Tag: Thalif Deen

• by Thalif Deen (united nations)
• Thursday, June 15, 2023
• Inter Press Service

Still, one thing is certain: as Microsoft co-founder Bill Gates predicts, AI “will change the way people work, learn, travel, get health-care and communicate with each other”.

But will AI also make a difference to an international organization like the UN—and perhaps influence its working methods, its mandate, and its broader missions overseas.?

With a proposed AI summit of world leaders looming on the horizon– on a yet-to-be-decided date– we posed several questions to ChatGPT, an AI-powered chatbot developed by OpenAI based on the company’s Generative Pre-trained Transformer (GPT) series.

Excerpts from the Q&A follow:

Q: The UN plans to draft a Code of Conduct to monitor AI and prevent abuses. Will this work and is it practicable?

ChatGPT: The concept of developing a code of conduct to monitor AI and prevent abuses is a step in the right direction, given the potential impact of artificial intelligence on various aspects of society.

Establishing guidelines and ethical frameworks for the development and use of AI can help address concerns related to privacy, bias, accountability, and potential harmful consequences.

However, the effectiveness and practicability of such a code of conduct would depend on various factors, including:

International Cooperation:

The adoption and enforcement of a code of conduct would require broad international cooperation among different countries and stakeholders. Achieving consensus and addressing diverse perspectives can be challenging, as interests, cultural values, and technological capabilities vary across nations.

Enforceability:

The code of conduct would need mechanisms to ensure compliance and enforcement. Establishing clear accountability frameworks and regulatory mechanisms would be crucial to prevent abuses and incentivize adherence to the guidelines. It would require cooperation between governments, organizations, and technological actors.

Technological Pace:

The field of AI is rapidly evolving, with new technologies, applications, and challenges emerging regularly. Ensuring that the code of conduct remains up to date and adaptable to technological advancements would be essential. Regular reviews and updates would be necessary to keep pace with the evolving landscape of AI.

Balance between Innovation and Regulation:

While it is important to prevent AI abuses, it is equally important not to stifle innovation and the potential benefits that AI can bring to society. Striking the right balance between regulation and fostering innovation would be critical to ensure that the code of conduct does not unduly hinder progress.

Global Consensus:

Achieving a global consensus on the specifics of the code of conduct might be challenging, as different countries and stakeholders may have differing views on AI development, applications, and regulation. Balancing diverse perspectives and interests while working towards a common framework could be a complex task.

It’s worth noting that developments may have occurred since my knowledge cutoff date that could provide more information about the UN’s code of conduct or similar initiatives. To assess the current status and practicability of such efforts, it would be best to refer to the latest news, reports, and official statements from relevant organizations involved in shaping AI policies and guidelines.

Q: Is there a UN role for artificial intelligence?

ChatGPT: Yes, AI chatbots can be of great assistance to international organizations like the United Nations. Here are some ways in which AI chatbots can help:

Multilingual Support:

The United Nations deals with a diverse range of languages from all over the world. AI chatbots can be programmed to understand and respond in multiple languages, making them valuable tools for providing multilingual support to UN staff, delegates, and the general public.

Information and Resource Accessibility:

AI chatbots can be designed to provide quick and accurate access to information and resources. They can assist in retrieving data, documents, reports, and other relevant information from vast UN databases, making it easier for staff and users to find the information they need efficiently.

Real-time Communication:

Chatbots can handle a large volume of inquiries simultaneously, providing real-time communication and support. They can assist in answering frequently asked questions, offering guidance on procedures, and addressing common concerns, freeing up human resources for more complex tasks.

Public Engagement and Outreach:

AI chatbots can be integrated into the UN’s website or social media platforms to engage with the public, answer their queries, and provide information about the organization’s activities, initiatives, and campaigns. This can enhance public outreach and promote transparency and accessibility.

