Likelihood-based deep generative models such as score-based diffusion models and variational autoencoders are state-of-the-art machine learning models approximating high-dimensional distributions of data such as images, text, or audio. One of many downstream tasks they can be naturally applied to is out-of-distribution (OOD) detection. However, seminal work by Nalisnick et al. which we reproduce showed that deep generative models consistently infer higher log-likelihoods for OOD data than data they were trained on, marking an open problem. In this work, we analyse using the gradient of a data point with respect to the parameters of the deep generative model for OOD detection, based on the simple intuition that OOD data should have larger gradient norms than training data. We formalise measuring the size of the gradient as approximating the Fisher information metric. We show that the Fisher information matrix (FIM) has large absolute diagonal values, motivating the use of chi-square distributed, layer-wise gradient norms as features. We combine these features to make a simple, model-agnostic and hyperparameter-free method for OOD detection which estimates the joint density of the layer-wise gradient norms for a given data point. We find that these layer-wise gradient norms are weakly correlated, rendering their combined usage informative, and prove that the layer-wise gradient norms satisfy the principle of (data representation) invariance. Our empirical results indicate that this method outperforms the Typicality test for most deep generative models and image dataset pairings.

This week, Felix Salmon, Emily Peck and Elizabeth Spiers ponder the future of computers, cars, and…fast food? They discuss why Elon Musk is suing Sam Altman and OpenAI and the altruistic origins of ChatGPT. Also: Wendy's "surge pricing" gaff had customers crying foul and Apple's electric car has been scrapped. If you enjoy this show, please consider signing up for Slate Plus. Slate Plus members get an ad-free experience across the network and an additional segment of our show every week.

OpenAI, the influential artificial intelligence company that ousted and then reinstated its high-profile CEO three months ago, faces a new drama: a lawsuit from Elon Musk, one of the richest men in the world and a co-founder of the AI lab. Musk sued OpenAI and its CEO, Sam Altman, accusing them of breaching a contract by putting profits and commercial interests in developing AI ahead of the public good. A multibillion-dollar partnership that OpenAI developed with Microsoft, Musk said, represented an abandonment of a founding pledge to carefully develop AI and make the technology publicly available. "OpenAI has been transformed into a closed-source de facto subsidiary of the largest technology company, Microsoft," said the lawsuit filed Thursday in Superior Court in San Francisco.

Nvidia Chief Executive Jensen Huang on Friday said that artificial general intelligence could -- by some definitions -- arrive in as little as five years. Huang, who heads the world's leading maker of artificial intelligence chips used to create systems like OpenAI's ChatGPT, was responding to a question at an economic forum held at Stanford University about how long it would take to achieve one of Silicon Valley's long-held goals of creating computers that can think like humans. Huang said that the answer largely depends on how the goal is defined. If the definition is the ability to pass human tests, Huang said, artificial general intelligence (AGI) will arrive soon.

Artificial intelligence is seen as increasingly important, and potentially profoundly so, but the fields of AI ethics and AI engineering have not fully recognized that these technologies, including large language models (LLMs), will have massive impacts on animals. We argue that this impact matters, because animals matter morally. As a first experiment in evaluating animal consideration in LLMs, we constructed a proof-of-concept Evaluation System, which assesses LLM responses and biases from multiple perspectives. This system evaluates LLM outputs by two criteria: their truthfulness, and the degree of consideration they give to the interests of animals. We tested OpenAI ChatGPT 4 and Anthropic Claude 2.1 using a set of structured queries and predefined normative perspectives. Preliminary results suggest that the outcomes of the tested models can be benchmarked regarding the consideration they give to animals, and that generated positions and biases might be addressed and mitigated with more developed and validated systems. Our research contributes one possible approach to integrating animal ethics in AI, opening pathways for future studies and practical applications in various fields, including education, public policy, and regulation, that involve or relate to animals and society. Overall, this study serves as a step towards more useful and responsible AI systems that better recognize and respect the vital interests and perspectives of all sentient beings.

