Contrary to fears that reinforcement learning would push models' internal reasoning (chain-of-thought) into an unexplainable shorthand, OpenAI has not seen significant evidence of this "neural ease." Models still predominantly use plain English for their internal monologue, a pleasantly surprising empirical finding that preserves a crucial method for safety research and interpretability.

Goodfire frames interpretability as the core of the AI-human interface. One direction is intentional design, allowing human control. The other, especially with superhuman scientific models, is extracting novel knowledge (e.g., new Alzheimer's biomarkers) that the AI discovers.

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.

The field is moving beyond labeling concepts with sparse autoencoders. The new frontier is understanding the intricate geometric structures (manifolds) these concepts form in a model's latent space and how circuits transform them, providing a more unified, dynamic view.

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.

This advanced safety method moves beyond black-box filtering by analyzing a model's internal activations at runtime. It identifies which sub-components are associated with undesirable outputs, allowing for intervention or modification of the model's behavior *during* the generation process, rather than just after the fact.

Access to frontier models is not a prerequisite for impactful AI safety research, particularly in interpretability. Open-source models like Llama or Qwen are now powerful enough ("above the waterline") to enable world-class research, democratizing the field beyond just the major labs.

The public-facing models from major labs are likely efficient Mixture-of-Experts (MOE) versions distilled from much larger, private, and computationally expensive dense models. This means the model users interact with is a smaller, optimized copy, not the original frontier model.