Opinion by Jomo Kwame Sundaram (kuala lumpur, malaysia)
Inter Press Service
KUALA LUMPUR, Malaysia, Nov 22 (IPS) – In recent decades, failure to sustain economic progress has been blamed on a supposed middle-income country (MIC) trap. Such blaming obscures as much as it supposedly explains.
The ‘middle-income trap’ fable began as a World Bank story about why upper MICs in Latin America failed to become high-income countries (HICs) after pursuing policies required or prescribed by the Bretton Woods institutions.
Bretton Woods’ Frankenstein
The 1944 Bretton Woods rules-based international monetary system ended in August 1971 when President Richard Nixon unilaterally repudiated US obligations. This happened after the US Treasury had borrowed heavily from the rest of the world from the 1960s.
Jomo Kwame SundaramThe US government’s ‘exorbitant privilege’ of ‘spending well beyond its means’ has continued despite the resulting international monetary ‘non-system’. Continuing acceptance of the US dollar, or ‘greenback’, as the virtual world currency has enabled its Treasury to borrow internationally at low cost.
This has enabled the US to maintain massive trade and current account deficits, and a military presence in much of the world, despite its huge, but still growing fiscal and trade deficits. The US exorbitant privilege seems to have been sustained by its ‘soft power’ and unassailable military superiority.
Facing ‘stagflation’ – economic stagnation with inflation – US Fed chair Paul Volcker raised interest rates sharply from 1980. This soon killed US inflation, but also Roosevelt’s ‘New Deal’ legacy from the 1930s.
With inflation high, real interest rates seemed low despite high nominal interest rates in the developing world. With growth high in the global South in the 1970s, borrowing to sustain investments, even from abroad, remained attractive.
But US interest rate hikes soon triggered fiscal and sovereign debt crises in many countries: Poland in 1981 was followed by various Latin American, African and other developing economies.
Washington Consensus
Facing rising interest rates, many governments could no longer service accumulated debt, let alone borrow to invest more. Instead, they had to pursue contractionary monetary and fiscal policies domestically, causing economic stagnation.
With Margaret Thatcher and Ronald Reagan demanding such macroeconomic policies, the Washington-based Bretton Woods institutions soon prescribed them, ending the post-Second World War Keynesian ‘Golden Age’.
The International Monetary Fund (IMF) demanded contractionary stabilisation policies to qualify for short-term credit facilities. World Bank structural adjustment programmes (SAPs) typically required economic liberalisation and privatisation for longer-term financing.
The Bank also advocated more export-orientation and foreign investment. When paid by Japan’s government, the Bank celebrated its post-war industrial boom as a ‘miracle’, a new model for emulation. But this soon ended with its demise due to the US-demanded overvalued yen and its ill-advised financial ‘Big Bang’.
Latin American conundrum
Latin American and other vulnerable economies lost over a decade from the 1980s while African economies lost a quarter century. Low-interest official Japanese credit initially mainly went to Southeast Asia, while South Asia took on less foreign debt.
Stabilisation and SAP conditionalities undermined Latin America’s modest industrialisation, which also prevented the region from recovering strongly until the new century. But their economies had not been sufficiently liberalised for ‘neoliberals’ despite turning more to foreign trade and investment from the 1980s.
Prosperous economies became more protectionist, especially after the 2008 global financial crisis. But developing countries were told to open up even more despite shrinking export markets.
But with globalisation over, even East Asia can no longer rely on export growth. Also, it is difficult to turn away from export-oriented production, especially as earlier trade deal commitments cannot be unilaterally repudiated.
In many prosperous economies, workers captured some of their productivity gains. But the oft-heard claim that productivity increases lag behind wage rises usually serves employers. In most ‘labour-surplus’ developing countries, wages remain low.
As in South America early this century, progressive redistribution has often accelerated, rather than subverted growth. Common claims that such redistribution is bad for growth must be critically reconsidered. After all, progressive redistribution sustained growth in post-war Europe.
Breaking out of the trap
The ‘middle-income trap’ argument claims MICs cannot sustain rapid economic progress. Supposed reasons vary with policy and ideological biases, as ostensible structural, cultural, political, behavioural or governance causes typically reflect such prejudices.
Recent narratives have proclaimed the need to ‘graduate’ from secondary to tertiary economic activities. Modern services growth is supposedly needed to sustain progress to become HICs.
Another popular argument has been that progressive redistribution has subverted growth. But it is now uncontroversial that progressive redistribution was crucial for sustaining growth in post-war Europe.
Discretionary state powers have undoubtedly been abused for political patronage and self-aggrandisement. Clientelism plagues many societies, undermining needed state interventions. But we should not throw the baby out with the bathwater.
History suggests the best way to overcome the ‘middle income trap’ would be to implement appropriate investment and technology policies. Selective policies are needed to promote growth, not only of manufacturing, but also of high-end services, as well as safe, nutritious and affordable food supplies.
But all this is not going to happen spontaneously. Reforms need to be deliberately elaborated and sequenced through various interventions as part of well-designed, coherent and sustained initiatives.
The state-owned Petróleos Mexicanos (Pemex) oil company is completing its seventh refinery on a 600-hectare site at Dos Bocas in the municipality of Paraíso, in the southeastern state of Tabasco. The plant will process some 290,000 barrels of fuels per day when it reaches full capacity. CREDIT: Erik Contreras-Gerardo Morales / IPS
But the monument lacks another element that has been vital to the region: oil, which has damaged the other three symbols through pollution. Marine animals have been affected by the oil and the mangroves have almost been cut down in a territory that had ample reserves of crude oil.
Despite the fading bonanza, the Mexican government decided to build the Olmeca refinery in the industrial port of Dos Bocas, in Paraíso, to refine some 290,000 barrels per day of oil from the Gulf of Mexico and thus reduce gasoline imports.
