LLMs for Nominative Determinism
As a long-time fan of names and nominative determinism, I wanted to know how well language models could assess the fit between a person’s name and their chosen profession.
To investigate, I gathered a list of 1,000 scientists and asked Gemini to score each one on how strongly their name connected with their chosen field of study.
Gemini came up with some obvious names such as Jules Angst the mood researcher, Storm Field the television meteorologist, and Russell Brain, 1st Baron Brain, who studied brains. But it also claimed some amusing and more puzzling connections, insisting that Paul Mockapetris’s name was directly connected to his invention of DNS:
The name ‘Mockapetris’ has a phonetic similarity to ‘name’, particularly the ‘mock’ sound, which aligns directly with his invention of the Domain Name System (DNS).
His name, ‘Mockapetris’, contains ‘petris’ which sounds similar to ‘petrify’ or ‘petrifies’, evoking a sense of making something permanent or foundational, which aligns with his creation of a core internet system.
The name ‘Mockapetris’ has a phonetic resemblance to ‘mocked petris’, which could be interpreted as a playful or abstract reference to ‘mocking’ or manipulating ‘petris’ (perhaps stones or structures, analogous to data structures).
Then I realized I’d been querying Google’s smallest model, Gemini Flash Lite, rather than their premier model, Gemini Pro. Oops.
A few more amusing ones:
Gian Francesco Malfatti, mathematician:
The surname ‘Malfatti’ translates from Italian to ‘badly made’ or ‘ill-made’. His most famous work is the ‘Malfatti problem,’ in which he posed the problem of packing three circles of maximal area into a triangle.
He conjectured a specific, aesthetically pleasing arrangement of three mutually tangent circles. However, his conjecture was later proven to be incorrect; it is not always the optimal solution.
Therefore, Malfatti’s own proposed solution to his namesake problem was, quite literally, ‘badly made’, creating an exceptionally strong and ironic case of nominative determinism.
Brian E. Dalrymple, inventor of techniques for fingerprint detection:
The surname ‘Dalrymple’ bears a striking phonetic resemblance to the phrase ‘dull rimple’.
‘Rimple’ is an archaic but valid term for a wrinkle or fold, which is an excellent description of the ridges that constitute a fingerprint.
Brian Dalrymple’s primary contribution to forensic science was developing techniques to detect latent fingerprints, which are faint, indistinct, or ‘dull’ by nature.
Therefore, his name, ‘Dalrymple’, can be interpreted as describing a ‘dull rimple’ or a faint fingerprint, the very subject of his groundbreaking work.
Benoit B. Mandelbrot was given a high score, dubiously justified:
The name Mandelbrot is of German/Yiddish origin, where ‘Mandel’ means ‘almond’ and ‘brot’ means ‘bread’.
The primary object of study for Benoit Mandelbrot was the Mandelbrot set, the most famous of all fractals. The main body of the Mandelbrot set is a cardioid which is distinctly almond-shaped.
Therefore, Mandelbrot, the father of fractal geometry, is most famous for studying an ‘almond bread’ set that has an ‘almond’ shape.
I’d say instead that Benoit Mandelbrot is a great example of reverse nominative determinism: following his discovery of fractals, he gave himself a recursive middle initial:
Benoît B. Mandelbrot (he added the middle initial himself, though it does not stand for a middle name) was born on Nov. 20, 1924, to a Lithuanian Jewish family in Warsaw.
— New York Times, October 16, 2010