A dystopian future for cybersecurity is presented by all good apocalyptic sci-fi films and books. Beyond the inclusion of open AI in many vendor slide decks in a way of positioning next-generation technology and a more automated, advanced, approach to technology, the concept is now becoming more mainstream. This advancement from a glorified Google search has sparked the interest of students seeking to expedite essay responses without consuming the time or need to read source materials, followed by teachers seeking to similarly automate marking. Anyone who has been frustrated by a website chatbot while attempting to get help or an answer to a vaguely complex question found solace in conversing with a computer. Without a doubt, it's opened up a world of possibilities for AI to influence how we interact with technology daily as individuals, rather than just being a mysterious black box powering systems ranging from weather forecasting to space rockets. Inevitably, the potential impact on cyber security will quickly become a key topic of discussion on both sides.

The increasing capabilities of artificial intelligence (AI) systems make it ever more important that we interpret their internals to ensure that their intentions are aligned with human values. Yet there is reason to believe that misaligned artificial intelligence will have a convergent instrumental incentive to make its thoughts difficult for us to interpret. In this article, I discuss many ways that a capable AI might circumvent scalable interpretability methods and suggest a framework for thinking about these potential future risks. I'm grateful to David Lindner, Evan R. Murphy, Alex Lintz, Sid Black, Kyle McDonnell, Laria Reynolds, Adam Shimi, and Daniel Braun whose comments greatly improved earlier drafts of this article. The article's weaknesses are mine, but many of its strengths are due to their contributions. Additionally, this article benefited from the prior work of many authors, but especially: Evan Hubinger, Peter Barnett, Adam Shimi, Neel Nanda, Evan R. Murphy, Eliezer Yudkowsky, Chris Olah. I collected several of the potential circumvention methods from their work. Part of this work was carried out while at Conjecture. The original post on which this paper was based can be found here.

Language is not only used to transmit neutral information; we often seek to persuade by arguing in favor of a particular view. Persuasion raises a number of challenges for classical accounts of belief updating, as information cannot be taken at face value. How should listeners account for a speaker's "hidden agenda" when incorporating new information? Here, we extend recent probabilistic models of recursive social reasoning to allow for persuasive goals and show that our model provides a pragmatic account for why weakly favorable arguments may backfire, a phenomenon known as the weak evidence effect. Critically, this model predicts a systematic relationship between belief updates and expectations about the information source: weak evidence should only backfire when speakers are expected to act under persuasive goals and prefer the strongest evidence. We introduce a simple experimental paradigm called the Stick Contest to measure the extent to which the weak evidence effect depends on speaker expectations, and show that a pragmatic listener model accounts for the empirical data better than alternative models. Our findings suggest further avenues for rational models of social reasoning to illuminate classical decision-making phenomena.

Computer engineers and radiologists at Duke University have developed an artificial intelligence platform to analyze potentially cancerous lesions in mammography scans to determine if a patient should receive an invasive biopsy. But unlike its many predecessors, this algorithm is interpretable, meaning it shows physicians exactly how it came to its conclusions. The researchers trained the AI to locate and evaluate lesions just like an actual radiologist would be trained, rather than allowing it to freely develop its own procedures, giving it several advantages over its "black box" counterparts. It could make for a useful training platform to teach students how to read mammography images. It could also help physicians in sparsely populated regions around the world who do not regularly read mammography scans make better health care decisions.

Computer engineers and radiologists at Duke University have developed an artificial intelligence platform to analyze potentially cancerous lesions in mammography scans to determine if a patient should receive an invasive biopsy. But unlike its many predecessors, this algorithm is interpretable, meaning it shows physicians exactly how it came to its conclusions. The researchers trained the AI to locate and evaluate lesions just like an actual radiologist would be trained, rather than allowing it to freely develop its own procedures, giving it several advantages over its "black box" counterparts. It could make for a useful training platform to teach students how to read mammography images. It could also help physicians in sparsely populated regions around the world who do not regularly read mammography scans make better health care decisions.

Over the next few years, artificial intelligence will reshape our homes, workplaces, and society at large, touching virtually every aspect of how we work and live. And yet, according to the World Economic Forum's 2020 Global Gender Gap Report, just 26% of professionals in this flourishing field are women. At IBM -- where our Watson technology is helping companies unlock the value of their data in entirely new, profound ways -- we believe that growing the percentage of women in the field is crucial to developing high-quality, unbiased AI. According to the recent IBM Global Women in AI Study conducted by Morning Consult, the vast majority of AI professionals believe the field has become more diverse over the past few years, and that this change is having a positive impact on AI technology. Among those who respond that the field has not become more diverse, 74% believe that it must, if the industry is to achieve its potential.