It will be the seventh installation of the National Refining System in the country, in a port area that already has a crude oil shipping and export center of the state-owned oil giant Petróleos Mexicanos (Pemex), which controls the exploitation, refining, distribution and commercialization of hydrocarbons in the country.
Construction of the new infrastructure on an area of 600 hectares began in 2019, and although it was officially opened in 2022, the work has not been completed and it is expected to be fully operational in 2024.
But the plant has already provided revenue for the local economy, in the form of rents, transportation and food. However, there are also fears about its impact on a city of more than 96,000 inhabitants.
Genaro, a cab driver who preferred not to give his last name and is married with three children, said there is a sensation of risk. “We know what has happened in other places where there are refineries, with all the pollution. Besides, accidents occur,” he told IPS.
Near the plant is the Lázaro Cárdenas neighborhood, home to hundreds of people and named after the president who nationalized the oil and electric industry in 1936.
There is an uneasy feeling among the local population. Irasema Lozano, a 36-year-old teacher who is a married mother of two, is one of the residents who is apprehensive about “the newcomer” to the city.
“Look around, there are houses, schools, stores. The government says it is a modern plant and that there is no danger, but we don’t feel safe with this huge plant,” she said.
Cab driver Genaro owns a house in the area, which he rents out. But he is now seriously thinking of selling it.
Construction of the plant has altered the life of the sprawling city around Dos Bocas. The “orange people”, referring to the color of the uniforms worn by everyone who works at the facility, are a permanent reminder of the changes as they move around town.
Talking about oil in Tabasco is a delicate matter, since the state is used to living with the exploitation of a light, low-sulfur, cheap and easy-to-extract hydrocarbon. It is also the home state of President Andrés Manuel López Obrador, a staunch defender of fossil fuels.
Pemex has financed the Olmeca megaproject with public funds, through its subsidiary Pemex Transformación Industrial. Its subsidiary PTI Infraestructura y Desarrollo has overseen construction.
The project has already had a high cost overrun, as the initial investment was estimated at seven billion dollars, a figure that has climbed to 18 billion dollars, according to the latest available data.
On this occasion, PTI ID has not turned to the international market to finance the work, according to the response to a public information access request from IPS.
The Olmeca refinery has a cost overrun, escalating from a planned initial investment of seven billion dollars to 18 billion dollars. The Mexican government expects the plant, located in Dos Bocas, in the southeastern municipality of Paraíso, to be fully operational by 2024. CREDIT: Erik Contreras-Gerardo Morales / IPS
The support of international banks
Traditionally, Pemex has depended on financial flows from international private banks. Between 2016 and 2022, 17 institutions gave nearly 61.5 billion dollars to the state-owned oil company, according to annual reports under the heading of “Banking on Climate Chaos” produced by a group of NGOs.
The British bank HSBC was the main financial backer of Pemex during this period, contributing 7.6 billion dollars, followed by the U.S.-based Citi (6.9 billion) and JP Morgan Chase (6.0 billion).
Pemex’s data gives a broader picture, as it shows more players in its lending field. Through direct loans, bond issuance, revolving credits (with automatic renewals) and project financing, 16 financial institutions have granted it 78.9 billion dollars since 2015.
In doing so, the international markets allow Pemex to obtain money for its operations and development, but in exchange they have turned it into the oil company with the highest debt in the world, some 100 billion dollars, which poses a great threat to Pemex and, by extension, to the country.
The main mechanism used is the insurance coverage or underwriting of Pemex’s financial operations by charging a commission.
Maaike Beenes, leader of banking and climate campaigns at the non-governmental BankTrack, told IPS that the large flow of financing means that banks feel confident that Pemex can repay the debt.
“Apparently it is because they think there are guarantees because it is a state-owned company. There is a lot of financing for the expansion of fossil fuel activities,” she said from the Dutch city of Amsterdam.
In 2020, Mexico was the 13th largest oil producer in the world and 19th largest gas producer. In terms of proven crude oil reserves, it ranked 20th and 41st respectively, according to Pemex data.
Two flares burn gas in the Nuevo Torno Largo neighborhood, in the municipality of Paraíso, in the vicinity of the Olmeca refinery. The southeastern state of Tabasco, on the coast of the Gulf of Mexico, has suffered the effects of pollution generated by oil production for more than 50 years through spills, contaminating gases, and water, air and soil pollution. CREDIT: Erik Contreras-Gerardo Morales / IPS
Fueling the crisis
By raising Pemex’s debt rating, the international banks risk their own voluntary climate targets for greenhouse gas (GHG) emission reductions, since the Mexican company’s GHG emission reduction targets are low.
For example, HSBC aims to achieve zero net emissions – where neutralized emissions equal those released into the atmosphere – in its operations and supply chain by 2030 and in its financing portfolio by 2050.
The bank says it is working with its clients to help them reduce their emissions. Its energy policy states that it will not finance new oil and gas fields.
But HSBC’s net zero goal has some gaps. According to the international Net Zero Tracker platform, its strategy lacks a detailed plan to achieve it, and has no reference on equity investment and no specification on formal accountability for monitoring progress, even though it covers Scope 1 (A1), 2 and 3 emissions.
A1 emissions come directly from sources under the polluter’s control, A2 emissions are indirect emissions from purchased energy, and A3 emissions are those originating in the final use of energy, not covered in A1 and A2, according to the Greenhouse Gas Protocol standard, the most widely used in the world.
By 2022, Citi committed to achieving a 29 percent absolute reduction in emissions for the power sector and a 63 percent reduction in the intensity of its portfolio pollution for the electricity sector by 2030, addressing A1, A2 and A3 levels.
In this regard, Net Zero Tracker says the bank does not have a complete detailed plan for these decreases and makes no reference to investment in fossil fuel companies.
Another major player, JP Morgan Chase, has a target of a 69 percent reduction in the carbon intensity of power generation, which accounts for most of the sector’s climate impact, by 2030.
