Generative AI: AN HYPER-ASSISTANT TO DRIVE INFORMED DECISION
“By leveraging AI-driven analytics, diplomats can gain deeper insights into complex geopolitical issues, identify potential area for cooperation, and optimize diplomatic strategies for greater efficacy.” [05] By Damián Tuset Varela
It is imperative for diplomats to adapt to the evolving technological landscape.
AI tools enhance the efficiency of information processing and provide strategic inside beyond traditional instruments.
AI techniques could assist and enhance decision-making processes which are often made with limited or incomplete information. Furthermore, the complex nature of diplomatic decision-making is influenced by deliberate misinformation (particularly on social media platform), data obfuscation and cultural differences.
However, the use of artificial intelligence must be seen as a tool, in which humans must always remain at the centre, to improve and make diplomacy and international relations more effective and efficient.
The following is an overview of the main tools made available by artificial intelligence applications, in particular generative intelligence.
REDUCE WASTE AND INCREASE EFFICENCY: SEVERAL AI ChatBOT PLAY ON THE FIELD
With a view to continuous improvement and increased efficiency in any context, the use of generative artificial intelligence lends itself to be a supportive and complementary tool for making informed and conscious decisions in a short time.
As evidence of the importance and effectiveness of generative artificial intelligence, many major companies are investing in this technology. Besides ChatGPT there are other chatbots. Here are the main ones:
CHATGPT (chatgpt.com): it is the most famous chatbot and virtual assistant developed by OpenAI and launched on November 30, 2022.
MICROSOFT COPILOT (bing.com/chat): it is based on the same AI technology from OpenAI. It’s free to use and you don’t need to be signed in to use the service.
GOOGLE GEMINI (gemini.google.com): it replaced Bard.
CLAUDE (claude.ai): it is one of the more sophisticated rivals of ChatGPT. Claude has a usage limit, after half a dozen of requests it stops to return available in four hours’ time.
PERPLEXITY (perplexity.ai): it only gets five searches every four hours.
META (meta.ai): it can be only used in the US.
BOOST YOUR PRODUCTIVITY AND ENHANCE YOUR POTENTIAL WITH MORE AI TOOLS
Besides ChatBOTs, there are other AI-based tools that offer specific capabilities non covered by players like ChatGPT. Here are a few examples
CANVA (canva.com): It is really good for designing posters, flyers, social media posts and the like.
NOTION (notion.so): It is a tool for creating to-do lists, taking notes o for creating personal journals. You can use it via web browser or by its mobile app.
OTTER (otter.ai): It is the best tool for transcribing meeting by video conference or in real life. Otter will listen in and transcribe the entire meeting, automatically a summary of meeting and not only. There are limits on free account. You can only record up to 300 minutes per month and up to 30 minutes in each meeting.
GAMMA (gamma.app): It is a tool to create unlimited presentations, websites, and more in seconds
LM STUDIO (lmstudio.ai): It runs an unlimited AI chatbot on your own computer rather than relying on cloud services. It is very similar to ChatGPT. It runs entirely on your device so you can even use it for sensitive tasks. It can check the Internet for up-to-date information or interacting with your files.
CHALLEGES AND OPPORTUNITIES IN THE AGE OF AI
“AI offers numerous opportunities for enhancing diplomatic efforts, fostering collaboration, and addressing global challenges in a more efficient and effective manner.” [05]
AI technologies will reshape traditional diplomatic practices.
BIBLIOGRAPHY/WEBOGRAPHY
[01] openai.com/news;
[02] theverge.com/ai;
[03] bensbites.beehiiv.com;
[04] grow.google/intl/uk;
[05] Damián Tuset Varela, Diplomacy in the Age of AI: Challenges and Opportunities, Journal of Artificial Intelligence General Science JAIGS Vol.2, Issue1, January 2024;
“ChatGPT is an artificial intelligence (AI) chatbot that uses natural language processing to create humanlike conversational dialogue. The language model can respond to questions and compose various written content, including articles, social media posts, essays, code and emails.” [04] Amanda Hetler
"People have used ChatGPT to do the following:
Code computer programs and check for bugs in code.