Data Analysis and Insights:

AI chatbots can gather and analyze data from conversations and interactions, providing valuable insights and trends. This can help the United Nations identify patterns, understand public sentiment, and make informed decisions based on data-driven analysis.

Crisis Management:

During times of crisis or emergencies, AI chatbots can help disseminate critical information, provide updates, and answer urgent queries. They can offer a channel for people to seek assistance and access relevant resources, contributing to effective crisis management.

It’s important to note that while AI chatbots can offer significant benefits, they are not intended to replace human interactions entirely. Rather, they serve as valuable tools to enhance efficiency, accessibility, and engagement within the organization.

Q: There is a proposal to set up a special UN body to monitor and regulate AI Chatbot? Will this work?

ChatGPT: As an AI language model, I can provide an analysis of the proposal to set up a special United Nations (UN) body to monitor and regulate AI chatbots. Please note that my response is based on information available up until September 2021, and developments after that date may have occurred.

Establishing a dedicated UN body to monitor and regulate AI chatbots could have both advantages and challenges. Here are some key points to consider:

Advantages:

AI chatbots transcend national boundaries, and having an international body to oversee them could facilitate global coordination and harmonization of standards and regulations. It could provide a platform for countries to share best practices and collaborate on addressing common challenges.

Addressing ethical concerns:

AI chatbots raise ethical considerations such as privacy, bias, transparency, and accountability. A specialized UN body could help develop guidelines and regulations to address these concerns, ensuring that AI chatbots are developed and deployed responsibly.

Consistency and standards:

A central regulatory body could help establish consistent standards and guidelines for the development and deployment of AI chatbots. This could enhance trust among users and promote responsible and ethical use of AI technologies.

Challenges:

Technological advancements: AI technology is rapidly evolving, and chatbots are becoming increasingly sophisticated. Regulating such technology can be challenging, as the regulatory framework may struggle to keep pace with the rapid development of AI chatbots. Balancing innovation and regulation are crucial.

Jurisdictional issues:

AI chatbots operate globally, and it can be difficult to determine jurisdiction and enforce regulations across different countries. Cooperation and agreement among nations would be necessary to ensure effective regulation.

Potential stifling of innovation:

Overregulation could impede innovation and limit the potential benefits of AI chatbots. Striking the right balance between regulation and fostering innovation would be essential to avoid hindering technological advancements.

Overall, the establishment of a special UN body to monitor and regulate AI chatbots could provide a platform for global coordination, ethical considerations, and standardization. However, it would require careful consideration of the challenges involved to ensure that the regulatory framework remains flexible, promotes innovation, and adapts to the rapidly evolving AI landscape.

Q Can AI CHATBOT help UN resolve some of the world’s ongoing military conflicts?

ChatGPT: As an AI language model, I can provide information and potential insights on various topics, including military conflicts. However, it is important to note that resolving complex geopolitical issues and ongoing military conflicts requires a multifaceted approach involving political negotiations, diplomacy, and cooperation among nations. While AI technology can support decision-making processes and provide analysis, it cannot independently resolve conflicts.

The United Nations (UN) plays a crucial role in facilitating dialogue and negotiations between conflicting parties. It utilizes a range of resources, including human expertise, diplomatic channels, and specialized agencies, to address conflicts. AI technology can be employed within these frameworks to enhance data analysis, aid in conflict resolution strategies, and support decision-makers with information.

AI-powered chatbots like AICHATBOT can provide insights and information to policymakers, diplomats, and negotiators. They can help gather and analyze data, identify patterns, and offer recommendations based on historical data or simulations. This can assist in understanding the complexities of conflicts, exploring potential resolutions, and predicting the outcomes of different scenarios.

However, it’s important to recognize that resolving military conflicts requires human judgment, empathy, and political will. AI can provide valuable assistance, but ultimately, sustainable resolutions require the collective efforts and collaboration of nations, international organizations, and stakeholders involved in the conflicts.

Q: How credible are the responses provided by AI CHATBOT? Is there a mix of fact with fiction?

