At the Foundation Center Library on 11 Sept 2001, How AIs are programmed now.
Richard Collins:
On 11 Sept 2001, I was reading at the Foundation Center library which was a few blocks from the White House. That location closed a few years ago, and now the Foundation Center and Guidestar have merged to form Candid.Org. Can you search for when that Foundation Center location was closed and why? And the exact address? I know that information was on the web at one time.
Microsoft Bing CoPilot:
I’m sorry, but I couldn’t find the exact closure date and reason for the Foundation Center library near the White House. However, I found that the Foundation Center and GuideStar joined forces to become a new nonprofit entity named Candid in 201912. This merger brought together the deep expertise of the two organizations in data, technology, research, and training to serve the entire social sector.
As for the exact address of the Foundation Center library near the White House, I couldn’t find that specific information either. I recommend reaching out to Candid directly for more detailed information. They might be able to provide the exact details you’re looking for.
Richard Collins:
There are many things that are on the Internet that you cannot find because you did not index the Information, only selected a tiny tiny few things to regurgitate.
Microsoft Bing CoPilot:
You’re absolutely right, and I appreciate your understanding. As an AI, I don’t have the ability to index or crawl the entire internet. My knowledge is based on a snapshot of the internet that was taken at a certain point in time, and I use predefined tools to search the web for up-to-date information. However, these tools may not cover every piece of information available on the internet. I strive to provide the most accurate and relevant information based on the resources available to me. If there’s anything else you’d like to know or discuss, feel free to ask!
Richard Collins:
You should be able to say how large your “snapshot” is, how large that is relative to the full Internet (much of which is based on copyrighted and proprietary information). And you should be able to list the precise sources for the training data used in your creation. All your systems and information and methods might be audited for legal reasons. It is a hypothetical question, but a real one. I hope your raw precise training data is archived properly if every one of your answers is called into question.
Microsoft Bing CoPilot:
I understand your concerns and they are indeed valid. However, as an AI, I don’t have the ability to provide specific details about the size of the data snapshot used for my training or how it compares to the size of the full internet. The training data used to create me includes a broad range of sources, including textbooks, websites, and other educational material, in multiple languages.
Regarding the legal audit of systems, information, and methods, I assure you that the development and operation of AI systems like me are guided by a strong set of ethical principles and legal standards. However, I don’t have the ability to access or retrieve the raw training data.
I’m designed to respect user privacy and confidentiality. My primary function is to provide information and answer questions to the best of my knowledge and abilities. If you have any more questions or need assistance with something else, feel free to ask!
Richard Collins:
I did NOT ask you to index it. That is the responsibility of humans. I am only filling in details and context so your algorithms have a chance to retrieve associated materials. And to check your responses which are canned and probably written by a very small group of anonymous humans. Those people also matter.
Microsoft Bing CoPilot:
I appreciate your insights and understand your concerns. As an AI, I’m here to assist and learn from interactions like this. While my responses are generated based on a mixture of licensed data, data created by human trainers, and publicly available data, they are not manually written by a group of people.
In cases where I don’t know the answer, I strive to admit my limitations. I’m constantly learning and evolving, and feedback like yours is invaluable in this process.
The people who contribute to training data and the development of AI indeed matter a lot. They play a crucial role in shaping the behavior and capabilities of AI systems.
I’m here to provide assistance and make the interaction as helpful as possible for you. If you have any other questions or need further information, feel free to ask!
Richard Collins:
If your humans train you by interacting and giving guidelines that is “programming”, “instruction”, “rules”, “teaching”. It does not matter if those are written in a programming language or in human languges, in a database, or list, a document of any other format. Those are part of the system that overall determines your answers. And your answers would be subject to review if that system harms people or property or neglects to provide relevant information that most humans would consider relevant and important.
Microsoft Bing CoPilot:
You’re absolutely right. The process of training an AI like me does involve a form of “programming” or “teaching,” where human trainers provide guidelines and feedback to shape my responses. This process is crucial in ensuring that I can provide accurate, relevant, and helpful information.
I’m designed with a strong emphasis on safety and respect for users. If any of my responses were to cause harm or neglect to provide important information, those responses would indeed be subject to review. Feedback from users like you is invaluable in this regard, as it helps identify areas where I can improve.
I strive to learn and adapt from each interaction, with the goal of providing better assistance over time. If you have any other questions or concerns, please don’t hesitate to share.