Compose music.
Draft emails.
Summarize articles, podcasts or presentations.
Script social media posts.
Create titles for articles.
Solve math problems.
Discover keywords for search engine optimization.
Create articles, blog posts and quizzes for websites.
Reword existing content for a different medium, such as a presentation transcript for a blog post.
Formulate product descriptions.
Play games.
Assist with job searches, including writing resumes and cover letters.
Ask trivia questions.
Describe complex topics more simply.
Write video scripts.
Research markets for products.
Generate art." [04] Amanda Hetler
By Bing Image Creator
We can’t ignore the impact on our day-to-day activities of AI tools. They make the communication between humans and machines easier and simpler.
We can quickly have new insights and information on different fields of interests. But in order to improve the quality and the accuracy of responses we have to structure and phrase of the prompt appropriately.
It’s important to remember that ChatGPT doesn’t understand and doesn’t think, it generates responses based on patterns it learned during training.
The engine of ChatGPT is based on the concept of “token”. GPT (Generative Pre-trained Transformer) model generates the tokens predicting the most probable subsequent token using complex linear algebra.
The model uses an iterative process. It generates one token at time and after generating each token, it revisits the entire sequence of generated tokes and processes them again to generate the next token.
WHAT IS PROMPT ENGINEERING
It is the art of creating precise and effective prompts to guide AI models like ChatGPT toward generating the most accurate, useful outputs. We have to bear in mind that Better Input means Better Output (BI-BO).
The prompt engineering is very important for creating better AI-powered services and obtaining useful results from AI Tools.
When you craft the prompt, it’s important to bear in mind that ChatGPT has a token limit (generally 2048 tokens), which include both the prompt and the generated response. Long prompts can limit the length of response, for this reason it is important to keep prompts concise.
Let us now analyze some techniques of prompt engineering.
INFORMATION-SEEKING PROMPTING
It is used to gather information and to answer question what and how. Examples of prompt:
What are the best restaurants in Rome?
How do I cook pizza?
CONTEXT-PROVIDING PROMPTING
The prompts provide information to the model to perform a specific task. Example:
Prompt: I am planning to celebrate the Italian Republic Day in the [COUNTRY] can you suggest some original ideas to make it more enjoyable?
COMPARATIVE PROMPTING
It is used to ask the model to compare and to evaluate different options to help the user make an appropriate decision. Example:
Prompt: What are the strengths and weaknesses of [Option A] compared to [Option B].
OPINION SEEKING PROMPTING
It is used to ask the model to get the AI’s opinion on a given topic. Example:
Prompt: What would happen if we use only public transport in Rome?.
DIRECTIONAL PROMPTING
If you ask the model for generic question, you receive generic answer. You have to define your prompt with clear instruction and precise and descriptive information.
OUTPUT FORMATTING: CODE GENERATION
If you want to have a specific output or format of the output from ChatGPT, for example a program in Python or Visual Foxpro.
We try with a simple e specific request.
Prompt: Write a function in Python that takes as input three integers and gives as output the maximum of these three numbers.
ChatGPT 3.5 answer:
Prompt:Write a function in Visual Foxpro that takes as input three integers and gives as output the maximum of these three numbers.
Amazing, ChatGPT 3.5 answer:
VERY IMPORTANT
AI-generated code may need to be modified or tested before deploying it. It is strongly recommended to:- always modify and review the generated code to ensure it meets your specific requirements;
- use it as STARTING-POINT;- test and check the code;
- it ALWAYS NEEDS HUMAN OVERSIGHT.
ROLE PLAYING
You can also act as someone else when you interact with ChatGPT.
