Thinking about science and technology in terms of return on investment misses the point. Here's what kids really need to know. That's what led me to become a professor. As a high school student, one of my major life goals was to figure out how to build an actual light sword. Doing so is all but impossible, so it didn't really matter if I went into engineering or science, but I pursued STEM just the same.

Diffusion models have seen immense success in modelling continuous data across a range of domains such as vision and audio. Despite the challenges of adapting diffusion models to discrete data, recent work explores their application to text generation by working in the continuous embedding space. However, these models lack a natural means to control the inherent trade-off between quality and diversity as afforded by the temperature hyperparameter in autoregressive models, hindering understanding of model performance and restricting generation quality. This work proposes the use of classifier-free guidance and stochastic clamping for manipulating the quality-diversity trade-off on sequence-to-sequence tasks, demonstrating that these techniques may be used to improve the performance of a diffusion language model.

There has been a string of articles recently about the end of generative AI hype. Our experts consider whether or not the bubble has burst. Joining the conversation this time are: Tom Dietterich (Oregon State University), Sabine Hauert (University of Bristol), Michael Littman (Brown University), and Marija Slavkovik (University of Bergen). Sabine Hauert: There have been a number of recent articles in the mainstream media talking about the fact that AI has not made any money, and that it might be all hype, or a bubble. Marija Slavkovik: There is this article by Cory Doctorow which asks what kind of bubble AI is. I really like his take that a lot of bubbles come and go; some of them leave us something useful and some of them just generate something for a brief moment in time, like excellent revenue for the investment bankers for example.

Last week, The Browser Company, a startup that makes the Arc web browser, released a slick new iPhone app called Arc Search. Instead of displaying links, its brand new "Browse for Me" feature reads the first handful of pages and summarizes them into a single, custom-built, Arc-formatted web page using large language models from OpenAI and others. If a user does click through to any of the actual pages, Arc Search blocks ads, cookies and trackers by default. Arc's efforts to reimagine web browsing have received near-universal acclaim. But over the last few days, "Browse for Me" earned The Browser Company its first online backlash.

Last year saw new artificial intelligence products released at the most rapid pace yet, though predictions of an AI boom on the scale of last decade's tech explosion have yet to come to fruition. "I think 2023 was the year that AI astonished people and 2024 will be the year of retrenchment as people learn the limitations of AI and where various AI systems have the greatest utility," Christopher Alexander, chief analytics officer for Pioneer Development Group, told Fox News Digital. "I think that the race for AI utility has just begun and AI will become a permanent fixture in people's lives. I think that the grand predictions for AI in this past year confused the current state of AI and the future state, which has led to some confusion in the market." Alexander's comments come after what was in many ways a landmark year for AI technology in 2023, with new platforms and developments making headlines throughout the year.

In this report, we explore the ability of language model agents to acquire resources, create copies of themselves, and adapt to novel challenges they encounter in the wild. We refer to this cluster of capabilities as "autonomous replication and adaptation" or ARA. We believe that systems capable of ARA could have wide-reaching and hard-to-anticipate consequences, and that measuring and forecasting ARA may be useful for informing measures around security, monitoring, and alignment. Additionally, once a system is capable of ARA, placing bounds on a system's capabilities may become significantly more difficult. We construct four simple example agents that combine language models with tools that allow them to take actions in the world. We then evaluate these agents on 12 tasks relevant to ARA. We find that these language model agents can only complete the easiest tasks from this list, although they make some progress on the more challenging tasks. Unfortunately, these evaluations are not adequate to rule out the possibility that near-future agents will be capable of ARA. In particular, we do not think that these evaluations provide good assurance that the ``next generation'' of language models (e.g. 100x effective compute scaleup on existing models) will not yield agents capable of ARA, unless intermediate evaluations are performed during pretraining. Relatedly, we expect that fine-tuning of the existing models could produce substantially more competent agents, even if the fine-tuning is not directly targeted at ARA.

According to the amateur online-business advisers of YouTube, the age of easily accessible AI is the age of asking and receiving. ChatGPT and other AI tools are ascendant in popular culture, as is the idea that you can ask them for anything. You can even ask them to make you rich. Joshua Mayo, a YouTube personality who makes videos about work-from-home "side hustles" and methods for becoming a millionaire before age 30, told me recently that his audience of mostly young people doesn't want to work a standard 9-to-5 job for several decades and then retire off of their 401(k). "A lot of them don't find that appealing," he said.

OpenAI warned Microsoft early this year about rushing the integration of GPT-4 into Bing without further training, according to The Wall Street Journal. Although Microsoft forged ahead anyway, the alert proved prescient as early users noticed "unhinged" behavior in the Bing AI tool. Rather than buying OpenAI outright, Microsoft invested in a 49-percent stake in the artificial intelligence startup, a strategy designed to help it avoid antitrust scrutiny. The arrangement gave Microsoft early access to OpenAI's ChatGPT and DALL-E 2 to boost its Bing search engine. In addition, it's adding OpenAI-powered CoPilot to Office and other software products as rival Google scrambles to catch up.

Did you sign off on those expenses in Concur? Ever feel too busy at work to get any actual work done? Well, apparently you are right. According to a new report from Microsoft, our workplaces have a serious productivity problem. The study – which surveyed nearly 31,000 full-time employed or self-employed workers across 31 markets between 1 February 2023 and 14 March 2023 – found that 64% say they struggle with having the time and energy to do their job.

A geography professor shared his method to detect AI-generated plagiarism with Fox News. He developed it after noticing that ChatGPT produced fake citations. Chatbots are the latest new tech that everyone seems to be obsessing over. They are computer programs that use artificial intelligence and natural language processing to simulate human conversations. These conversational assistants can be accessed through various messaging platforms such as ChatGPT, Bing Chat and Bard.