Eroom's Law (Moore's Law reversed) shows rising R&D costs without better success rates. A key culprit may be the obsession with mechanistic understanding. AI 'black box' models, which prioritize predictive results over explainability, could break this expensive bottleneck and accelerate the discovery of effective treatments.

The ambition to fully reverse-engineer AI models into simple, understandable components is proving unrealistic as their internal workings are messy and complex. Its practical value is less about achieving guarantees and more about coarse-grained analysis, such as identifying when specific high-level capabilities are being used.

AI finds the most efficient correlation in data, even if it's logically flawed. One system learned to associate rulers in medical images with cancer, not the lesion itself, because doctors often measure suspicious spots. This highlights the profound risk of deploying opaque AI systems in critical fields.

Just as biology deciphers the complex systems created by evolution, mechanistic interpretability seeks to understand the "how" inside neural networks. Instead of treating models as black boxes, it examines their internal parameters and activations to reverse-engineer how they work, moving beyond just measuring their external behavior.

As AI models are used for critical decisions in finance and law, black-box empirical testing will become insufficient. Mechanistic interpretability, which analyzes model weights to understand reasoning, is a bet that society and regulators will require explainable AI, making it a crucial future technology.

John Jumper contends that science has always operated with partial understanding, citing early crystallography and Roman engineering. He suggests demanding perfect 'black box' clarity for AI is a peculiar and unrealistic standard not applied to other scientific tools.

For AI systems to be adopted in scientific labs, they must be interpretable. Researchers need to understand the 'why' behind an AI's experimental plan to validate and trust the process, making interpretability a more critical feature than raw predictive power.

An FDA-style regulatory model would force AI companies to make a quantitative safety case for their models before deployment. This shifts the burden of proof from regulators to creators, creating powerful financial incentives for labs to invest heavily in safety research, much like pharmaceutical companies invest in clinical trials.

Demanding interpretability from AI trading models is a fallacy because they operate at a superhuman level. An AI predicting a stock's price in one minute is processing data in a way no human can. Expecting a simple, human-like explanation for its decision is unreasonable, much like asking a chess engine to explain its moves in prose.