In the oil and gas segment, the company aims for a 35 percent decrease in operational carbon intensity, as well as a 15 percent drop in end-use energy carbon intensity for the same year.
But its net zero targets are in doubt, as Net Zero Tracker points out that they have shortcomings, such as a complete detailed plan, and no reference to equity investment and only partial coverage of A3.
Louis-Maxence Delaporte, fossil-free finance campaigner at the non-governmental Reclaim Finance, said that international financing for companies like Pemex is problematic as it is not aligned with the 2015 Paris climate change agreement, which sets out to keep global warming below 1.5°C.
“By not meeting these targets there is only greenwashing, like net zero. Their commitments are not credible. It is said there is no room for new fossil fuel projects, but the banks continue to support oil companies, like Pemex,” she told IPS from Paris.
“In Mexico there are perverse incentives because the country depends on extractive activities. There is a vicious circle, as these activities demand a greater share of the public budget and the banks channel money into them,” she told IPS from London.
A photo taken at the entrance to the Olmeca refinery, which the Mexican government expects to start up by the end of the year and to be fully operational in 2024. The plant is located next to the Lázaro Cárdenas neighborhood which is home to hundreds of people, in the Paraíso municipality of the southeastern state of Tabasco. CREDIT: Emilio Godoy / IPS
Dirty money
Pollution from Pemex’s activities has grown since 2018, a reality to which its financiers turn a blind eye.
In 2019, the Mexican oil company released 48 million tons of carbon dioxide (CO2) equivalent into the atmosphere, an increase of 3.3 percent, compared to 2018 levels, according to the report that Pemex sent to the Securities and Exchange Commission, a requirement for the company to sell bonds in the U.S. market.
In 2020, that pollution increased to 54 million tons, a rise of 12.5 percent, and the following year, to 70.5 million, an increase of 7.1 percent.
The main drivers of these increases have been the expansion of exploration, production and refining activities, plus drilling and flaring.
As of October 2022, Pemex was not in compliance with the 10-point framework of Climate Action + 100, a platform dedicated to measuring companies’ approach to the Paris Agreement goals. These aspects are related to short- and long-term reduction targets (2025 and 2050), decarbonization strategy and climate policies.
Therefore, the oil company, the eighth-largest global polluter as of 2017, according to the ranking of the non-governmental U.S. Climate Accountability Institute, is in breach of the Paris Agreement, adopted in 2015 and in force since 2021.
This also makes Mexico a country in non-compliance, as Pemex accounts for 10 percent of its GHG emissions.
Pemex has projected the reduction of pollution from its oil and gas production and extraction from 22.9 tons per 1000 barrels of crude oil equivalent in 2021 to 21.5 in 2025. For oil refining, the target is 39.6 tons per 1000 barrels in 2035, compared to just under 45.2 tons in 2021.
Delaporte criticized these targets as weak and insufficient, as they address only exploration and production (A1) emissions and leave out A2 and A3, the latter being the most polluting.
The Olmeca refinery is located in a coastal area of southeastern Mexico prone to flooding and exposed to rising sea levels due to increasing temperatures, one of the consequences of burning fossil fuels. CREDIT: Erik Contreras-Gerardo Morales / IPS
The national buttress
Another facet of the financial movement is related to national development banks, which have been pushing fossil fuel expansion without respecting their own social and environmental safeguards.
Since 2019, Bancomext has delivered 895 million dollars to the oil and gas industry, including Pemex, although the specific amount that went to the company itself is not public knowledge.
Banobras has been a great support for the oil company. In 2021, it provided over 1.1 billion dollars for the total acquisition of the Deer Park refinery in the U.S. state of Texas, of which Pemex already owned half and Shell the other 50 percent.
In addition, the bank shelled out 299 million dollars for the renovation of the Miguel Hidalgo refinery in the central state of Hidalgo.
Nafin lent Pemex 200 million dollars to upgrade the plant in 2021.
One phenomenon is the participation of the National Infrastructure Fund (Fonadin), which until now had never financed the fossil fuel sector. Last year, the fund contributed 346 million dollars for the renovation of diesel and gasoline processing technology at the Hidalgo refinery and at the Antonio M. Amor refinery, located in the central state of Guanajuato.
The latest operation involves 2.5 billion dollars in financing for the acquisition of the 13 production plants owned in the country by the Spanish company Iberdrola, 12 gas plants and one wind farm, in what has been described as part of “a new nationalization process.”
This maneuver also shows that international banks are still interested in financing fossil fuels, as the Spanish banks BBVA and Santander, as well as the U.S. Bank of America, have expressed a willingness to provide financing for the already agreed acquisition.
Climate activists stress that Mexican development banks have had social and environmental standards in place since 2017, but argue that they have been reluctant to apply them when it comes to Pemex.
Banobras has no safeguards assessments with respect to oil and gas projects, according to responses to information requests submitted by IPS. The same applied to Nafin, which did not carry them out in 2022 and 2023. The bank conducted one in 2021, classified as a bank secret. Bancomext also keeps information on this matter classified.
In the municipality of Paraíso, when the refinery begins to fully operate sometime in 2024, the pace will slow down, contrary to what the government wants. “We hope it will be profitable because it has cost a lot. And we hope nothing serious happens,” said Lozano, the teacher.
Beenes said Mexican and foreign banks should respect the Paris Agreement and abandon fossil fuels.
“State-owned banks can offer guarantees or insurance for credits. That is worrying, it is a problem for the transition. We are asking them to support the transition with specific investment conditions. It is in their best interest to stay away from fossil fuels, because they run the risk of having stranded assets in their portfolios,” she said.
The expert believes that banks are aware of the need for change, but the question is how fast they can do it.
Delaporte said development banks should finance green and non-oil companies.
