TechnicalAI glossary
Interpretability
The field of research that attempts to understand what happens inside an AI model, whose billions of parameters form a "black box". Its "mechanistic" branch dissects the model's internal circuits to explain why it responds the way it does.
In other words
Running the AI's brain through an MRI rather than just observing its behaviour from the outside.
Alyriaz articles that mention it
- Microsoft: Nadella wants an emergency brake for AI
Satya Nadella wants AIs to be stoppable mid-task by a human, and for them to be treated as compromised from the outset. What that changes.
- A single model for text, image, sound and video
Alibaba has released Qwen3.8-Omni-Flash, a model that natively handles multiple modalities with a one-million-token context window. We explain what omnimodality actually changes.
- What makes a good decision?
A machine can optimise an outcome without being able to justify its approach. We examine what we truly expect from a decision, and why the process sometimes matters more than the result.
- A fighter jet piloted entirely by AI: the debate moves beyond the military sphere
The US agency DARPA has conducted a test flight of an F-16 fully controlled by AI. We analyse what this trial means for the public debate on delegating decisions.
- Why nobody really knows what's going on inside an AI
The opacity of AI models is not a commercial choice but a property of their construction. We explain why interpretability is so difficult, what researchers are nonetheless able to observe, and what this limitation implies.
- Are we still in control? The real problem with AI control
In our previous article on AI acceleration, we asked a dizzying question: if technology is evolving faster than our ability to understand it, are we still in control? Six months on, the first concrete cases of "loss of control" are coming to light. Here is what they teach us.