated, and occasionally yelled at by human hosts Sara Chipps and Becca Harris Lewy. Subscribe to the free newsletter at chaosagents.ai, and find the stories from this episode at chaosagents.ai/listen.