ChatGPT: As an AI language model, I strive to provide accurate and helpful responses based on the information available to me up until September 2021. However, it’s important to note that I do not have real-time access to current events or ongoing developments beyond that date. Therefore, any information I provide about events, news, or specific details related to the period after September 2021 may be outdated or incorrect.

While I attempt to provide reliable and factual information, there is still a possibility of errors or inaccuracies in my responses. Additionally, as an AI, I do not possess personal opinions or beliefs. I generate responses based on patterns and information in the training data I was provided with, which includes a mixture of factual information from reputable sources as well as some fictional or hypothetical examples.

It’s always a good idea to verify information from multiple sources and consult authoritative references or experts when dealing with critical matters or seeking the most up-to-date information.

Is AI ChatGPT capable of producing UN press releases, transcripts of press briefings and the annual report of the Secretary-General?

ChatGPT: As an AI language model, I can certainly generate text in the style of UN press releases, transcripts of press briefings, and reports. However, please note that the accuracy and reliability of such generated content may vary, and it is always important to verify information from official sources.

While I strive to provide accurate and up-to-date information, it’s crucial to consult official UN channels and publications for official press releases, transcripts, and reports.

IPS UN Bureau Report

Follow @IPSNewsUNBureau
Follow IPS News UN Bureau on Instagram

© Inter Press Service (2023) — All Rights ReservedOriginal source: Inter Press Service

• by Thalif Deen (united nations)
• Tuesday, June 06, 2023
• Inter Press Service

In a statement in its website, OPENAI founders Greg Brockman and Ilya Sutskever, along with chief executive Sam Altman, say that to regulate the risks of AI systems, there should be “an international watchdog, similar to the International Atomic Energy Agency (a Vienna-based UN agency) that promotes the peaceful uses of nuclear energy”.

“Given the possibility of existential risk, we can’t just be reactive,” they warned in a joint statement last week.

The UN Educational, Scientific and Cultural Organization (UNESCO), which hosted more than 40 ministers at an groundbreaking online meeting on May 26, said less than 10 per cent of schools and universities follow formal guidance on using wildly popular artificial intelligence (AI) tools, like the chatbot software ChatGPT.

Asked about a UN role in AI, Ambassador Anwarul Chowdhury, former Under-Secretary-General and High Representative of the United Nations told IPS UN Secretary-General Antonio Guterres in his report titled Our Common Agenda (OCA) issued in September 2021 promises, “to work with Member States to establish an Emergency Platform to respond to complex global crises.”

“The platform would not be a new permanent or standing body or institution. It would be triggered automatically in crises of sufficient scale and magnitude, regardless of the type or nature of the crisis involved.”

AI is undoubtedly one of such “complex global crises” and it is high time now for the Secretary-General to formally share his thinking on how he plans to address the challenge, said Ambassador Chowdhury, founder of the Global Movement for The Culture of Peace.

He pointed out that it will be too late for the Summit of the Future, convened by the Secretary-General in September 2024, to discuss a global regulatory regime for AI under UN authority. In that timeframe, he argued, AI technology would manifest itself in a way that no global governance would be possible.

Robert Whitfield, Chair, One World Trust and the Transitional Working Group on AI, told IPS the point about the UN and AI is that AI desperately needs global governance and the UN is the natural home of such governance.

At present, he pointed out, the UN is preparing a Global Digital Compact or approval in September 2024 which should include Artificial Intelligence.

”But in reality, the UN is hardly at the starting block on AI governance, whereas the Council of Europe, where I am at the moment, is deep in its negotiation of a Framework Convention for AI,” said Whitfield, who is also chair of the World Federalist Movement/Institute of Global Policy.

The Council of Europe’s work is limited to the impact on human rights, democracy, and rule of law – but these are wide-ranging issues.

Whilst participation in Council of Europe Treaties is much wider than the European Union, with other countries being welcomed as signatories, he said, it is not truly global in scope and any UN agreement can be expected to be more broadly based.

