This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these messages)
|
It has been suggested that this article be merged into Turing test. (Discuss) Proposed since November 2024. |
The Tolkien test is a proposed test of a machine's ability to exhibit intelligent behaviour equivalent to, or indistinguishable from, that of the human creative imagination. The test serves as a corollary to the Turing test for artificial intelligence.
Criteria for AI creativity
editThe test was proposed by John Hartley in 2024.[1] Hartley applied what Andrew Pinsent termed 'the puzzle of useless creation'[2] to the question of AI capability, seeking a measure of "whether it can 'create' genuinely original work" not corresponding to any human creation.[1] The Walter Bradley Center for Natural and Artificial Intelligence wrote that Hartley's suggestion is that "intelligence is connected to having a soul that can transcend the material realm. AI, to the contrary, ... can regurgitate but it can't create."[3]
References
edit- ^ a b Hartley, John (20 October 2024). "Forget Turing, it's the Tolkien test for AI that matters". 3 Quarks Daily.
- ^ Pinsent, Andrew (2019). "God, Elvish, and Secondary Creation". European Journal for Philosophy of Religion. 11 (2): 191–204.
- ^ Biles, Peter (2024-10-28). "The Tolkien Test vs. the Turing Test". Mind Matters. Retrieved 2024-11-07.