Modern large language models (LLMs) like ChatGPT have shown remarkable performance on general language tasks but still struggle on complex reasoning tasks, which drives the research on cognitive behaviors of LLMs to explore human-like problem-solving strategies. Along this direction, one representative strategy is self-reflection, which asks an LLM to refine the solution with the feedback generated by itself iteratively. However, our study shows that such reflection-style methods suffer from the Degeneration-of-Thought (DoT) problem: once the LLM has established confidence in its solutions, it is unable to generate novel thoughts later through reflection even if its initial stance is incorrect. To address the DoT problem, we propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution. Clearly, our MAD framework encourages divergent thinking in LLMs which would be helpful for tasks that require deep levels of contemplation. Experiment results on two challenging datasets, commonsense machine translation and counter-intuitive arithmetic reasoning, demonstrate the effectiveness of our MAD framework. Extensive analyses suggest that the adaptive break of debate and the modest level of "tit for tat" state are required for MAD to obtain good performance. Moreover, we find that LLMs might not be a fair judge if different LLMs are used for agents. Codes: https://github.com/Skytliang/Multi-Agents-Debate

In the 22 years since the publication of her first story collection, Stranger Things Happen, Kelly Link's fiction has crept from the status of cult favorite to something approaching the mainstream--or, rather, the mainstream has crept toward her. Link has never written a novel, only short stories (although a novel has been promised for next year), and her first two books were published by the small press she operates with her husband, Gavin Grant. Furthermore, she writes in genres once regarded as peripheral: fantasy and (occasionally) science fiction. None of this has been considered conducive to literary fame, but times have changed. Novelists ranging from Michael Chabon (a big Link fan) to Kate Atkinson have dissolved many of the boundaries between genre fiction and the mainstream.

For years, racism mandated that Black people and other people of color in the United States use back doors to enter restaurants, movie theaters, and other public places. While these practices have ended, digital back doors may once again make them and others second-class citizens when it comes to health. Digital back doors are technological processes and tools used in health care, such as racially biased algorithms, infrastructural limitations, and dirty data. These unwittingly exacerbate existing health inequities, which the World Health Organization defines as "systematic differences in the health status of different population groups." How are digital back doors created? Their root cause is human made, due to the development and application of technology by some health information technology (health IT) developers and clinicians who fail to fully or explicitly consider equity in health care.

How does Amazon help Alexa understand what people mean and not just what they say? And, we couldn't be talking about Alexa, smart home tech, and AI at a better time. During this week's Amazon Devices event, the company made a host of smart home announcements, including a new batch of Echo smart speakers, which will include Amazon's new custom AZ1 Neural Edge processor. In August this year, I had a chance to speak with Evan Welbourne, senior manager of applied science for Alexa Smart Home at Amazon, about everything from how the company is using AI and ML to improve Alexa's understanding of what people say, Amazon's approach to data privacy, the unique ways people are interacting with Alexa around COVID-19, and where he sees the future of voice and smart tech going in the future. The following is an transcript of our conversation edited for readability. Bill Detwiler: So before we talk about maybe IoT, we talk about Alexa, and kind of what's happening with the COVID pandemic, as people are working more from home, and as they may have questions that they're asking about Alexa, about the pandemic, let's talk about kind of just your role there at Amazon, and what you're doing with Alexa, especially with AI and ML. So I lead machine learning for Alexa Smart Home. And what that sort of means generally is that we try to find ways to use machine learning to make Smart Home more useful and easier to use for everybody that uses smart home. It's always a challenge because we've got the early adopters who are tech savvy, they've been using smart home for years, and that's kind of one customer segment. But we've also got the people who are brand new to smart home these days, people who have no background in smart home, they're just unboxing their first light, they may not be that tech savvy.

The governing regulations over the use of data and who has access to it will change the landscape of how we move about in the online world. Over the past decade, data has emerged as "the new oil" – a driving force behind the world's economy. Because of the sheer amount of data, new concerns for its use have driven innovation within the privacy and security sphere. Let's take a look at how some of these situations will shape what we understand of privacy and how it appears in industry use cases. Widespread consensus with artificial intelligence is that people still don't trust AI.

An important leap for artificial intelligence in recent years is machines' ability to teach themselves, through endless practice, to solve problems, from mastering ancient board games to navigating busy roads. But a few subtle tweaks in the training regime can poison this "reinforcement learning," so that the resulting algorithm responds--like a sleeper agent--to a specified trigger by misbehaving in strange or harmful ways. "In essence, this type of back door gives the attacker some ability to directly control" the algorithm, says Wenchao Li, an assistant professor at Boston University who devised the attack with colleagues. Their recent paper is the latest in a growing body of evidence suggesting that AI programs can be sabotaged by the data used to train them. As companies, governments, and militaries rush to deploy AI, the potential for mischief could be serious.

The worst foreign-policy decision by the United States of the last generation – and perhaps longer – was the "war of choice" that it launched in Iraq in 2003 for the stated purpose of eliminating weapons of mass destruction that did not, in fact, exist. Understanding the illogic behind that disastrous decision has never been more relevant, because it is being used to justify a similarly misguided US policy today. The decision to invade Iraq followed the illogic of then-US vice-president Richard Cheney, who declared that even if the risk of WMD falling into terrorist hands was tiny – say, 1% – we should act as if that scenario would certainly occur. Such reasoning is guaranteed to lead to wrong decisions more often than not. Yet the US and some of its allies are now using the Cheney Doctrine to attack Chinese technology.

Last week, the nonprofit research group OpenAI revealed that it had developed a new text-generation model that can write coherent, versatile prose given a certain subject matter prompt. However, the organization said, it would not be releasing the full algorithm due to "safety and security concerns." Instead, OpenAI decided to release a "much smaller" version of the model and withhold the data sets and training codes that were used to develop it. If your knowledge of the model, called GPT-2, came solely on headlines from the resulting news coverage, you might think that OpenAI had built a weapons-grade chatbot. A headline from Metro U.K. read, "Elon Musk-Founded OpenAI Builds Artificial Intelligence So Powerful That It Must Be Kept Locked Up for the Good of Humanity."

First of all, Provino Technologies is not an AI chip startup. There are already too many of those. But the secretive 40-member company, established in 2015 by Shailendra Desai, who had cut his teeth at PA Semi and Apple for system-on-chip (SoC) designs, is getting intense interest from a select few Fortune 500 companies because of his team's network-on-chip (NoC) IP. Although the potential number of IP licensees might not be huge, they are a few "large established chip companies" and those "newly getting into the semiconductor business," explained Desai. They have surprised Desai by considering ways to use Provino's scalable interconnect architecture for broader applications in -- you guessed it -- AI.

Machine learning and AI developers are starting to examine the integrity of training data, which in some cases will be used to train millions or even billions of devices. But this is the beginning of what will become a mammoth effort, because today no one is quite sure how that training data can be corrupted, or what to do about it if it is corrupted. Machine learning, deep learning and artificial intelligence are powerful tools for improving the reliability and functionality of systems and speeding time to market. But the AI algorithms also can contain bugs, subtle biases, or even malware that can go undetected for years, according to more than a dozen experts interviewed over the past several months. In some cases, the cause may be errors in programming, which is not uncommon as new tools or technologies are developed and rolled out. Machine learning and AI algorithms are still being fine-tuned and patched.