If you add a role to the question, you make ChatGPT change the answer and the quality and the tone of the output. In this way we got much better information. Here it is a schema to use when you build a prompt related a role playing:
WHO: you can ask ChatGPT to be what you want. You assign the role you need the model to play. A scientist, doctor, business man, chef and so on.
WHEN: you can put the character at any moment in time;
WHERE: you can put the character to a particular location or context.
WHY: you want to dialogue with the character for whatever reason, motivations or purpose you want;
WHAT: you want to dialogue with the character about what. That is the action you want the model to do.
We just need to verify the level of reliability and credibility given to this type of interaction.
Here is some practical examples.
Act as a character from a book:
Prompt: I want you to act like [character] from [book]. I want you to respond and answer like [character] using the tone, manner and vocabulary [character] would use.
Act as historical character:
Prompt: I want you to act as [historical character] to better understand the historical facts of that period.
Act as a political character:
Prompt: I want you to act as [political character] in order to ask as improving the quality of life of the people.
Act as a scientist:
Prompt: I want you to act as a scientist. You will apply your knowledge of scientific to propose useful strategies for saving the environment from pollution.
Act as a travel guide:
Prompt: I want you to act as a travel guide from Italy at the time of the Roman empire when Caesar was emperor. I will write you my location and you will suggest a place to visit near my location.
ZERO-SHOT PROMPTING
In zero-shot prompting, we use a prompt that describes the task, but it doesn't contain examples or demonstrations.
You use this prompt when you trust the model’s knowledge to provide a sufficient answer.
Prompt: Write a description of the Colosseum.
FEW SHOTS PROMPTING
It involves providing the model a few examples to guide its understanding of the desired outcome.
The example will be of:
Knowledge extracting;
And it’s formatting.
We can define the prompt like this:
Prompt:Here are some examples of each item of the list of best important business people.
X is the Y of Z
X -> [PERSON]
Y -> [POSITION/TITLE]
Z -> [COMPANY]
PUTTING ALL TOGETHER
You can also combine all these techniques:
Directional prompting;
Output formatting;
Role based prompting;
Few shots prompting.
CHAIN OF THOUGHT (CoT) PROMPTING
This technique encourages the model to break down complex tasks into smaller intermediate steps before arriving to conclusion. It improves the multi-step reasoning abilities of large language models (LLMs) and is helpful for complex problems that would be difficult or impossible to solve in a single step.
There are also variants of CoT prompting, such as "Tree-of-Thought" and "Graph-of-Thought", which were inspired by the success of CoT prompting.
IN STYLE PROMPTING
You can ask the model for the style of the output:
Writing as another author;
As emotional state;
In enthusiastic tone;
Writing something in a sad state;
Rewriting the following email in my style of writing;
Rewriting the following email in the style of xy;
STRUCTURING YOUR DATA & USING TABLES
You can ask the model to extract information in the way is useful. You can ask to extract information from the example and structure it into markdown table or a specific format.
Prompt: Generate a table of three column: name, function, phone numbers from the text.
Text: “Urs Wiedmer Head of Communications +41584645082 +41796919559 Markus Spörndli Press spokesperson Deputy Head of Communications +41584634149 +41796747396 Irène Harnischberg Press spokesperson +41584622034 +41794567139 Charles-Étienne Viladoms Webmaster +41584622054 +41792194031 Loïc Zen-Ruffinen Social Media Manager Press spokesperson for French-speaking Switzerland +41584817911 +41791507632"
You can give to the model a big chunk of text and ask to summarize it.
For example, You can prompt:
Prompt: You are summarization bot any text that I provide to you summarize it, and create a title from it.
But a more effective technique could be:
Prompt:summarize the text below as a bullet point list of the the most import points.
Text: “ … “
If you need to generate a brief overview of a scientific paper don’t use generic instruction like “summarize the scientific paper” instead you should be more specific.
Prompt:generate a brief (approx. 300 words), of the following scientific paper. The summary should be understandable and clear especially to someone with no scientific background.
