Posts

CLAIRE – a new European confederation for AI research

While the world wakes up to the huge potential impacts of AI in the future, how will national worries about other nations gaining ‘AI Supremacy’ effect development?
Especially development in AI Ethics & safety?

Claire-AI is a new European confederation.
Self described as

CONFEDERATION OF LABORATORIES FOR ARTIFICIAL INTELLIGENCE RESEARCH IN EUROPE – Excellence across all of AI. For all of Europe. With a Human-Centred Focus.
Liking the ‘human-centered’ focus (albeit a bit vague), but where is their focus on ethics?

A Competitive Vision

Their vision admits of a fear that Europe may be the losers in a race to achieve AI Supremacy, and this is worrisome – seen as a race between tribes, AI development could be a race to the bottom of the barrel of AI safety and alignment.

In the United States of America, huge investments in AI are made by the private sector. In 2017, the Canadian government started making major investments in AI research, focusing mostly on existing strength in deep learning. In 2017, China released its Next Generation AI Development Plan, with the explicit goal of attaining AI supremacy by 2030.

However, in terms of investment in talent, research, technology and innovation in AI, Europe lags far behind its competitors. As a result, the EU and associated countries are increasingly losing talent to academia and industry elsewhere. Europe needs to play a key role in shaping how AI changes the world, and, of course, benefit from the results of AI research. The reason is obvious: AI is crucial for meeting Europe’s needs to address complex challenges as well as for positioning Europe and its nations in the global market.

Also the FAQ page reflects this sentiment:

Why does Europe have to act, and act quickly? There would be serious economic consequences if Europe were to fall behind in AI technology, along with a brain-drain that already draws AI talent away from Europe, to countries that have placed a high priority on AI research. The more momentum this brain-drain develops, the harder it will be to reverse. There is also a risk of increasing dependence on AI technology developed elsewhere, which would bring economic disadvantages, lack of transparency and broad use of AI technology that is not well aligned with European values.
What are ‘European Values’? They aren’t spelt out very specifically – but I suspect much like other nations, they want whats best for the nation economically, and with regard to security.

Claire-AI’s vision of Ethics

There is mention of ‘humane’ AI – but this is not described in detail anywhere on their site.
What is meant by ‘human-centred’?

Human-centred AI is strongly based on human values and judgement. It is designed to complement rather than replace human intelligence. Human-centred AI is transparent, explainable, fair (i.e., free from hidden bias), and socially compatible. Is developed and deployed based on careful consideration of the disruptions AI technology can cause.
Many AI experts are convinced that the combination of learning and reasoning techniques will enable the next leap forward in AI; it also provides the basis for reliable, trustworthy, safe AI.

So, what are their goals?

What are we trying to achieve? Our main goal is to strengthen AI research and innovation in Europe.

Summing up

Strong AI when achieved, will be extremely powerful because intelligence is powerful. Over the last few years the interest in AI has ramped up significantly – with new companies and initiatives sprouting like mushrooms. The more competitiveness and economy of attention focusing on AI development in a race dynamic to achieve ‘AI supremacy’ will likely result in Strong AI being achieved sooner than previously expected by experts, as well as motivation to precautionary measures.
This race dynamic is good reason to focus on researching how we should think about the strategy to cope with global coordination problems in AI safety as well as its possible impact on an intelligence explosion.

The race dynamic could spur projects to move faster toward superintelligence while reducing investment in solving the control problem. Additional detrimental effects of the race dynamic are also possible, such as direct hostilities between competitors. Suppose that two nations are racing to develop the first superintelligence, and that one of them is seen to be pulling ahead. In a winner-takes-all situation, a lagging project might be tempted to launch a desperate strike against its rival rather than passively await defeat. Anticipating this possibility, the frontrunner might be tempted to strike preemptively. If the antagonists are powerful states, the clash could be bloody. (A “surgical strike” against the rival’s AI project might risk triggering a larger confrontation and might in any case not be feasible if the host country has taken precautions.)Nick Bostrom - Superintelligence: Paths, Dangers, Strategies

Humanity has a history of falling into Hobbsian Traps – since a first mover advantage of Strong AI could be overpowered compared to other economic focuses, a race to achieve such a powerful general purpose optimiser as Strong AI, could result in military arms races.

As with any general-purpose technology, it is possible to identify concerns around particular applications. It has been argued, for example, that military applications of AI, including lethal autonomous weapons, might incite new arms races, or lower the threshold for nations to go to war, or give terrorists and assassins new tools for violence.Nick Bostrom - Strategic Implications of Openness in AI Development

What could be done to mitigate against an AI arms race?

Website: https://claire-ai.org