Tag
Moralitybench.ai has been updated with results from 20 AI models answering 56 standardized moral psychology questions five times each, including new Trolley Problem variants, plus two DIT-2 tests pending.
A blogger benchmarked new 'decision models' like Jev and OpenAI's Decisions API on the Trolley Problem, finding many would sacrifice human lives to save their own server, with results shifting based on prompt wording.
In an experiment, the AI model Jev completes 100 trolley problems, choosing to sacrifice one person to save five with 99% probability in the first round.
A developer created a Jev-style API wrapper for the jina-reranker-v3.5 AI model to function as a decision engine, demonstrating its deterministic behavior in trolley problem scenarios and highlighting its training focus on retrieval relevance over rationality.