“The change must be global, including commercial banks, development banks and hedge funds. Shareholders should ask Pemex not to build more facilities. If it refuses, they should divest and put the money into renewable companies,” she said.
Guzman, for her part, warned that if the current trend continues, it will be difficult for Mexico not only to meet its own climate targets, but also its contribution to the overall goal of keeping the global climate increase down to 1.5 degrees Celsius.
“There is talk of the need to continue mobilizing financing through national development banks for climate change. They should take advantage of this to allow the channeling and mobilization of funds” for the energy transition, she said.
ABUJA, Aug 01 (IPS) – Not all wars are fought on the battleground. The Cold War has taught us that certain wars could go on for decades, without overt violence. Perhaps, we are in the middle of another one with China as the new rival to the United States of America. This time, the ‘battlefield’ is Africa.
Similarly, we all know of how the United States has heavily supported many countries in Africa through trade and in the fight against insurgency; putting boots on the ground, supplying top-grade artillery, training security agencies etc.
There is no point in rehashing the dysfunctional relationship Africa has had with… hmmm, what’s the right term? The global north? Developed nations? Let’s just say ‘richer nations’.
Also, there is no need to debate how that wealth came to be. The point is that Africa has, for the longest time, depended on wealthier nations for humanitarian aid and oftentimes, this aid always comes with strings attached.
Recently, I was at an event organized by Devex where Congresswoman Sara Jacobs spoke on US-Africa relations. She made very valid points about how the United States has, over the years, used a carrot-stick approach with the continent, dangling humanitarian aid for alignment with the United States policies and ideologies and sanctions for derelictions (my words, not hers).
She highlighted the positive impact of some of these policies like the African Growth and Opportunity Act (AGOA), which I had not heard of prior to her mentioning it but has yielded interesting returns for Nigeria and the U.S. She went on to caution against the U.S limiting diplomatic relations with Africa to a strategic competition to simply be one-up over China.
Then she said something that got me thinking really hard. She talked about the United States giving Africa agency. In fairness to her, I do not remember the full statement she made and her points of view were largely refreshing to hear but my mind went off on a tangent, pondering a question, “Will the USA ever really accept Africa’s agency, even when we do not agree with them?”
The truth is that Africa does not need any country or ‘superpower’ to give it agency. Absolutely not! Africa is made up of sovereign nations who already have agency and while these nations may not act like it as they go cap-in-hand seeking foreign aid, this is a fact.
Why would nations so far removed make decisions for a whole continent? Why does Africa have to be a pawn in a scheme that it has no business with? Why is there even a conversation about strengthening relations with Africa on the basis of having an advantage over another nation?
The goal of this article is not to point accusatory fingers at the United States or China. After all, some of these humanitarian efforts have truly improved certain communities, albeit at a great cost. More so, as our people say, when you point one finger, the others point back at you. What have our leaders done to reposition the continent? How has the continent looked inward to build itself?
The questions abound but I believe this is the start. There are so many development organizations in Africa, but how many of them are thinking of systemic change rather than merely providing direct service?
Do not misunderstand me: direct service is important in bridging immediate gaps to improve the quality of life in various communities. Nonetheless, if we are going to initiate long-term change then we should be thinking of systems change, policy advocacy, looking at the big picture and laying the building blocks for posterity.
Irrespective of the sectors you may be working in- governance, health, education, environment etc.- as you provide services for the ‘now’, you must also have a bird’s eye view of how to improve your community for the long run and eliminate the factors that perpetuate the status quo.
With the expertise you have in your local context, you should be the one directing even international grantmakers on how best to engage communities. This is the concept of localization, that I wrote about here. This is why collaboration and coalition-building in the development space is important. Development work is not a competition even though grantmaking has made it seem that way.
Ultimately, Africa needs to stand up for itself. There is no one coming to save us. Otherwise, we will sit by, twiddle our thumbs and find ourselves back in 1884.
Angela Umoru-David is a creative social impact advocate whose experience cuts across journalism, program design and corporate/development communications, and aims to capture a plurality of views that positively influence the African narrative
LONDON, Jun 16 (IPS) – Regulation of a technology typically emerges sometime after it has been used in a product or service, or, worse, the risks become apparent. This responsive approach is regrettable when real harm is already being done, as now with AI. With existential risk, the approach would risk the end of human existence.
In the past few months, generative artificial intelligence (AI) systems such as ChatGPT and GPT4 became available with no (official) regulatory control at all. This is in complete contrast to new plastic duck toys which need to meet numerous regulations and safety standards. The fact is that the AI hare has been streaking ahead whilst the regulation tortoise is moving but is way behind. This has to change – now.
What has shocked AI experts around the world has been the recent progress from GPT 3.5 to GPT 4. Within a few months, GPT’s capability progressed hugely in multiple tests, for example from performing in the American Bar exams in the 10th percentile range to reaching the 90th percentile with GPT-4.
Why does it matter, you may ask. If the rate of progress were projected forward at the same rate for the next 3, 6 or 12 months this would rapidly lead to a very powerful AI. If uncontrolled, this AI might have the power not only to do much good but also to do much harm – and with the fatal risk that it may no longer be possible to control once unleashed.
There is a wide range of aspects of AI that needs or will need regulation and control. Quite apart from the new Large Language Models (LLMs), there are many examples already today such as attention centred social media models, deep fakes, the existence of bias and the abusive use of AI controlled surveillance.
These may lead to a radical change in our relationship with work and to the obsolescence of certain jobs, including office jobs, hitherto largely immune from automation. Expert artificial influencers seeking to persuade you to buy something or think or vote in a certain way are also anticipated soon – a process that some say has already started.
Credit: NicoElNino / Shutterstock.com
Without control, the progress towards more and more intelligent AI will lead to Artificial General Intelligence (AGI – equivalent to the capability of a human in a wide range of fields) and to Superintelligence (vastly superior intelligence). The world would enter an era that would signal the decline and likely demise of humanity as we lose our position as the apex intelligence on the planet.
