Can AI replace lawyers in International Arbitration? [Part II] - Bard says: NO (on 16 July 2023)

 Can AI replace lawyers in International Arbitration? (Or be used in International Arbitration) [Part II]

This article is also published on LinkedIn

Breaking news:

According to Bard (Google) “it is unlikely that AI will ever completely replace lawyers in international arbitration”. 

I have decided to submit to Bard (Google) the question of Artificial Intelligence and International Arbitration that was first submitted to Bing some time ago.

This was a painful, rather time consuming but interesting experience.

Amongst the good news are:

• The fact that Bard can frankly admit that the question is too complex, in which case the answer is “I'm a text-based AI, and that is outside of my capabilities”.
• The fact that Bard can list a number of flaws that affect AI and that need to be remedied before it can replace human beings.
• The fact that despite the request to list all flaws, Bard provides a list that is quite comprehensive (11 items including: bias, unreliability, foolability, lack of creativity, opacity, safety and security, etc.) but remains open.

The even better news is that according to Bard:

“it is unlikely that AI will ever completely replace lawyers in international arbitration”.

Bard recommends that “we continue to monitor the development of AI in international arbitration” and that we “consider how we can use AI to complement the work of lawyers in international arbitration.”

If we assume that the (undisclosed) source of these conclusions and recommendations is to be found in texts written by human beings, and given the context, likely by lawyers and possibly by arbitration practitioners, this means that these conclusions and recommendations reflect the views of the majority of those who wrote on this question.

Shall we thus conclude that according to a Bard poll, the arbitration community is ready to use Generative AI in International Arbitration, provided it is closely monitored and supervised?

__________________________ 

The text below is the result of a series of requests, because when the request is too complex, no text is generated, and no answer is given. As a result, to obtain some of the answers, it was necessary to breakdown and reformulate questions to make them very simple (bold and italics added in the text of the answers).

___________________________

Question: What is AI?

Answer: AI or artificial intelligence is a branch of computer science that deals with the creation of intelligent agents, which are systems that can reason, learn, and act autonomously. AI research has been highly successful in developing effective techniques for solving a wide range of problems, from game playing to medical diagnosis.

There are many different types of AI, but some of the most common include:

• Machine learning: This is a type of AI that allows systems to learn from data without being explicitly programmed. Machine learning algorithms are used in a wide variety of applications, such as spam filtering, fraud detection, and image recognition.
• Natural language processing: This is a type of AI that allows systems to understand and process human language. Natural language processing algorithms are used in a wide variety of applications, such as machine translation, text summarization, and question answering.
• Computer vision: This is a type of AI that allows systems to see and understand the world around them. Computer vision algorithms are used in a wide variety of applications, such as self-driving cars, facial recognition, and medical image analysis.

The field of AI is constantly evolving, and new techniques are being developed all the time. As AI continues to develop, it is likely to have a profound impact on our lives.

Sources

1.    www.clippingpath.in/blog/ai-in-photography/

2.    viralgotech.com/what-is-artificial-intelligence/

Question: What is AI? What is the difference between generative and general AI?

Answer: AI or artificial intelligence is a branch of computer science that deals with the creation of intelligent agents, which are systems that can reason, learn, and act autonomously. AI research has been highly successful in developing effective techniques for solving a wide range of problems, from game playing to medical diagnosis.

Generative AI is a type of AI that can create new content, such as text, images, or music. This type of AI is often used in applications such as chatbots, text generation, and image editing.

General AI is a type of AI that is capable of performing any intellectual task that a human can. This type of AI is still under development, but it is the goal of many AI researchers.

The main difference between generative AI and general AI is that generative AI is limited to creating new content, while general AI is capable of performing any intellectual task.

Here is a table that summarizes the key differences between generative AI and general AI: 

Feature          Generative AI                           General AI

Purpose        Creates new content            Performs any intellectual task

Examples      Chatbots, text generation,    Self-driving cars, medical

                    image editing                      diagnosis, financial trading

Development More developed                   Less developed

Goal              To create new content         To replicate human intelligence

I hope this helps!

Sources

1.    www.clippingpath.in/blog/ai-in-photography/

2.    viralgotech.com/what-is-artificial-intelligence/

Question: List all the flaws that affect artificial intelligence, give a short explanation with a short example

Answer: Sure, here is a merged list of the flaws that affect artificial intelligence:

