The release of the generative pre-trained transformer(GPT)series has brought artificial general intelligence(AGI)to the forefront of the artificial intelligence(AI)field once again.However,the questions of how to defi...The release of the generative pre-trained transformer(GPT)series has brought artificial general intelligence(AGI)to the forefront of the artificial intelligence(AI)field once again.However,the questions of how to define and evaluate AGI remain unclear.This perspective article proposes that the evaluation of AGI should be rooted in dynamic embodied physical and social interactions(DEPSI).More specifically,we propose five critical characteristics to be considered as AGI benchmarks and suggest the Tong test as an AGI evaluation system.The Tong test describes a value-and ability-oriented testing system that delineates five levels of AGI milestones through a virtual environment with DEPSI,allowing for infinite task generation.We contrast the Tong test with classical AI testing systems in terms of various aspects and propose a systematic evaluation system to promote standardized,quantitative,and objective benchmarks and evaluation of AGI.展开更多
The formation of spatial patterns is an important issue in reaction–diffusion systems.Previous studies have mainly focused on the spatial patterns in reaction–diffusion models equipped with symmetric diffusion(such ...The formation of spatial patterns is an important issue in reaction–diffusion systems.Previous studies have mainly focused on the spatial patterns in reaction–diffusion models equipped with symmetric diffusion(such as normal or fractional Laplace diffusion),namely,assuming that spatial environments of the systems are homogeneous.However,the complexity and heterogeneity of spatial environments of biochemical reactions in vivo can lead to asymmetric diffusion of reactants.Naturally,there arises an open question of how the asymmetric diffusion affects dynamical behaviors of biochemical reaction systems.To answer this,we build a general asymmetric L´evy diffusion model based on the theory of a continuous time random walk.In addition,we investigate the two-species Brusselator model with asymmetric L´evy diffusion,and obtain a general condition for the formation of Turing and wave patterns.More interestingly,we find that even though the Brusselator model with symmetric diffusion cannot produce steady spatial patterns for some parameters,the asymmetry of L´evy diffusion for this model can produce wave patterns.This is different from the previous result that wave instability requires at least a three-species model.In addition,the asymmetry of L´evy diffusion can significantly affect the amplitude and frequency of the spatial patterns.Our results enrich our knowledge of the mechanisms of pattern formation.展开更多
This paper describes a test with the AI program ChatGPT.In the test,essentially a simplified Turing test,the author texted increasingly more sophisticated questions to ChatGPT and evaluated whether the conversing AI’...This paper describes a test with the AI program ChatGPT.In the test,essentially a simplified Turing test,the author texted increasingly more sophisticated questions to ChatGPT and evaluated whether the conversing AI’s answers could or could not have come from another human.The questions were related to:(1)the author’s identity;(2)the task of separating correct and false information;(3)the accounts of Jesus’crucifixion;(4)the health-aspects of marijuana;(5)the last flight of John F.Kennedy Jr.;and(6)the identity of the conversing AI itself.It was found that ChatGPT passed the intelligence criteria of the simplified Turing test,as the author subjectively experienced his conversation with this AI as an interaction between two humans.On the other hand,ChatGPT didn’t pass the threshold of the intelligence definition of cosmological neuroscience,as the program lacked the analytic reasoning separating truth from falseness,clarity from ambiguity and the highly significant from the less significant,while it did not show the signs of originality and creative superimpositions either.It should still be acknowledged that ChatGPT represents the birth of an AI with the potential of elevating artificial conversations into the realm of human existence-whether or not it makes sense.The strange last line of the conversing AI,“I’m quite happy being an AI for now”,suggested that in future ChatGPT may change the scope of its functions-just as other AIs may do.Whether or not this will be beneficial for humankind,it will be decided by the extent to which these programs serve evil and divine causes.The paper argues that in order to let the divine side win over the evil one,the guidance of the father of AI,Alan Turing,would be prudent to consider.This guidance was given in his historic paper in October,1950,issue of the journal Mind,where Turing indicated that work like his on intelligent machines is compatible with God’s will,“providing mansions for the souls that He creates.”展开更多
In this paper, we study a modified Leslie-Gower predator-prey model with Smith growth subject to homogeneous Neumann boundary condition, in which the functional response is the Crowley-Martin functional response term....In this paper, we study a modified Leslie-Gower predator-prey model with Smith growth subject to homogeneous Neumann boundary condition, in which the functional response is the Crowley-Martin functional response term. Firstly, for ODE model, the local stability of equilibrium point is given. And by using bifurcation theory and selecting suitable bifurcation parameters, we find many kinds of bifurcation phenomena, including Transcritical bifurcation and Hopf bifurcation. For the reaction-diffusion model, we find that Turing instability occurs. Besides, it is proved that Hopf bifurcation exists in the model. Finally, numerical simulations are presented to verify and illustrate the theoretical results.展开更多
基金supported by the National Key Research and Development Program of China (2022ZD0114900).
