CONCEPT
The Imitation Game (Collins)
Collins's domain-specific variant of Turing's original test — a methodology for evaluating expertise by asking whether a non-expert (or a machine) can be distinguished from a genuine expert by judges with contributory expertise in the specific field.
The Imitation Game is Collins's methodological instrument for operationalizing the distinction between interactional and contributory expertise. Where Turing's original test asked whether a machine could fool a general audience in open-ended conversation, Collins's version asks the more discriminating question: can the machine (or the aspirant to interactional expertise) fool specialists in the target domain? Collins used the methodology to validate his own interactional expertise in gravitational wave physics — a panel of judges could not reliably distinguish his answers from those of actual physicists — and proposed it as the proper test for evaluating AI competence in specific fields.
In The You On AI Field Guide
The methodological innovation is the shift from general to domain-specific evaluation. General Turing Tests systematically underestimate the mimeomorphic sophistication of modern language models — LLMs can fool most general audiences on most topics — while systematically overestimating their contributory competence. The specialist Imitation Game cuts the