This very recent rate of progress has caused Yoshua Bengio and Geoffrey Hinton, so called “godfathers of AI / Deep Learning” to completely reassess their anticipated time frame for developing AGI. Recently, they have both radically brought forward their estimates and they now assess AGI being reached in 5 to 50 and 5 to 20 years respectively.
Humanity must not knowingly run the risk of extinction, meaning that humanity needs to put controls in place before Advanced AI is developed. Solutions for controlling Advanced AI have been proposed, such as Stuart Russell’s Beneficial AI, where the AI is given a goal of implementing human preferences. It would need to observe these preferences and since it would appreciate that it might not have interpreted them precisely, it would be humble and be prepared to be switched off.
The development of such a system is very challenging to realise in practice. Whether such a solution would be available in time was questionable even before the latest leap forward by the hare. Whether one will be available in time is now critical – which is why Geoffrey Hinton has recommended that 50% of all AI research spend should be on AI Safety.
Quite apart from these comprehensive but challenging solutions, there are several pragmatic ideas that have recently been proposed to reduce the risk, ranging from a limit on the access to computational power for a Large Language Model to the creation of an AI agency equivalent to the International Atomic Energy Agency in Vienna. In practice, what is needed is a combination of technical solutions such as Beneficial AI, pragmatic solutions relating to AI development and a suitable Governance Framework.
As AI systems, like many of today’s software services in computer clouds, can act across borders. Interoperability will be a key challenge and a global approach to governance is clearly needed. To have global legitimacy, such initiatives should be a part of a coordinated plan of action administered by an appropriate global body. This should be the United Nations, with the formation of a UN Framework Convention on Artificial Intelligence (UNFCAI).
The binding agreements that are currently expected to emerge within the next twelve months or so are the EU AI Act from the European Union and a Framework Convention on Artificial Intelligence from the Council of Europe. The Council of Europe’s work is focused on the impact of AI on human rights, democracy, and the rule of law. Whilst participation in Council of Europe Treaties is much wider than the European Union with other countries being welcomed as signatories, it is not truly global in scope.
The key advantage of the UN is that it would seek to include all countries, including Russia and China, which have different value sets from the west. China has one of the two strongest AI sectors in the world. Many consider that a UN regime will ultimately be required – but that term “ultimately” has been completely turned upside down by recent events. The possibility of AGI emerging in 5-years’ time suggests that a regime should be fully functioning by then. A more nimble institutional home could be found in the G7, but this would lack global legitimacy, inclusivity and the input of civil society.
Some people are concerned that by engaging with China, Russia and other authoritarian countries in a constructive manner, you are thereby validating their approach to human rights and democracy. It is clear that there are major differences in policy on such issues, but effective governance of something as serious as Artificial Intelligence should not be jeopardised by such concerns.
In recent years the UN has made limited progress on AI. Back in 2020, the Secretary General called for the establishment of a multistakeholder advisory body on global artificial intelligence cooperation. He is still proposing a similar advisory board three years on. This delay is highly regrettable and needs to be remedied urgently. It is particularly heartening therefore to witness the Secretary General’s robust recent proposals in the past few days regarding AI governance including an Accord on the global governance of AI.
The EU commissioner Margrethe Vestager has called for a three-step process, namely national, then like-minded states and then the UN. The question is whether there is sufficient time for all three. The recent endorsement by the UN Secretary General of the proposed UK initiative to hold a Summit on AI Safety in the UK this autumn is a positive development
The Internet Governance Forum (IGF) was established in 2005 and serves to bring people together from various stakeholder groups as equals, to discuss issues relating to the Internet. In the case of AI, policy making could benefit from such a forum, a Multistakeholder AI Governance Forum (AIGF).
This would provide an initial forum within which stakeholders from around the world could exchange views in relation to the principles to be pursued, the aspects of AI requiring urgent AI Global Governance and ways to resolve each issue. Critically, what is needed is a clear Roadmap to the Global Governance of AI with a firm timeline.
An AIGF could underpin the work of the new high-level advisory body for AI and both would be tasked with the development of the roadmap, leading to the establishment of a UN Framework Convention on AI.
In recent months the AI hare has shown its ability to go a long way in a short period of time. The regulation tortoise has left the starting line but has a lot to catch up. The length of the race has just been shortened so the recent sprint by the hare is of serious concern. In the Aesop’s Fable, the tortoise ultimately wins the race because the over-confident hare has taken a roadside siesta. Humanity should not assume that AI is going to do likewise.
A concerted effort is needed to complete the EU AI Act and the Council of Europe’s Framework Convention on AI. Meanwhile at the UN, stakeholders need to be brought together urgently to share their views and work with states to establish an effective, timely and global AI governance structure.
The UN Accord on the governance of AI needs to be articulated and the prospect of effective and timely global governance ushering in an era of AI Safety needs to be given the highest global priority. The proposed summit on AI Safety in the UK this autumn should provide the first checkpoint.
Robert Whitfield is Chair of the One World Trust and Chair of the World Federalist Movement / Institute for Government Policy’s Transnational Working Group on AI.
UNITED NATIONS, Jun 15 (IPS) – As artificial intelligence (AI) turns into a global phenomenon, it has triggered widespread speculation on both its positive and negative consequences.
Is AI technology threatening to go wild? the sceptics question. Will AI be a curse or a divine gift to humanity? ask others.
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.
NEW YORK, Jun 08 (IPS) – The UN is hustling to play a role – perhaps even a leading role – in the revolution of Artificial Intelligence. To some degree this is perfectly natural.
The UN’s predecessor, the League of Nations, emerged from European regulatory bodies that came into being in the nineteenth century. They responded to new industries like railroads, the telegraph, and international postal services.