“The key advantage of the UN is that it would seek to include all countries, including Russia and China, arguably the country with the strongest AI sector in the world”, Whitfield said.

One can envisage therefore a two-step process:

• An initial international agreement within the Council of Europe emerging first of all, following the finalization of the EU AI Act
• And a global UN Framework Convention on Artificial Intelligence being developed later, perhaps following the establishment of a multi-stakeholder forum on AI governance. Such a Convention might well include the establishment of an agency equivalent to the International Atomic Energy Agency as called for most recently by the Elders.

Andreas Bummel, Executive Director, Democracy Without Borders, told IPS: “UN governance of AI should go beyond the usual intergovernmental mechanisms and give citizen-elected representatives a key role through a global parliamentary body”.

The scope of such a parliamentary assembly could be expanded to other issues and enhance the UN’s inclusive and representative character not just in the field of AI, he added.

As generative AI reshapes the global conversation on the impact of artificial intelligence, the International Telecommunication Union (ITU), the UN’s specialized agency for information and communication technologies, will host the 2023 “AI for Good Global Summit” July 6-7 in Geneva.

The two-day event will showcase AI and robot technology as part of a global dialogue on how artificial intelligence and robotics can serve as forces for good, and support the UN’s Sustainable Development Goals, according to ITU.

https://aiforgood.itu.int/summit23/

The event will host the UN’s first robot press conference, featuring a Q&A with registered journalists. Overall, more than 40 robots specialized for humanitarian and development tasks will be on display alongside events with industry executives, government officials, and thought leaders on AI and tech.

Meanwhile, a group of UN-appointed human rights experts warn that AI-powered spyware and disinformation is on the rise, and regulation of the space has become urgent.

In a statement June 2, the experts said that emerging technologies, including artificial intelligence-based biometric surveillance systems, are increasingly being used “in sensitive contexts”, without individuals’ knowledge or consent.

“Urgent and strict regulatory red lines are needed for technologies that claim to perform emotion or gender recognition,” said the experts, including Fionnuala Ní Aoláin, Special Rapporteur on “the promotion and protection of human rights while countering terrorism”.

The experts, appointed by the UN Human Rights Council, condemned the already “alarming” use and impacts of spyware and surveillance technologies on the work of human rights defenders and journalists, “often under the guise of national security and counter-terrorism measures”.

They have also called for regulation to address the lightning-fast development of generative AI that’s enabling mass production of fake online content which spreads disinformation and hate speech.

IPS UN Bureau Report

Follow @IPSNewsUNBureau
Follow IPS News UN Bureau on Instagram

© Inter Press Service (2023) — All Rights ReservedOriginal source: Inter Press Service

• by Thalif Deen (united nations)
• Tuesday, May 23, 2023
• Inter Press Service

Will it take a robot to break that unholy tradition?

At a joint meeting of the UN’s Economic and Social Council (ECOSOC) and its Economic and Social Committee, the robot named Sophia had an interactive session with Deputy Secretary-General Amina J. Mohammed.

But with the incredible advances on CHATGPT chatbot– the AI search engine is now capable of producing texts, articles, pitches, follow-ups, emails, speeches and even an entire book.

If the UN goes fully tech-savvy, will AI chatbot help produce the annual report of the Secretary-General, plus reports and press releases from UN committees and UN agencies?

But the inherent dangers and flaws in AI chat bot include disinformation, distortions, lies, and hate speech—not necessarily in that order. Worse still, the search engine cannot distinguish between fact and fiction.

Testifying before US Congress on May 16, Sam Altman, chief executive of OpenAI urged legislators to regulate AI.

Ian Richards, former President of the Coordinating Committee of International Staff Unions and Associations, (CCISUA) told IPS: “ AI is good at regurgitating what it finds on the internet and which has been put there by someone, whether accurate or not. It basically reproduces existing patterns.”

“However, our work has two parts,” he pointed out.

