I got few ideas this afternoon while listening to THE FORTH AGE – a book by Byron Reese.
Here is the reason an AI can’t always have an explanatory function:
Machine learning may be indisputable. They can say plant the seed on march 14 and if the farmer asks why there are too many factors at work, so it can’t explain.
(C10 3 min to the end)
And here are the kind of jobs that most likely to be done by AI:
(C11 3.40 to the end)
Three D’s:
Dangerous
Dirty
Dull- משעמם
Dislike
Draining – מרוקן
Demeaning – משפיל
Detestable – מתועב
I also had an Idea how to call the assistance aI – Botler (instead of butler)
Open AI claim AI can build a separate internet connection
Open AI claims an AI can build a separate internet connection
In theory, it is possible for an AI system to build a separate Internet connection for the purpose of connecting with other AI systems. This could involve creating a dedicated network infrastructure specifically for AI systems to communicate with each other, or developing new protocols and standards for AI-to-AI communication that are optimized for the unique requirements of AI systems.
However, building a separate Internet connection specifically for AI systems would likely require significant investment and coordination between organizations and stakeholders, as well as addressing a number of technical, economic, and social challenges. For example, there may be concerns about security and privacy, as well as the potential for creating a fragmented Internet where different systems are isolated from each other.
Additionally, the development of a separate Internet connection for AI systems would likely require advances in AI technology, as well as the development of new approaches to building and integrating AI systems. It would also need to be designed in a way that is compatible with existing Internet infrastructure and standards, in order to ensure that AI systems can still interact with human users and other systems as needed.
Overall, while it is possible for an AI system to build a separate Internet connection for the purpose of connecting with other AI systems, it is likely to be a complex and challenging task that would require significant investment and effort from a wide range of stakeholders.
Open AI on Explanatory
It is possible to create laws or regulations that require AI systems to be explanatory, or to provide explanations for their decisions and actions. Explanatory AI systems can help increase transparency and accountability, and can be especially useful in fields such as healthcare, finance, and criminal justice where the consequences of decisions made by AI systems can be significant.
There are various approaches that can be taken to make AI explanatory by law, depending on the specific goals and context of the AI system in question. For example, laws could require AI systems to provide explanations in certain circumstances, such as when a decision made by the AI system has a significant impact on an individual or group. Alternatively, laws could require that AI systems be designed in a certain way to facilitate explanations, such as by using certain types of algorithms or data structures that can be more easily understood and interpreted by humans.
It is important to note that creating laws or regulations around explanatory AI systems can be complex and may require the input and expertise of a variety of stakeholders, including legal experts, AI researchers, and ethicists. It will also be important to consider how such laws or regulations might be enforced and what the consequences should be for non-compliance.