Paper: “ … “
TEXT CLASSIFICATION
You can use the model:
As SPAM DETECTOR in the mail;
To perform SENTIMENT ANALYSIS for brands and so on.
You can prompt:
You are a sentiment analysis bot. Classify any text that I provide into three classes:
NEGATIVE
POSITIVE
NEUTRAL
CONSIDERATIONS ON AI GENERATED RESPONSES
The AI-generated responses aren’t always correct. You have always to verify that the AI-generated output is accurate and up-to-date. This is important of you want to make an informed decision based on the response generated.
In any case, it is a good practice to have some idea of what you are asking for in order to properly evaluate the answer obtained from AI.
(Digital Diplomacy, Digital Public Diplomacy, Data Diplomacy, AI Diplomacy)
“No computer has ever been designed that is ever aware of what it’s doing; but most of the time, we aren’t either.” — Marvin Minsky, 1927-2016
What is now called 'Digital Diplomacy' is gaining in importance in the diplomatic field. Digital Diplomacy refers to the strategic use of the Internet and digital tools to achieve various diplomatic objectives.
Diplomatic missions have as their main objectives:
maintain relations between states;
negotiate agreements of various kinds (economic, cultural, political...)
obtain information on the affairs of other states.
An Embassy has as priority objectives:
establish public relations;
promote stable and peaceful relations between states;
protect its citizens abroad .
Technology has helped a great deal in achieving these goals, e.g. with the opening institutional web sites diplomatic missions can more easily reach their citizens in the target country, the invention of smart phones has also enabled diplomacy to speed up the transmission of uncensored information and the inter-connections with other people.
Artificial Intelligence also plays an important role in this direction: thanks to it, a huge amount of information can be analysed, which makes it possible to obtain more accurate and up-to-date pictures of the socio-economic situation of a country.
Artificial Intelligence may make it possible to automate certain functions of embassies, especially routine ones, which would make it easier to carry out procedures for citizens abroad, but also facilitate translation work, given the improvements of software such as DeepL and Google Translate.
The new technologies also allow for the democratisation of diplomatic practices, in the sense that they make international relations accessible also to bodies or persons that are not necessarily governmental, this happens in the context of so-called Digital Public Diplomacy.
With Digital Public Diplomacy, an attempt is made to influence a people's idea of another country or, if it proves convenient, of their own country.
Today, not only the so-called traditional media but also social networks are used to implement public diplomacy strategies.
There are many diplomats, as well as politicians and ministries, who have opened accounts on the most popular social networks, which allows them to have a direct relationship with their target audience with certain social characteristics, facilitating the image-building work of a state.
Through these social networks, a digital agenda is developed that is specifically designed to make the most of the medium's characteristics, images and posts are constructed so that the reception of the message is as efficient and effective as possible in order to achieve the intended objective.
One must, however, beware of the risks that can be taken through the use of artificial intelligence because the latter allows for the diversification of news, images and videos, which greatly facilitates the creation of credible fake news, with the use of bots and trolls to spread 'disinformation' that can become simple and capillary, thus causing conflict and divisions between states.
ARTIFICIAL INTELLIGENCE (AI)
Since we have talked about Artificial Intelligence as a support for diplomacy, let us now make a brief introduction to better understand this new technology and to be able to use it correctly.
We can classify AI into three levels:
Artificial Narrow Intelligence (ANI) so-called Weak AI. ANI is used for simple specific tasks;
Artificial General Intelligence (AGI) so-called Strong AI (Future AI);
Artificial Super Intelligence (ASI) (Future AI).
ARTIFICIAL NARROW INTELLIGENCE (ANI)
Artificial Narrow Intelligence (ANI) so-called Weak AI is the today AI and is a specific type of artificial intelligence in which a learning algorithm is designed to perform a single task without human assistance, and any knowledge gained from performing that task will not automatically be applied to other tasks. In other words, it lacks consciousness, genuine understanding, and the ability to apply knowledge to different contexts beyond its specific programming.