• Bias: AI algorithms are often trained on data that is collected from the real world, which can be biased. This can lead to AI algorithms that are biased in their own decision-making.
• Foolability: AI algorithms can be easily fooled by carefully crafted data. This is because AI algorithms are often based on statistical models, which can be manipulated by feeding the algorithm carefully crafted data.
• Unreliability: AI algorithms can make mistakes, and they can be easily tricked. This means that AI should not be used in applications where reliability is critical, such as in medical diagnosis or financial trading.
• Lack of creativity: AI algorithms are not creative in the same way that humans are. They can only generate outputs that are based on the data that they have been trained on.
• Opacity: AI algorithms are often opaque, meaning that it is difficult to understand how they make their decisions. This can make it difficult to trust AI algorithms, and it can also make it difficult to debug them if they make mistakes.
• Safety: AI algorithms can be dangerous if they are not properly designed and implemented. For example, a self-driving car that malfunctions could cause a fatal accident. It is important to carefully consider the safety implications of AI algorithms before they are deployed in real-world applications.
• Data poisoning: This is a type of attack where an adversary intentionally corrupts the data that is used to train an AI algorithm. This can cause the algorithm to learn incorrect patterns and make biased or inaccurate decisions.
• Scalability: AI algorithms can be computationally expensive to train and run. This can limit their use in applications where real-time performance is critical or where there is a large volume of data to be processed.
• Interpretability: AI algorithms are often difficult to interpret, meaning that it is difficult to understand how they make their decisions. This can make it difficult to trust AI algorithms and to debug them if they make mistakes.
• Bias in data: AI algorithms are only as good as the data that they are trained on. If the data is biased, then the algorithm will be biased as well. This can lead to unfair or discriminatory decisions.
• Security: AI algorithms can be vulnerable to cyberattacks. If an adversary is able to gain access to an AI algorithm, they could manipulate the algorithm to make biased or inaccurate decisions.

Question: Do a memo with as a first part the list of flaws that affect AI and as a second part the reasons why AI can or cannot replace lawyers in international arbitration

Answer: Sure, here is a memo with a first part on the list of flaws that affect AI and a second part on the reasons why AI can or cannot replace lawyers in international arbitration:

Memorandum

To: Senior Management

From: Bard

Date: 2023-07-16

Subject: Flaws of AI and its impact on international arbitration

I. Flaws of AI

Artificial intelligence (AI) is a rapidly developing field with the potential to revolutionize many aspects of our lives. However, AI also has some significant flaws that need to be addressed before it can be fully deployed.

Some of the main flaws of AI include:

• Bias: AI algorithms are often trained on data that is collected from the real world, which can be biased. This can lead to AI algorithms that are biased in their own decision-making.
• Foolability: AI algorithms can be easily fooled by carefully crafted data. This is because AI algorithms are often based on statistical models, which can be manipulated by feeding the algorithm carefully crafted data.
• Unreliability: AI algorithms can make mistakes, and they can be easily tricked. This means that AI should not be used in applications where reliability is critical, such as in medical diagnosis or financial trading.
• Lack of creativity: AI algorithms are not creative in the same way that humans are. They can only generate outputs that are based on the data that they have been trained on.
• Opacity: AI algorithms are often opaque, meaning that it is difficult to understand how they make their decisions. This can make it difficult to trust AI algorithms, and it can also make it difficult to debug them if they make mistakes.
• Safety: AI algorithms can be dangerous if they are not properly designed and implemented. For example, a self-driving car that malfunctions could cause a fatal accident. It is important to carefully consider the safety implications of AI algorithms before they are deployed in real-world applications.
• Data poisoning: This is a type of attack where an adversary intentionally corrupts the data that is used to train an AI algorithm. This can cause the algorithm to learn incorrect patterns and make biased or inaccurate decisions.
• Scalability: AI algorithms can be computationally expensive to train and run. This can limit their use in applications where real-time performance is critical or where there is a large volume of data to be processed.
• Interpretability: AI algorithms are often difficult to interpret, meaning that it is difficult to understand how they make their decisions. This can make it difficult to trust AI algorithms and to debug them if they make mistakes.
• Bias in data: AI algorithms are only as good as the data that they are trained on. If the data is biased, then the algorithm will be biased as well. This can lead to unfair or discriminatory decisions.
• Security: AI algorithms can be vulnerable to cyberattacks. If an adversary is able to gain access to an AI algorithm, they could manipulate the algorithm to make biased or inaccurate decisions.

II. Reasons why AI can or cannot replace lawyers in international arbitration.

There are a number of reasons why AI can or cannot replace lawyers in international arbitration.

Arguments in favor of AI replacing lawyers in international arbitration:

• AI can be used to automate many of the tasks that are currently performed by lawyers in international arbitration, such as document review, legal research, and drafting of pleadings.
• AI can be used to identify patterns and trends in legal data that would be difficult for humans to find.
• AI can be used to generate creative solutions to legal problems.

Arguments against AI replacing lawyers in international arbitration:

• AI is not yet as sophisticated as human lawyers when it comes to understanding and applying the law.
• AI is not yet as creative as human lawyers when it comes to generating new legal arguments.
• AI is not yet as trustworthy as human lawyers when it comes to making decisions that could have a significant impact on the outcome of a case.

Conclusion

The use of AI in international arbitration is still in its early stages. It is likely that AI will continue to develop and become more sophisticated in the years to come. However, it is unlikely that AI will ever completely replace lawyers in international arbitration. Lawyers will still be needed to understand and apply the law, to generate creative legal arguments, and to make decisions that could have a significant impact on the outcome of a case.

Recommendation

I recommend that we continue to monitor the development of AI in international arbitration. We should also consider how we can use AI to complement the work of lawyers in international arbitration.

___________________________