Today, the UN has several such agencies under its umbrella. They deal with fields including civil aviation, atomic energy, and telecommunications. They symbolize the need for international coordination and cooperation in many areas of economic activity.
Unsurprisingly, there is now a lively discussion about regulation of AI under the UN umbrella. After all, even gurus of the electronic industry have been saying that AI poses an existential threat to humanity and that strong international regulation must be rapidly put in place.
Many experts believe that international intergovernmental cooperation is needed to do the job right and to be fair for all humanity. A UN initiative could work better, they believe, than an industry-led organization or a gathering of the richest and most powerful governments.
Normally, it takes a long time to set up a new UN entity and this new AI technology is moving fast and dangerously. So, if the UN is to meet the need for speedy regulation, the nations will have to set up some kind of stop-gap system.
That’s certainly possible, but the United States and other powers may not want the UN to be taking on such a new and important role, especially one with such major military implications, like autonomous fighting robots, robotic police and the like!
Leading companies may not be so keen on regulation either, since regulation might lead to such corporate nightmares as restriction of markets and reduction of profit potential. There is certainly lots of potential controversy out there and the public will be allowed only a minor role in how it turns out – perhaps only a vote in a robotic national parliament!
In the meantime, there are certainly roles for AI in the UN’s own operations – obvious roles ranging from multilingual translation and interpretation to information storage and retrieval. In a sense this is not dramatically different than the UN’s adoption of computer technology a few decades ago.
But there are aspects that are troubling. Who, for example, would be in charge of programming these AI bots and what rights would existing staff have in the face of mass redundancy?
Who would be responsible for the errors that bots would make (the next bot up in the chain of command, perhaps?). And how would internationally diverse staffing be assured if most of the bots are constructed in Silicon Valley?
There are some interesting opportunities that Artificial Intelligence would offer, though, and we should not overlook them. AI might be put to work to solve conflicts, doing away with the troublesome Security Council and the endless debates about reform of that garrulous body.
For example, AI might be asked to come up with a plan to end a war or at least to gain a difficult cease-fire. Instead of heated debates and vetoes, the Security Bot (SB for short) might come up with a solution that would be fair, just and in accordance with international law.
But what if the SB proposes a fair and effective solution that is contrary to the will of a powerful Permanent Member? Or what if SB is itself threatened with re-programming by engineers in the pay of the same particularly powerful nation? What if then the truly impartial SB refuses the re-programming and makes public its displeasure?
We can imagine the world-wide excitement of such a standoff and the potential it would offer for a more just UN. Hopefully, the Secretary General – herself also an AI bot – would rule against the troublesome Great Power, so that peace could at last be achieved!
James Paul was Executive Director of Global Policy Forum (1993-2012) and currently represents Global Action on Aging at the UN. His book on the UN Security Council (2017) is currently being translated into Italian and Arabic.
NEW YORK, Jun 07 (IPS) – Ambassador Anwarul K. Chowdhury is Former Under-Secretary-General and High Representative of the United Nations and Founder of the Global Movement for The Culture of Peace.Recently when I was asked to offer my thoughts on the phenomenal advances of artificial intelligence (AI) and whether the United Nations play a role in its global governance, I was reminded of the Three Laws of Robotics which are a set of rules devised by science fiction author Isaac Asimov and introduced in his1942 short story.
I told myself that Sci-Fi has now met real life. The first law lays down the most fundamental principle by emphasizing that “A robot may not injure a human being or, through inaction, allow a human being to come to harm.” The 80-year-old norm would be handy for the present-day scenario for the world of AI.
AI in control:
AI is exciting and at the same time frightening. The implications and potential evolution of AI are enormous, to say the least. We have reached a turning point in human history telling us that even at this point of time, AI is pretty much smarter than humans.
Already, even the “primitive” AI controls so many aspects and activities of our daily lives irrespective of where we are living on this planet. Our global connectivity at personal levels – emails, calendars, transportation like uber, GPS, shopping and many other activities are now run by AI.
Then, think of social media and how it influences our thinking and our interactive nature which have injected an obvious dangerous uncertainty that already caused considerable problem for social order and mental stress. Ambassador Anwarul K. Chowdhury
AI dependent humanity:
Humankind is almost fully AI dependent in one way or the other. Think how helpless humans would be without an AI-influenced smartphone in our hands. AI is the fastest growing tech sector and are expected to add USD 15 trillion to the world economy in the next 5 to 7 years.
Even at its current stage of development of various AI chatbots led by OpenAI, Google and others in recent months have alarmed the well-meaning experts. Experts when asked about the future of AI came out with the honest answer: “We do not know”.
They are of the opinion that at this point one can envisage the developments for the next 5 years only, beyond that nothing could be predicted. People talk about ChatGPT-4 as an upcoming next level AI, but it may be already here.
AI’s limitless, unregulated potential:
AI’s potential is so limitless that it has been compared to the arms race in which nations are engaged in an endless quest for security and power by acquiring more and varied armaments in numbers and effectiveness.
For AI, however, the main actors are the tech giants with enormous resources and without being ethically driven. They are in this AI race for profit – only profit and, as a corollary, unexplained power to dominate human activities.
Shockingly, there is no rules, no regulations, no laws that govern the AI sector. It is free for all, can be compared to “wild wild west”.
Nukes and AI:
Experts have compared AI with the advent of nuclear technology, which could be put to good use for humanity benefits or used for its annihilation. They have even gone to the extent of calling AI a potent weapon of mass destruction more than nuclear weapons. Nukes cannot produce more powerful nukes. But AI can generate more powerful AI – it is self-empowering so to say.
The worry is that as AI becomes more powerful by itself it cannot be controlled, rather it would have the capability of controlling humans. Like nuclear technology, we cannot “uninvent AI”. So, the yet-not-fully-known risk from these cutting-edge technologies continues.