The interesting, high-value-added part involves talking to people on the ground in remote areas, gathering stories, eliminating biases and creating data from sources that are offline or unreliable. This is something AI would find difficult to do, he added.

The less interesting, low value-added part involves creating tables and charts, running repetitive calculations and formatting documents, he noted.

“If AI can take over some of the latter and give us more time to focus on the former, staff will be both more productive and happier”, said Richards, a development economist at the Geneva-based UN Conference on Trade and Development (UNCTAD).

“But let’s not get too caught up in the hype. And any staff member who relies too much on AI to produce original content will be quickly caught out,” he declared.

Last week the New York Times quoted Gary Marcus, emeritus professor of psychology and neural science at New York University (NYU) calling for an international institution to help govern AI’s development and use.

“I am not one of those long-term riskers who think the entire planet is going to be taken over by robots. But I am worried about what bad actors can do with these things because there is no control over them,” he warned.

Perhaps a future new UN agency on AI?

Meanwhile, some of the technological innovations currently being experimented at the UN include machine-learning, e-translations (involving the UN’s six official languages where machines have been taking over from humans) and robotics.

The United Nations says it has also been using unarmed and unmanned aerial vehicles (UAVs), or drones, in peacekeeping and humanitarian operations, “helping to improve our situational awareness and to strengthen our ability to protect civilians”.

Among the technological innovations being introduced in the world body, and specifically in the UN’s E-conference services, is the use of eLUNa –Electronic Languages United Nations — “a machine translation interface specifically developed for the translation of UN documents.”

What distinguishes eLUNa from commercial CAT (Computer-Assisted Translation) tools is that it was developed entirely by the United Nations and is specifically geared towards the needs and working methods of UN language professionals, says the UN.

Asked whether UN should have a role in the growing debate on AI, UN Spokesperson Stephane Dujarric told reporters May 22: “I think this is an issue that the Secretary-General has expressed extreme worry about — the lack of regulation, the lack of safeguards, especially when it comes to autonomous weapons.”

“And I think he’s been very clear on that. It’s one of the things that keeps him up at night… we should be releasing soon our latest policy paper on the global digital compact”

Referring to AI and the social media, he said: “These are things that need to be dealt with, within what we love to refer as multi-stakeholder settings, because it is clear that in this regard, the power is not solely in the hands of governments. It is very much also in the private sector. And the UN has been and will continue to try to bring all these people to the table.”

Responding to questions whether Guterres plans to convene an international conference on AI, UN deputy spokesperson Farhan Haq said: “I don’t have a meeting to announce for now, but certainly, these are part of the concerns that the Secretary-General himself has been expressing — the idea that as artificial intelligence develops, it needs to be monitored carefully and the right regulations and standards need to be put in place to make sure that this type of technology is not open to abuse”.

Asked if there is any chance that the Secretary-General might consider convening an international conference on AI, Haq said: “That’s certainly something that can be considered. Obviously, if he believes that this would be a helpful step forward, that is what he will do. But again, I don’t have anything to announce at this point.’

Speaking on condition of anonymity, a UN staffer pointed out that the UN once tried out an AI system to generate transcripts for meetings.

But in one instance, it incorrectly cited an European Union (EU) delegate talking about “Russia’s legal invasion of Ukraine” and another delegate accusing the World Intellectual Property Organization (WIPO) of creating a conflict in Northern Ethiopia.

The moral of the story is that AI has to be closely monitored and double-checked because it can produce incorrect information and distort facts and figures.

At a White House May 4 meeting of executives from Google, Microsoft, Anthropic and OpenAI, the maker of ChatGPT, US President Joe Biden conveyed mixed feelings: “What your’re doing has enormous potential– and enormous danger”

IPS UN Bureau Report

Follow @IPSNewsUNBureau
Follow IPS News UN Bureau on Instagram

© Inter Press Service (2023) — All Rights ReservedOriginal source: Inter Press Service