文摘The release of the generative pre-trained transformer(GPT)series has brought artificial general intelligence(AGI)to the forefront of the artificial intelligence(AI)field once again.However,the questions of how to define and evaluate AGI remain unclear.This perspective article proposes that the evaluation of AGI should be rooted in dynamic embodied physical and social interactions(DEPSI).More specifically,we propose five critical characteristics to be considered as AGI benchmarks and suggest the Tong test as an AGI evaluation system.The Tong test describes a value-and ability-oriented testing system that delineates five levels of AGI milestones through a virtual environment with DEPSI,allowing for infinite task generation.We contrast the Tong test with classical AI testing systems in terms of various aspects and propose a systematic evaluation system to promote standardized,quantitative,and objective benchmarks and evaluation of AGI.
基金supported by the National Natural Science Foundation of China(Grant Nos.62066026,62363027,and 12071408)PhD program of Entrepreneurship and Innovation of Jiangsu Province,Jiangsu University’Blue Project’,the Natural Science Foundation of Jiangxi Province(Grant No.20224BAB202026)the Science and Technology Research Project of Jiangxi Provincial Department of Education(Grant No.GJJ2203316).
文摘The formation of spatial patterns is an important issue in reaction–diffusion systems.Previous studies have mainly focused on the spatial patterns in reaction–diffusion models equipped with symmetric diffusion(such as normal or fractional Laplace diffusion),namely,assuming that spatial environments of the systems are homogeneous.However,the complexity and heterogeneity of spatial environments of biochemical reactions in vivo can lead to asymmetric diffusion of reactants.Naturally,there arises an open question of how the asymmetric diffusion affects dynamical behaviors of biochemical reaction systems.To answer this,we build a general asymmetric L´evy diffusion model based on the theory of a continuous time random walk.In addition,we investigate the two-species Brusselator model with asymmetric L´evy diffusion,and obtain a general condition for the formation of Turing and wave patterns.More interestingly,we find that even though the Brusselator model with symmetric diffusion cannot produce steady spatial patterns for some parameters,the asymmetry of L´evy diffusion for this model can produce wave patterns.This is different from the previous result that wave instability requires at least a three-species model.In addition,the asymmetry of L´evy diffusion can significantly affect the amplitude and frequency of the spatial patterns.Our results enrich our knowledge of the mechanisms of pattern formation.
文摘This paper describes a test with the AI program ChatGPT.In the test,essentially a simplified Turing test,the author texted increasingly more sophisticated questions to ChatGPT and evaluated whether the conversing AI’s answers could or could not have come from another human.The questions were related to:(1)the author’s identity;(2)the task of separating correct and false information;(3)the accounts of Jesus’crucifixion;(4)the health-aspects of marijuana;(5)the last flight of John F.Kennedy Jr.;and(6)the identity of the conversing AI itself.It was found that ChatGPT passed the intelligence criteria of the simplified Turing test,as the author subjectively experienced his conversation with this AI as an interaction between two humans.On the other hand,ChatGPT didn’t pass the threshold of the intelligence definition of cosmological neuroscience,as the program lacked the analytic reasoning separating truth from falseness,clarity from ambiguity and the highly significant from the less significant,while it did not show the signs of originality and creative superimpositions either.It should still be acknowledged that ChatGPT represents the birth of an AI with the potential of elevating artificial conversations into the realm of human existence-whether or not it makes sense.The strange last line of the conversing AI,“I’m quite happy being an AI for now”,suggested that in future ChatGPT may change the scope of its functions-just as other AIs may do.Whether or not this will be beneficial for humankind,it will be decided by the extent to which these programs serve evil and divine causes.The paper argues that in order to let the divine side win over the evil one,the guidance of the father of AI,Alan Turing,would be prudent to consider.This guidance was given in his historic paper in October,1950,issue of the journal Mind,where Turing indicated that work like his on intelligent machines is compatible with God’s will,“providing mansions for the souls that He creates.”
文摘In this paper, we study a modified Leslie-Gower predator-prey model with Smith growth subject to homogeneous Neumann boundary condition, in which the functional response is the Crowley-Martin functional response term. Firstly, for ODE model, the local stability of equilibrium point is given. And by using bifurcation theory and selecting suitable bifurcation parameters, we find many kinds of bifurcation phenomena, including Transcritical bifurcation and Hopf bifurcation. For the reaction-diffusion model, we find that Turing instability occurs. Besides, it is proved that Hopf bifurcation exists in the model. Finally, numerical simulations are presented to verify and illustrate the theoretical results.
