Yuri Vishnevsky
This note is one of a collection of messy drafts & inklings of new ideas.

October 2025
LLMs for Nominative Determinism

I was curious if language models could identify connections between people’s names and the directions they take with their work. Gathering a list of names & descriptions of scientists, I asked Google’s Gemini to score each area of study how strongly nominatively determined it was.

This came up with some obvious hits such as Jules Angst (mood researcher), Storm Field (meteorologist), and Russell Brain, 1st Baron Brain (neurologist), but also claimed some questionable connections that were amusing and puzzling, such as insisting that Paul Mockapetris’s name was directly connected to his invention of DNS, with a shifting justification each time I asked:

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 had been querying Google’s smallest model, Gemini Flash Lite. Oops.

A few more amusing cases:

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 Mandelbrot was put on the list with 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, since he gave himself a recursive middle initial following his discovery of fractals.

From his obituary:

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.

Back to top