The past 20 years have seen remarkable advances in the mining industry, particularly in mineral exploration technologies with vast volumes of data generated from geologic, geophysical, geochemical, satellite and other surveying techniques. However, the abundance of data has not necessarily translated into the discovery of new deposits, according to Colin Barnett, co-founder of BW Mining, a Boulder, Colorado-based data mining and mineral exploration company. "One of the problems we're facing in exploration is the huge increase in the amounts of data we have to look at," said Barnett, in his presentation at the Managing and exploring big data through artificial intelligence and machine learning session at the recent PDAC 2020 convention in Toronto. "And although it's high-quality data, the sheer volume is becoming almost overwhelming for human interpreters, and so we need help in getting to the bottom of it." By integrating hundreds or even thousands of interdependent layers of data, with each layer making its own statistically determined contribution, machine learning offers a solution to the problem of tackling the massive amounts of data generated, and a powerful new tool in the search for mineral deposits. But, in an interview with The Northern Miner, he cautioned that to fully exploit the potential of machine learning in mineral exploration, "prospectors will still need to devote considerable time and effort to the preparation of data before machine learning techniques can add value for companies."

The past 20 years have seen remarkable advances in the mining industry, particularly in mineral exploration technologies with vast volumes of data generated from geologic, geophysical, geochemical, satellite and other surveying techniques. However, the abundance of data has not necessarily translated into the discovery of new deposits, according to Colin Barnett, co-founder of BW Mining, a Boulder, Colorado-based data mining and mineral exploration company. "One of the problems we're facing in exploration is the huge increase in the amounts of data we have to look at," said Barnett, in his presentation at the Managing and exploring big data through artificial intelligence and machine learning session the recent PDAC 2020 convention in Toronto. "And although it's high-quality data, the sheer volume is becoming almost overwhelming for human interpreters, and so we need help in getting to the bottom of it." By integrating hundreds or even thousands of interdependent layers of data, with each layer making its own statistically determined contribution, machine learning offers a solution to the problem of tackling the massive amounts of data generated, and a powerful new tool in the search for mineral deposits. But, in an interview with The Northern Miner, he cautioned that to fully exploit the potential of machine learning in mineral exploration, "prospectors will still need to devote considerable time and effort to the preparation of data before machine learning techniques can add value for companies."

If the industry needed more evidence that IoT devices and applications are taking over the world, Cisco this week said that by 2023 machine-to-machine communications will make up 50% or about 14.7 billion of all networked connections compared to 33% (6.1 billion) in 2018 and 3.1 percent in 2017. The M2M findings were just a part of Cisco's annual forecast of networking trends now called the Cisco Annual Internet Report. The report replaces the Visual Networking Index (VNI) Forecast and looks at everything from 5G and Wi-Fi growth to broadband trends collected from actual network traffic reports and independent analyst forecasts. On the M2M projections, Cisco stated the rapid growth is due to a variety of hot M2M applications, such as smart meters, video surveillance, healthcare monitoring, transportation and package tracking. Traffic is growing faster than the number of connections because the use of video applications on M2M connections is up, as well as other high-bandwidth, low-latency applications such as telemedicine and smart-car navigation systems.

If the industry needed more evidence that IoT devices and applications are taking over the world, Cisco this week said that by 2023 machine-to-machine communications will make up 50% or about 14.7 billion of all networked connections compared to 33% (6.1 billion) in 2018 and 3.1 percent in 2017. The M2M findings were just a part of Cisco's annual forecast of networking trends now called the Cisco Annual Internet Report. The report replaces the Visual Networking Index (VNI) Forecast and looks at everything from 5G and Wi-Fi growth to broadband trends collected from actual network traffic reports and independent analyst forecasts. On the M2M projections, Cisco stated the rapid growth is due to a variety of hot M2M applications, such as smart meters, video surveillance, healthcare monitoring, transportation and package tracking. Traffic is growing faster than the number of connections because the use of video applications on M2M connections is up, as well as other high-bandwidth, low-latency applications such as telemedicine and smart-car navigation systems. It will provide access connections for applications that require greater bandwidth and lower latencies, and that will nurture new innovations not previously possible, wrote Thomas Barnett, Director of Thought Leadership in Cisco Systems' worldwide service provider marketing group in a blog about the report.