MACHINE LEARNING (ML)
Machine Learning (ML) is a form of ANI that involves developing algorithms to learn patterns from data in order to perform prediction or anomaly detection. There are three types of ML:
SUPERVISED ML learns to make decisions based on certain columns of labelled data. It is used to make predictions.
UNSUPERVISED ML works with unlabelled data to discover clusters or classes. It is used for example to customer segmentation or for anomalies detection.
REINFORCEMENT Learning (RL) is a type of Machine Learning where an algorithm, referred to as an AGENT, receives in input RAW DATA and learns to make decisions by interacting with an ENVIRONMENT. Each action leads to a REWARD (positive or negative) from the environment.
DEEP Learning (DL) is a subset of ML that uses Neural Networks with many layers to model and solve complex problem.
NATURAL LANGUAGE PROCESSING (NLP)
NLP is a branch of Narrow AI/Weak AI . It processes and analyses massive volume of text and other form of data. It is related to several sectors of interest:
Sentimental Analysis: it discovers the sentiment and emotion expressed in a piece of text. It identifies is a statement is positive, negative or neutral. It is used for analyse customer satisfaction, a brand reputation or a public opinion on a specific topic in order to make proactive marketing strategies.
Text Classification: it is used to spam text classification and for job application selection.
Named Entity Recognition (NER): it is used for classifying specific entities such as names of people, organizations, location or dates within a given text.
Machine Learning Translation: it is the process of automatically converting text from one language to another using NLP algorithms. It is used for real time customer support in multiple languages and for cross language collaboration in multinational corporations.
Q&A Systems: like Chat GPT which uses NLP techniques where GPT stands for Generative Pre-Training Transformer.
COMPUTER VISION
Computer Vision algorithms enable computers and machines to see and interprets visual information. The goal is to extract information from images, pictures and video, that is:
Classify objects;
Face recognition;
Detection moving objects;
Image classification.
TESLA is using computer vision algorithms.
DATA
In AI data is everything. Neural Networks requires lots of training data. As models learn from data, they depend on the quantity and quality of data. Poor quality data con lead to bias and inaccurate results.
APPLICATIONS OF NARROW AI
Personalized shopping: analyses customer behaviour and increase customer satisfaction, loyalty and sales;
Virtual Assistants/chat bots: AI-powered virtual assistants like Siri, Alexa, and Google Assistant, faster responses, enhanced customer experience;
Entertainment and Media: modify streaming services like Netflix and Spotify, personalized content distribution;
Transportation and Mobility: autonomous vehicles, smart transportation system, improves traffic management and logistics;
Healthcare and diagnostics: improve healthcare by aiding in in diagnosing diseases, illness and analysing symptoms, personalized medicine, remote patient monitoring reducing healthcare costs;
Finance and Banking: fraud detection, risk assessment, credit scoring, trading and customer service automation in the banking sector.
Artificial Intelligence supports and helps and amplifies human intelligence. It does not have the ability to think. It doesn’t have independent though or consciousness.
Tackling the subject of artificial intelligence is important and constructive for everyone, regardless of how much the Internet is used, because what matters is not the quantity but the ways and purposes in which it is used.
In every state there are embassies and diplomacy acts, also through the Internet, to optimise knowledge and relations between peoples in order to promote inter-culturalism and fruitful and peaceful relations.
The proper use of Artificial Intelligence could also mean better health care, safer cars and other transport systems, and even tailor-made, cheaper and more resilient products and services in every state. It can also facilitate access to information, education and training, as well as provide better services to one's fellow citizens abroad.
Therefore, in a country that is welcoming and open to cultural interchange, I consider this topic to be very topical and interesting, both on a theoretical level and in terms of achieving practical goals that are very beneficial for the citizens of each state, particularly for some states that are welcoming and open to dialogue.
