Source Nature · Published · Open the original ↗
Capability
This AI ‘mechanic’ can peer inside the black box of other neural networks
Being able to target and debug systems could improve artificial-intelligence safety and utility.
Researchers have used an artificial-intelligence model to read and tinker with the internal workings of another AI network, offering a new way to peek into the ‘black box’ of AI .
Computer scientists usually improve models by training them in tiny increments or by building them from scratch. A team at the Massachusetts Institute of Technology (MIT) in Cambridge has demonstrated how an AI model called GPT-6 Astra can interpret the raw internal values of some other models well enough to predict what different parts of the systems do. It can then edit the models to make improvements, including boosting their mathematical abilities. The authors reported their findings in a preprint 1 on 2 November.
Frontier AI models are “showing early sparks” of an ability to treat neural networks like files that they can read, reason about and change, says co-author Rikiya Takehi, a machine-learning researcher at MIT.
The opening of the report, quoted unchanged from Nature. The full text continues at the source.