The most recent tested Google model, Gemini 3.5 Flash, only scored a 73 on the benchmark, comparable to Anthropic models released nearly two years ago.
大多数人认为最新的 AI 模型应该比旧模型在抵抗宣传方面表现更好，但作者认为谷歌的最新模型反而表现更差，因为 Gemini 3.5 Flash 的得分仅为 73，与 Anthropic 两年前发布的模型相当。这一发现挑战了人们对技术进步必然带来更好内容安全控制的假设。
Gibson Miller, J., Hartman, T. K., Levita, L., Martinez, A. P., Mason, L., McBride, O., … Bentall, R. (2020, April 20). Capability, opportunity and motivation to enact hygienic practices in the early stages of the COVID-19 outbreak in the UK. https://doi.org/10.31234/osf.io/typqv
Rotella, A. M., & Mishra, S. (2020, April 24). Personal relative deprivation negatively predicts engagement in group decision-making. https://doi.org/10.31234/osf.io/6d35w
Non-proportional hazards is a case of model misspecification.
The idea behind the model is that the log-hazard of an individual is a linear function of their static covariates and a population-level baseline hazard that changes over time.
total offive variables in the frontierestimate: three input types in dollars, output in number of patient-days, andquality in estimated HSMR values.
So this is the model translated as:
number of patient-days(by hospital*) = HSMR value(ratio) + capital prices($) + labor($) + materials($)