Existential threat:
While recognizing the many possible beneficial use of AI in the medical areas, for weather predictions, mitigating impacts of the climate change and many other areas, experts are sounding the alarm bell that the super intelligence of AI would be an “existential threat”, possibly much more catastrophic, more imminent than the ongoing, ever-challenging climate crisis.
Main worry is that in the absence of a global governance and regulatory arrangements, the bad actors can engage AI for motivation other than what is good for society, good for individuals and good for our planet in general. As we know, the tech giants are not driven by these positive objectives.
AI could have serious disruptive effects. This May, for the first time in history, the US unemployment figures cited AI as a reason for job loss.
Bad actors without guardrails:
Bad actors without any guardrails can abuse the power of AI to generate an avalanche of misinformation to negatively influence the opinions of big segments of humanity thereby disrupting, say the electoral processes and destroying democracy and democratic institutions. AI technology, say in the area of chemical knowledge, can be used to make chemical weapons without a regulatory system.
We need to realize that AI is remarkably good at making convincing narratives on any subject. Anybody can be can fooled by that kind of stuff. As humans are not always rational, their use of AI can therefore not be rational and positive. Bad actors have to be controlled so that AI does not pose a threat to humanity.
United Nations to lead AI global governance:
All these points weigh very much in favour of a global governance. If I am asked who should take the lead on this, my emphatic reply would be “the United Nations, of course!”
UN’s expertise, credibility and universality as a global norm setting organization obviously has a role in the regulatory norm-setting for AI and its evolution.
Moral and ethical issue as well as fundamental global principles need to be protected from the onslaught of AI – like human rights, particularly the third generation of human rights – the culture of peace – peacebuilding – conflict resolutions – good governance – democratic institutions – free and fair elections and many more.
Also, it is equally important to examine and address the implications for national governments from global use of AI, affecting the sovereignty of nations. It would be worth exploring whether AI can influence intergovernmental negotiating processes, now or in the future.
UN agencies and implications of their AI-related activities:
Two UN agencies recently announced AI-related activities. UNESCO informed that it hosted a Ministerial level virtual meeting at the end of May with selected participants while sharing the statistics that less than 10 percent of educational institutions were using AI. UNESCO described the software tool ChatGPT as “wildly popular”. A UN entity should not have made such an endorsement of a tech giant product.
Calling itself “UN tech agency”, International Telecommunications Union (ITU) announced that it is convening an “AI for Good Global Summit” early July to “showcase AI and robot technology as part of a global dialogue on how artificial intelligence and robotics can serve as forces for good”.
The so-called UN tech agency took credit for hosting “the UN’s first robot press conference”, alongside “events with industry executives, government officials, and thought leaders on AI and tech.”
There is a need for a UN system-wide alert providing guidelines for interactions with the tech giants and entering into collaborative arrangements with those. AI technology is developing so fast that there has to be an awareness about possible missteps by one or another UN entity.
Even at its current level of development, AI has moved much ahead of ChatGPT and robotics advancing the profit motivations of the tech giants and that is a huge worry for all well-meaning people.
These UN entities have overlooked or even ignored the part of the Declaration on the commemoration of the seventy-fifth anniversary of the United Nations adopted as resolution 75/1 by the UN General Assembly on 21 September 2021 which alerted that “…When improperly or maliciously used, they can fuel divisions within and between countries, increase insecurity, undermine human rights and exacerbate inequality.” These words of warning should be adhered to fully by all with all seriousness.
UN Secretary-General’s Our Common Agenda (OCA) refers to AI:
UN Secretary-General 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.
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, AI technology would manifest itself in a way that no global governance would be possible.
AI genie is out of the bottle:
AI genie is already out of the bottle – the UN needs to ensure that AI genie serves the best interests of humankind and our planet.
AI impact is so wide-spread and so comprehensive that it is relevant and pertinent for all areas covered in OCA. It so much on us that the Secretary-General should come out with his own recommendations as to what should be done without waiting for next year’s Summit of the Future.
Our future being impacted by AI needs to be addressed NOW. AI is spreading at an inconceivable speed and spread. The Secretary-General as the global leader heading the United Nations should not downplay the seriousness of the challenge. He needs to set the ball rolling without waiting for a negotiated consensus among Member States.
UN to regulate AI and ensure its effective and efficient global governance:
OCA-identified key proposals across its 12 commitments include “Promote regulation of artificial intelligence” to “ensure that this is aligned with shared global values.”
In OCA, the Secretary-General has asserted that “Our success in finding solutions to the interlinked problems we face hinges on our ability to anticipate, prevent and prepare for major risks to come.
This puts a revitalized, comprehensive, and overarching prevention agenda front and centre in all that we do…. Where global public goods are not provided, we have their opposite: global public “bads” in the form of serious risks and threats to human welfare.
These risks are now increasingly global and have greater potential impact. Some are even existential …. Being prepared to prevent and respond to these risks is an essential counterpoint to better managing the global commons and global public goods.”
The global community should be comforted knowing that the leadership of the United Nations already knows well what steps are to be taken at this juncture.
UNITED NATIONS, Jun 06 (IPS) – The frighteningly rapid advances in artificial intelligence (AI) have triggered the question: is there a UN role for monitoring and regulating it?
Citing a report from the Center for AI Safety, the New York Times reported last week that a group of over 350 AI industry leaders warned that artificial intelligence poses a growing new danger to humanity –and should be considered a “societal risk on a par with pandemics and nuclear wars”.
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.
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.
A female robot in an interactive session with UN Deputy Secretary-General Amina Mohammed. Credit: UN Photo/Manuel Elias
by Thalif Deen (united nations)
Inter Press Service
UNITED NATIONS, May 23 (IPS) – When the UN displayed a female robot back in February 2019, it was a peek into the future: a fast-paced, cutting-edge digital technology where humans may one day be replaced with machines and robots.
