This research report addresses the absence of an actionable definition for Loss of Control (LoC) in AI systems by developing a novel taxonomy and preparedness framework. Despite increasing policy and research attention, existing LoC definitions vary significantly in scope and timeline, hindering effective LoC assessment and mitigation. To address this issue, we draw from an extensive literature review and propose a graded LoC taxonomy, based on the metrics of severity and persistence, that distinguishes between Deviation, Bounded LoC, and Strict LoC. We model pathways toward a societal state of vulnerability in which sufficiently advanced AI systems have acquired or could acquire the means to cause Bounded or Strict LoC once a catalyst, either misalignment or pure malfunction, materializes. We argue that this state becomes increasingly likely over time, absent strategic intervention, and propose a strategy to avoid reaching a state of vulnerability. Rather than focusing solely on intervening on AI capabilities and propensities potentially relevant for LoC or on preventing potential catalysts, we introduce a complementary framework that emphasizes three extrinsic factors: Deployment context, Affordances, and Permissions (the DAP framework). Compared to work on intrinsic factors and catalysts, this framework has the unfair advantage of being actionable today. Finally, we put forward a plan to maintain preparedness and prevent the occurrence of LoC outcomes should a state of societal vulnerability be reached, focusing on governance measures (threat modeling, deployment policies, emergency response) and technical controls (pre-deployment testing, control measures, monitoring) that could maintain a condition of perennial suspension.

As artificial intelligence (AI) research reaches new peaks, more and more AI systems are being implemented, applied, and deployed worldwide. Further integration of such systems with human societies demands a thorough consideration of their consequences and effects. The inherent property of most, if not all, AI systems is to act with an unprecedented level of autonomy, often in settings where its actions might directly affect human beings. The growing field of Value Alignment (VA) aims to explicitly study the values pursued and exhibited by AI agents and make sure that they correspond to human values. Motivating examples of VA often consider the long-term and potentially existential threats posed by powerful, superintelligent AI agents with misaligned values [Russell, 2022a]. Not less pertinent are the short-term threats of more mundane, highly specialized AI systems, employed in particular in control settings, becoming misaligned. A prominent case where a potential misalignment is particularly dangerous is given by systems where humans voluntarily cede control of a system to algorithms. Examples of such systems abound: self-driving cars, where the driver cedes control of their vehicle [Haboucha et al., 2017]; recommender systems and content algorithms [Carissimo et al., 2023], where the user cedes some control over their access to information; traffic control systems, where drivers cede control of traffic flow coordination [Korecki and Helbing, 2022], are all examples of systems where AI is a control method of choice or is in the process of becoming one

In case you have been somewhere else in the solar system, here is a brief AI news update. My apologies if it sounds like the opening paragraph of a bad science fiction novel. On 14 March 2023, OpenAI, a company based in San Francisco and part owned by Microsoft, released an AI system called GPT-4. On 22 March, a report by a distinguished group of researchers at Microsoft, including two members of the US National Academies, claimed that GPT-4 exhibits "sparks of artificial general intelligence". On 29 March, the Future of Life Institute, a non-profit headed by the MIT physics professor Max Tegmark, released an open letter asking for a pause on "giant AI experiments". It has been signed by well-known figures such as Tesla's CEO, Elon Musk, Apple's co-founder Steve Wozniak, and the Turing award-winner Yoshua Bengio, as well as hundreds of prominent AI researchers.

Prominent'experts' recently released an open statement for a'pause' to developing AI citing ambiguous risks and yet to be proven'dangers'. I am surprised that exceptionally intelligent persons such as Yoshua Bengio, Stuart Russell, Elon Musk, Steve Wozniak, Yuval Noah Harari and others have signed on this. If they had that option, I may have joined in too – with caveats as described below. Before expressing disagreement with parts of this letter, I agree with these set of experts that AI could be misused or abused, and present future dangers. Artificial Intelligence (AI) is of itself not evil or good, nor safe or dangerous. It would have been better to exclude the "PAUSE" as an emphatic part of the open letter / solution.

In March 2016, to much fanfare, AlphaGo beat Go world champion Lee Sedol, convincingly, in a 5 game match, 4 to 1. Computers have only gotten faster since then; one might have thought that the matter was settled. And of course computers have only gotten faster ever since. And the human that won wasn't even a professional Go player, let along a World Champion, just a strong amateur named Kellin Pelrine. And the match wasn't even close; Pelrine beat a top AI system 14 games to 1, in a 15 match series. Almost seven years to the day after AlphaGo beat Sedol.

AI is a phrase thrown about a lot nowadays, maybe a little too much. But do you even know what it means, you've probably used it many times before without even realizing it, or even that AI defying humans isn't what we should be worrying about? Well, according to Cambridge dictionary, AI "is the study of how to make computers that have some of the qualities of the human mind" Basically giving the computer the ability to think, creepy, I know. Well, now that we've got the basic picture of what it means, what is it being used for? This may or may not come as a surprise to you, but you were very likely led to this page through AI.

I think the film is great! I've recommended to my friends and colleagues in IT to watch it as soon as they get a chance. I think currently in society the risks of AI (more specifically Artifical General Intelligence and Artificial Super Intelligence) are not understood by most people, even most IT and AI researchers, as the main focus (and main budgets) goes to ANI (narrow AI) that already makes is way into our society and has a lot of (potential) benefits in various fields including medicine (e.g. It's brilliant that in this film Keir Dullea looks back on "2001" and his interactions with HAL. For most people outside the field of AI, HAL is still the most recognizable superintelligent AI computer.

The lectures will examine what Russell will argue is the most profound change in human history as the world becomes increasingly reliant on super-powerful AI. Examining the impact of AI on jobs, military conflict and human behaviour, Russell will argue that our current approach to AI is wrong and that if we continue down this path, we will have less and less control over AI at the same time as it has an increasing impact on our lives. How can we ensure machines do the right thing? The lectures will suggest a way forward based on a new model for AI, one based on machines that learn about and defer to human preferences. The series of lectures will be held in four locations across the UK; Newcastle, Edinburgh, Manchester and London and will be broadcast on Radio 4 and the World Service as well as available on BBC Sounds.

Ever since Garry Kasparov lost his second chess match against IBM's Deep Blue in 1997, the writing has been on the wall for humanity. Or so some like to think. Advances in artificial intelligence will lead – by some estimates, in only a few decades – to the development of superintelligent, sentient machines. Movies from The Terminator to The Matrix have portrayed this prospect as rather undesirable. But is this anything more than yet another sci-fi "Project Fear"?

The technologies referred to as "artificial intelligence" or "AI" are more momentous than most people realize. Their impact will be at least equal to, and may well exceed, that of electricity, the computer, and the internet. What's more, their impact will be massive and rapid, faster than what the internet has wrought in the past thirty years. Much of it will be wondrous, giving sight to the blind and enabling self-driving vehicles, for example, but AI-engendered technology may also devastate job rolls, enable an all- encompassing surveillance state, and provoke social upheavals yet unforeseen. The time we have to understand this fast-moving technology and establish principles for its governance is very short. The term "AI" was coined by a computer scientist in 1956.