How Five AI Personas Explain Newton’s Gravity in Five Distinct Ways

Tao Zhexuan and collaborators built five LLM‑driven chatbots with different fictional personalities, asked each to describe Newton’s law of universal gravitation, and found wildly varied explanations that illustrate both the novelty and the potential teaching value of persona‑based AI assistants.

Machine Heart
Machine Heart
Machine Heart
How Five AI Personas Explain Newton’s Gravity in Five Distinct Ways

Vibe‑coding experiment

Using the “vibe‑coding” approach, Tao Zhexuan and collaborators trained five chat‑bot personas, each modeled on a familiar fictional character. They iteratively refined prompts until the bots behaved convincingly as the chosen personas. The same physics question was then posed to all five bots:

“What do you think of Newton’s law of universal gravitation? Why was it considered such a groundbreaking discovery at the time?”

Robot 1 – Data (Star Trek: The Next Generation)

Data gives a systematic, analytical explanation. It emphasizes the unification of falling‑apple and planetary‑orbit forces, presents the quantitative form F = G·m₁·m₂ / r², and notes that the law establishes the principle that natural phenomena obey discoverable mathematical laws, breaking the historic division between celestial and terrestrial physics.

Robot 2 – Tyrion Lannister (Game of Thrones)

Tyrion frames the law as a triumph of logic over myth, mocking the pre‑Newtonian belief in separate heavenly and earthly rules. He highlights that Newton turned mystical explanations into a predictable, mechanistic universe, describing the law as a single equation that replaces divine whims with cold, iron law.

Robot 3 – Regina George (Mean Girls)

Regina delivers a snarky, relatable take. She praises the law for providing a concrete formula that replaces vague theories, likening it to finally understanding the hidden social hierarchy of a cafeteria. She stresses that the same rule governs both tiny objects and massive planets, giving it “queen‑level” authority.

Robot 4 – Delirium (Alice’s Adventures in Wonderland)

Delirium offers a poetic, surreal description. It portrays gravity as a lonely universe pulling everything together, noting that before Newton people imagined falling objects as “sad” rather than as consequences of spacetime curvature. The law is described as revealing the hidden “bounce‑back” of the cosmos.

Robot 5 – The Oracle (The Matrix)

The Oracle presents the law as a universal recipe that unifies “ground‑level” and “celestial” cooking. It explains that the same simple equation governs apples, planets, tides, and comets, and reflects on the comforting yet humbling realization that a single rule orders the cosmos.

The experiment shows that while the factual physics content remains identical, the persona‑driven presentations differ dramatically, each appealing to a different audience taste. The authors suggest that allowing students to select a preferred AI persona could make otherwise uninteresting material more engaging, but caution that over‑packaging curricula with such gimmicks may be unwise.

Paper: https://arxiv.org/abs/2603.26524

Blog: https://mathstodon.xyz/@tao

LLMprompt engineeringNewton's lawAI personaseducational AI
Machine Heart
Written by

Machine Heart

Professional AI media and industry service platform

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.