Open AI, the company behind the popular AI chatbot Chat GPT, has now developed an evaluation scale to assess how closely AI models can approach human levels of intelligence, according to a Bloomberg report.
The scale has a total of five levels. The higher the level, the closer the AI model is judged to be to human intelligence. Today’s large-scale language models are currently judged to be at level one; that corresponds to basic intelligence, but not a more advanced problem-solving ability.
Level two means that the system has a basic problem-solving ability that should be comparable to a human with a PhD. Level three means the system can act as a representative for the user. Level four means that the system can create new innovations. Finally, level five involves the step to achieve artificial general intelligence (AGI), an AI system can perform the work of entire organizations.
Open AI has previously defined AGI as a highly automated system that can outperform humans on the majority of economically valuable tasks. Open AI’s evaluation scale is considered preliminary and could be adjusted in the future.
Open AI, the company behind the popular AI chatbot Chat GPT, has now developed an evaluation scale to assess how closely AI models can approach human levels of intelligence, according to a Bloomberg report.
The scale has a total of five levels. The higher the level, the closer the AI model is judged to be to human intelligence. Today’s large-scale language models are currently judged to be at level one; that corresponds to basic intelligence, but not a more advanced problem-solving ability.
Level two means that the system has a basic problem-solving ability that should be comparable to a human with a PhD. Level three means the system can act as a representative for the user. Level four means that the system can create new innovations. Finally, level five involves the step to achieve artificial general intelligence (AGI), an AI system can perform the work of entire organizations.
Open AI has previously defined AGI as a highly automated system that can outperform humans on the majority of economically valuable tasks. Open AI’s evaluation scale is considered preliminary and could be adjusted in the future. Read More
Related posts:
Estudio de plataformas para la creación de competiciones aplicado a la tarea de clasificación de imágenes
Anthropic Claude 3.5 Sonnet is here, and it’s free
Purdue, Elanco Animal Health announce One Health Innovation District in Indianapolis
A Machine-Learning-Based Cyberattack Detector for a Cloud-Based SDN Controller
Asana to bring genAI ‘teammates’ to its work management app
Home-Court Advantage is Greater for Teams Competing at Higher Playing Levels: An Exploratory Analysis of Spanish Male Basketball Leagues