In October, the White House released a 70-plus-page document called the "Blueprint for an A.I. Bill of Rights." The document's ambition was sweeping. It called for the right for individuals to "opt out" from automated systems in favor of human ones, the right to a clear explanation as to why a given A.I. system made the decision it did, and the right for the public to give input on how A.I. systems are developed and deployed. But if it did become law, it would transform how A.I. systems would need to be devised. And, for that reason, it raises an important set of questions: What does a public vision for A.I. actually look like?

Garante, the Italian data protection authority, apparently jumped the gun at the end of March when it imposed a temporary ban on ChatGPT, a chatbot that uses artificial intelligence (AI) to generate texts that seem as if they were created by humans, and computer games. The watchdog was less concerned by the use of AI -- the simulation of human intelligence by computer systems -- than by breaches of data protection legislation. Garante then told the Microsoft Corp-backed company behind ChatGPT, OpenAI, that it would have to be more transparent with its users about how their data were processed. It also said that the US company had to obtain permission from users if their data were to be used to further develop the software -- that is, to help it learn -- and that access to minors had to be filtered. In a press release, the Italian authority said that the ban would be lifted if OpenAI met these conditions by April 30.

General Atomics Aeronautical Systems (GA-ASI) has flown live, tactical, air combat maneuvers using AI pilots to control a company-owned MQ-20 Avenger UAS. Collaborative maneuvers between human and AI pilots were conducted using GA-ASI's Live, Virtual, Constructive (LVC) collaborative combat aircraft ecosystem over a Low Earth Orbit (LEO) SATCOM provider's IP-based Mission Beyond Visual Line of Sight (BVLOS) datalink. The LEO SATCOM connection was also used to rapidly retrain and redeploy AI pilots while the aircraft was airborne, demonstrating GA-ASI's ability to update AI pilots within minutes. This marks the first deployment of an LEO SATCOM provider connections running on an operationally relevant unmanned combat aerial vehicle platform. The team used two L3Harris Technologies RASOR Multi-Functional Processors (MFPs) – one that housed the transceiver card and another that controlled the BVLOS Active Electronically Scanned Array (AESA).

If you had "leaking classified US military documents for the lulz" on your 2023 Bingo card, congratulations. The fast-paced drama surrounding the online disclosure of top-secret material ripped through this week's news. We'll dive into the details below, but there's one key takeaway: This bizarre kind of leak may be only the beginning. Anyone worried about chaos agents of a different variety now have a new way to protect their online identities. LinkedIn this week began to roll out new tools that allow you to verify your identity and your job.

Universal Music Group has been asking music streaming services like Spotify to stop developers from scraping its material to train AI bots to make new songs. The label, which controls about a third of the recorded music industry, has also been issuing substantial numbers of takedown requests in relation to AI uploads appearing online. It is the latest move in the music industry's growing battle to prevent AIs from using its songs without licensing them. On a "royalty free music generator" like Mubert, it's already possible to type in a prompt and the programme will use AI to search a catalogue of music for patterns. Tell it to play a "fast voodoo rhythm in the style of a nursery rhyme with some pretty electronics", and it will copy parts of songs that correspond and generate music to match.

I'll be talking about ChatGPT, artificial intelligence, and why I don't think we're doomed. I'll start by admitting that I'm a human. I've been using software and search engines while researching and writing this post. So what you are reading has been tarnished by technology's terrible taint. Looking at it another way, today's tech has helped me find facts and arrange my ideas. I also strongly suspect that using today's technology has affected how I write. If I'd lived in an earlier era -- mayhap composing with goose quills, iron gall ink and cotton paper -- I might be writing stuff like "The Dunwich Horror". And yes, mayhap is a real word; although it's not used much these days.1 "…As before, the sides of the road shewed a bruising indicative of the blasphemously stupendous bulk of the horror; whilst the conformation of the tracks seemed to argue a passage in two directions…." Even in Lovecraft's day, there was only one Lovecraft.2 I'll also admit to a bias.

The publication of this series was inspired by the release ChatGPT, which is a generative artificial intelligence (AI) chatbox developed by Open AI. ChatGPT uses machine learning and natural language processing to provide relatively sophisticated and human-like responses to almost any question. Unlike traditional AI systems, ChatGPT is a generative AI platform, which means that the content it creates is "new," rather than a reiteration of something that already exists. As ChatGPT demonstrates, content can be produced through generative AI in a matter of seconds and may be composed of images, videos, audio, text or even code. The reality is that generative AI is well on the way to becoming not just faster and cheaper, but better in some cases than what humans create by hand.

'The Five' co-hosts discuss Elon Musk's warning to Tucker Carlson about artificial intelligence's potential to destroy civilization. A California lawmaker introduced legislation that would criminalize using artificial intelligence to create pornography while using a person's likeness without consent. Assembly member Tri Ta, a Republican representing Westminster, California, introduced the legislation in February that aims to punish people up to $1,000, or a year in jail, if they distribute "deepfake" porn depicting an individual without their consent. "This bill would make it a crime for a person to knowingly, and without the consent of the depicted individual, distribute to, exhibit to, or exchange with others, or offer to distribute to, exhibit to, or exchange with others audio or visual media that falsely depicts an individual engaging in sexual conduct that would appear to a reasonable observer to be an authentic record of the conduct. By creating a new crime, this bill would impose a state-mandated local program," a legislative council's digest of the bill states.

Inverse problems are ubiquitous in the sciences and engineering. Two categories of inverse problems concerning a physical system are (1) estimate parameters in a model of the system from observed input-output pairs and (2) given a model of the system, reconstruct the input to it that caused some observed output. Applied inverse problems are challenging because a solution may (i) not exist, (ii) not be unique, or (iii) be sensitive to measurement noise contaminating the data. Bayesian statistical inversion (BSI) is an approach to tackle ill-posed and/or ill-conditioned inverse problems. Advantageously, BSI provides a "solution" that (i) quantifies uncertainty by assigning a probability to each possible value of the unknown parameter/input and (ii) incorporates prior information and beliefs about the parameter/input. Herein, we provide a tutorial of BSI for inverse problems, by way of illustrative examples dealing with heat transfer from ambient air to a cold lime fruit. First, we use BSI to infer a parameter in a dynamic model of the lime temperature from measurements of the lime temperature over time. Second, we use BSI to reconstruct the initial condition of the lime from a measurement of its temperature later in time. We demonstrate the incorporation of prior information, visualize the posterior distributions of the parameter/initial condition, and show posterior samples of lime temperature trajectories from the model. Our tutorial aims to reach a wide range of scientists and engineers.

The neural collapse (NC) phenomenon describes an underlying geometric symmetry for deep neural networks, where both deeply learned features and classifiers converge to a simplex equiangular tight frame. It has been shown that both cross-entropy loss and mean square error can provably lead to NC. We remove NC's key assumption on the feature dimension and the number of classes, and then present a generalized neural collapse (GNC) hypothesis that effectively subsumes the original NC. Inspired by how NC characterizes the training target of neural networks, we decouple GNC into two objectives: minimal intra-class variability and maximal inter-class separability. We then use hyperspherical uniformity (which characterizes the degree of uniformity on the unit hypersphere) as a unified framework to quantify these two objectives. Finally, we propose a general objective -- hyperspherical uniformity gap (HUG), which is defined by the difference between inter-class and intra-class hyperspherical uniformity. HUG not only provably converges to GNC, but also decouples GNC into two separate objectives. Unlike cross-entropy loss that couples intra-class compactness and inter-class separability, HUG enjoys more flexibility and serves as a good alternative loss function. Empirical results show that HUG works well in terms of generalization and robustness.