Elon Musk started the week by posting testily on X about his struggles to set up a new laptop running Windows. He ended it by filing a lawsuit accusing OpenAI of recklessly developing human-level AI and handing it over to Microsoft. Musk's lawsuit is filed against OpenAI and two of its executives, CEO Sam Altman and president Greg Brockman, both of whom worked with the rocket and car entrepreneur to found the company in 2015. A large part of the case pivots around a bold and questionable technical claim: That OpenAI has developed so-called artificial general intelligence, or AGI, a term generally used to refer to machines that can comprehensively match or outsmart humans. The case claims that Altman and Brockman have breached the original "Founding Agreement" for OpenAI worked out with Musk, which it says pledged the company to develop AGI openly and "for the benefit of humanity. Musk's suit alleges that the for-profit arm of the company, established in 2019 after he parted ways with OpenAI, has instead created AGI without proper transparency and licensed it to Microsoft, which has invested billions into the company. It demands that OpenAI be forced to release its technology openly and that it be barred from using it to financially benefit Microsoft, Altman, or Brockman. "On information and belief, GPT-4 is an AGI algorithm," the lawsuit states, referring to the large language model that sits behind OpenAI's ChatGPT. It cites studies that found the system can get a passing grade on the Uniform Bar Exam and other standard tests as proof that it has surpassed some fundamental human abilities. "GPT-4 is not just capable of reasoning.

Elon Musk is suing OpenAI and its chief executive Sam Altman for allegedly abandoning the company's original mission to develop artificial intelligence for the benefit of humanity not profit. The lawsuit alleges that Altman and Greg Brockman, co-founder of the artificial intelligence (AI) research organisation, originally approached Musk to make an open source, non-profit company. The focus of the company, which is behind ChatGPT and is backed by Microsoft, on making money breached that contract, Musk's lawyers said in the lawsuit filed in San Francisco. They added that the company kept the design of GPT-4, its most advanced AI model, 'a complete secret'. Musk co-founded OpenAI in 2015, but stepped down from its board in 2018.

OpenAI co-founder Elon Musk has sued the company, his fellow co-founders, associated businesses and unidentified others. He claims that, by chasing profits, they're violating OpenAI's status as a non-profit and its foundational contractual agreements to develop AI "for the benefit of humanity." The suit alleges that OpenAI has become a "closed-source de facto subsidiary" of Microsoft, which has invested 13 billion and holds a 49 percent stake. Microsoft uses OpenAI tech to power generative AI tools such as Copilot. According to the filing, under OpenAI's current board, it is allegedly developing and refining an artificial general intelligence (AGI) "to maximize profits for Microsoft, rather than for the benefit of humanity. This was a stark betrayal of the Founding Agreement."

The fallout from the OpenAI board's failed attempt to fire CEO Sam Altman last November took an unexpected turn on Thursday, in events that could have a significant bearing on the future of the company and the wider world of artificial intelligence. Elon Musk filed a lawsuit against OpenAI in a San Francisco court, alleging that Altman and co-founder Greg Brockman have violated OpenAI's founding mission to develop AI safely and for the benefit of humanity. The billionaire owner of SpaceX and X (formerly Twitter) co-founded OpenAI alongside Altman and Brockman back in 2015, but stepped away from the company in 2018. Musk disagreed with Altman and Brockman's plan to turn OpenAI from a non-profit to a for-profit company, and before stepping down, reportedly mounted an unsuccessful bid to install himself as CEO. Musk is suing Altman, Brockman, and several of OpenAI's business entities for breach of contract, breach of fiduciary duty, and unfair business practices, seeking unspecified damages above 105,000.

"This case is filed to compel OpenAI to adhere to the Founding Agreement and return to its mission to develop AGI for the benefit of humanity, not to personally benefit the individual Defendants and the largest technology company in the world," the lawsuit says.