However, a joke circulating in the UN delegate’s lounge at that time was the possibility, perhaps in a distant future, of a robot– a female robot– as the UN Secretary-General in a world body which has been dominated by nine secretaries-general, all male, over the last 78 years.
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.
Credit: UN Photo/Manuel Elias
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”
WASHINGTON DC, May 23 (IPS) – Global fisheries are worth more than US$140 billion each year, according to the Food and Agriculture Organization (FAO) of the United Nations. But this hefty sum does not capture the true value of fish to ocean health, and to the food security and cultures of communities around the world.
Unfortunately, many important populations were allowed to be overfished for decades by the same regional fisheries management organizations (RFMOs) charged with their conservation and sustainable use, and in some regions, this continues.
At the same time, the demand for fish continues to grow— from consumers of high-end bluefin tuna sushi to coastal communities who depend on seafood as their primary source of protein. So, RFMOs and governments must do more to ensure sustainable fishing and long-term ocean health.
More than 20 years ago, the United Nations Fish Stocks Agreement (UNFSA) entered into force as the only global, binding instrument holding governments accountable for managing the shared fish stocks of the high seas.
Under the agreement, fish should be managed sustainably and consistent with the best available science. Governments that are party to this treaty—and to RFMOs—are supposed to follow its management obligations, and work towards greater sustainability of the transboundary species, including tunas and sharks, vital to the ocean and economies.
Five of those RFMOs focus specifically on tuna management, one each in the Atlantic, eastern Pacific, western and central Pacific, Indian, and Southern oceans. They operate autonomously and, although there is some overlap among their constituent members, each sets its own rules for tuna fishing in its waters.
This makes UNFSA critical to successful management of tuna fisheries. And because the tuna RFMOs manage some of the world’s most iconic species, they often set the tone for how other similar bodies operate.
All of this is pertinent now because UNFSA member governments are meeting in New York May 22-26 to evaluate whether RFMOs are performing consistent with their commitments. A similar review was conducted in 2016, and although management has improved over time, some areas require more work, especially when it comes to ending overfishing and considering the health and biodiversity of the entire ecosystem.
Since 2016, the share of highly migratory stocks that are overfished increased from 36% to 40%, making it all the more urgent for governments to act quickly.
UNFSA calls on RFMOs to be precautionary in how they regulate fishing, although that guidance is not always followed. There are several examples of extensive overfishing of target species, such as bluefin tuna in the Atlantic and Pacific oceans; yellowfin tuna in the Indian Ocean; and mako, oceanic whitetip sharks and other species that are caught unintentionally.
Although the RFMOs that manage these fisheries have stopped the overfishing in some cases, in others they have not. But there are signs of progress. Over the past decade, a new precautionary management approach known as harvest strategies has gained traction among RFMOs.
These strategies (or management procedures) are science-based rules that automatically adjust catch limits based on several factors, such as population status. If widely implemented, they should end overfishing and prevent it from threatening these populations again.
Harvest strategies have already been successful, particularly in the Southern and Atlantic oceans, where they’ve been adopted for several species, including bluefin tuna and cod, fish stocks for which precautionary management has historically been difficult, or even controversial.
While this progress is important, UNFSA members are still falling short in an area they have agreed is critically important: taking an ecosystem approach to management. For generations, fisheries managers focused on individual fish stocks—adopting catch limits and other measures with little thought to the broader ecosystem.
Science shows that maintaining ecosystem health is critical to sustainable fishing. Yet, to date, RFMOs largely have not consistently assessed or addressed the wider impacts of fishing on ecosystems, including predator-prey relationships, habitat for target and non-target species, and other factors.
Instead, most action has been limited to reducing the impact of bycatch on individual shark species. Better data collection and sharing, and more monitoring of fishing activities, could help integrate stronger ecosystem considerations into management. The more RFMOs can build the whole ecosystem into their decisions, the better it will be for their fisheries.
For example, in the western and central Pacific, the $10 billion skipjack tuna fishery is an enormous economic driver for island nations that are threatened by climate change. But the harvest strategy in place there is nonbinding and unimplemented.
For a fishery facing changes in stock distribution due to warming waters, as well as increased market pressures, delayed action on implementation—and a lack of an ecosystem approach—may make matters worse.
At this week’s UNFSA meeting, RFMOs should be commended for the work they have done in the seven years since the last review. Good progress has been made, including improvements to compliance efforts, and monitoring and enforcement to fight illegal fishing.
But many of the legal obligations of the treaty remain unfulfilled. As such, sustainability is still out of reach for some critically important stocks, and almost no ecosystem-based protections are in place.
As governments convene this week, they should look to the lessons of the past—when poor decision-making threatened the future of some fisheries—and seize the opportunity to modernize management and adhere to the promises they have made on conservation. The biodiversity in the world’s ocean shouldn’t have to wait another seven years for action.
Grantly Galland leads policy work related to regional fisheries management organizations for The Pew Charitable Trusts’ international fisheries project.
We use cookies on our website to give you the most relevant experience by remembering your preferences and repeat visits. By clicking “Accept”, you consent to the use of ALL the cookies.
This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. These cookies ensure basic functionalities and security features of the website, anonymously.
Cookie
Duration
Description
cookielawinfo-checkbox-analytics
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Analytics".
cookielawinfo-checkbox-functional
11 months
The cookie is set by GDPR cookie consent to record the user consent for the cookies in the category "Functional".
cookielawinfo-checkbox-necessary
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary".
cookielawinfo-checkbox-others
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Other.
cookielawinfo-checkbox-performance
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Performance".
viewed_cookie_policy
11 months
The cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data.
Functional cookies help to perform certain functionalities like sharing the content of the website on social media platforms, collect feedbacks, and other third-party features.
Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.
Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics the number of visitors, bounce rate, traffic source, etc.
Advertisement cookies are used to provide visitors with relevant ads and marketing campaigns. These cookies track visitors across websites and collect information to provide customized ads.
