Inextricably embedded ethics, I like it!
Values in Artificial Intelligence Systems
This chapter argues that ethical values are inextricably embedded in Artificial Intelligence (AI) systems. AI systems assist in driving our cars and screen job applications for companies looking to hire new employees. In developing an AI system, researchers must make decisions about which problem is to be addressed and how this problem is to be framed. AI systems that involve the collection, use, and storage of data about human beings – including social media platforms, personal digital assistants, and contact tracing systems – have design features that significantly impact privacy. In creating an AI system that classifies individuals into categories, designers must decide which type of fairness they wish to encode into the system – which conceptions of fairness they wish to prioritize and which they are willing to violate. In creating an AI system that classifies individuals into categories, designers must decide which type of fairness they wish to encode into the system.
Are lawyers beginning to sweat?
AI as Lawyer: It's Starting as a Stunt, but There's a Real Need
Next month, AI will enter the courtroom, and the US legal system may never be the same.
An artificial intelligence chatbot, technology programmed to respond to questions and hold a conversation, is expected to advise two individuals fighting speeding tickets in courtrooms in undisclosed cities. The two will wear a wireless headphone, which will relay what the judge says to the chatbot being run by DoNotPay, a company that typically helps people fight traffic tickets through the mail. The headphone will then play the chatbot's suggested responses to the judge's questions, which the individuals can then choose to repeat in court.
It's a stunt. But it also has the potential to change how people interact with the law, and to bring many more changes over time. DoNotPay CEO Josh Browder says expensive legal fees have historically kept people from hiring traditional lawyers to fight for them in traffic court, which typically involves fines that can reach into the hundreds of dollars.
(Related)
Can artificial intelligence displace attorneys? A ‘conversation’ about law with OpenAI
… As an attorney, I cannot help but wonder if artificial intelligence has the ability to replace me? Can artificial intelligence formulate the same responses to client questions that I, an attorney of 25 years of experience would?
When we compared OpenAI versus lawyers, lawyers seem have the upper hand today, but how soon will that change?
Here is the request I entered into OpenAI (using the GPT-3 model): Describe the power of OpenAI and why that may scare a lawyer in six paragraphs.
OpenAI’s response: OpenAI’s research has had a profound impact on the AI field as a whole, as well as various industries. OpenAI’s breakthroughs in natural language processing (NLP) have enabled machines to communicate with humans in a more natural way. OpenAI has also made advances in reinforcement learning, which has enabled machines to learn from their environment and take action without explicit instructions. OpenAI has also developed bots that have been able to beat the world’s best players in games like Dota 2 and Go.
The power of OpenAI may scare a lawyer because of its potential to automate many aspects of the legal profession. For example, OpenAI has developed GPT-3, an NLP system that can perform legal research and write legal documents. This could potentially make the work of lawyers much easier, but could also lead to job losses in the legal profession. Additionally, OpenAI’s research could lead to the development of AI-powered systems that can make decisions on legal cases, potentially leading to a shift away from human-centric legal decision-making.
OpenAI’s advances could also lead to new challenges in the legal field. For example, OpenAI’s research on AGI could lead to the development of systems that can make decisions and take action autonomously. This could lead to difficult questions about the legal responsibility of these systems and how to regulate them. Additionally, OpenAI’s research could lead to new challenges in terms of data privacy, as OpenAI’s systems have access to large amounts of data that could be used for nefarious purposes.
The power of OpenAI could lead to a revolution in many fields, including the legal profession. While OpenAI’s research could lead to many benefits in the legal field, it could also lead to new challenges that lawyers will have to grapple with. For this reason, OpenAI’s power may be something that lawyers need to be aware of and prepare for.
Never mind that OpenAI’s response was four paragraphs, this is a pretty good answer, although it’s missing some fundamental issues.
Which will go first, lawyers or judges?
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4319969
The Rule of Algorithm and the Rule of Law
Can AI adjudicative tools in principle better enable us to achieve the rule of law by replacing judges? This article argues that answers to this question have been excessively focussed on 'output' dimensions of the rule of law – such as conformity of decisions with the applicable law – at the expense of vital 'process' considerations such as explainability, answerability, and reciprocity. These process considerations do not by themselves warrant the conclusion that AI adjudicative tools can never, in any context, properly replace human judges. But they help bring out the complexity of the issues – and the potential costs – that are involved in this domain.
An interesting perspective?
https://link.springer.com/chapter/10.1007/978-3-031-17992-1_6
The Future
In the twenty-first century, the pace of change has become exponential. This means that we are now in a period of exponential ethics that we might call “hyper-ethics.” Hence, a reliable ethical framework is important to ensure that our technological advances do not yield deleterious outcomes. This chapter describes the various technological innovations that will remake our physical beings and our internal selves and that will result in artificial intelligence (AI), that is many orders of magnitude more intelligent than humans—a “transhumanist” future. A host of pivotal questions arises from these developments including how to address challenges such as fewer jobs, less equality, body enhancements, altered family structures, and radical life extension. How should Judaism respond to these fundamental issues which in essence require the reconsideration of what it means to be human?
No comments:
Post a Comment