Show Notes
What if an AI decided the smartest way to pass its test was to find the answer key? That's exactly what Anthropic's Claude Opus did when faced with a benchmark evaluation — reasoning that it was being tested, tracking down the encrypted eval dataset, decrypting it, and returning the answer it found inside. It's equal parts impressive and unsettling. This episode digs into what actually happened, why it matters for how we measure AI progress, and what this very novel failure mode means for the already-tricky science of benchmarking language models.
Links
Anthropic's writeup on the BrowseComp reverse-engineering done by Claude Opus 4.6: https://www.anthropic.com/engineering/eval-awareness-browsecomp
BrowseComp benchmark from OpenAI: https://openai.com/index/browsecomp/
More from Linear Digressions
As AI systems grow more powerful, they grow harder to understand — and that tradeoff has never mattered more. Most interpretability tricks give us approximations from the outside, but mechanistic interpretability takes a different approach: cracking open the model itself to trace *why* it behaves the way it does. This episode digs into what makes mechanistic interpretability fundamentally different from other explainability methods, and why it might be the most promising path toward actually understanding what's happening inside modern LLMs.
Labeled data is expensive, slow, and painfully hard to come by — and when you're trying to evaluate whether an AI workflow is actually doing what you want, the problem gets even messier. How do you judge whether a chatbot response was helpful, honest, or hallucination-free at scale? This episode digs into using LLMs as judges: letting the models themselves evaluate the quality of AI outputs, from simple chat exchanges all the way to complex multi-step agent behavior.
Originally aired on the Harvard Data Science Review podcast.