Microsoft Corp.'s 13 billion investment into OpenAI Inc. risks a full-blown investigation by European Union deals watchdogs, after a mutiny at the ChatGPT creator laid bare deep ties between the two companies. The European Commission said on Tuesday that it's examining whether Microsoft's involvement should be vetted under the bloc's merger rules -- paving the way for a formal probe and even a potential unwinding if it's found to hamper fair competition. The EU move, part of a broader look at artificial intelligence, follows a similar step by the UK's Competition and Markets Authority. "Virtual worlds and generative AI are rapidly developing," said Margrethe Vestager, the EU's antitrust commissioner. "It is fundamental that these new markets stay competitive, and that nothing stands in the way of businesses growing and providing the best and most innovative products to consumers."

But true data intelligence is about more than establishing the right data foundation. Organizations are also wrestling with how to overcome dependence on highly technical staff and create frameworks for data privacy and organizational control when using generative AI. Specifically, they are looking to enable all employees to use natural language to glean actionable insight from the company's own data; to leverage that data at scale to train, build, deploy, and tune their own secure large language models (LLMs); and to infuse intelligence about the company's data into every business process. In this next frontier of data intelligence, organizations will maximize value by democratizing AI while differentiating through their people, processes, and technology within their industry context. Based on a global, cross-industry survey of 600 technology leaders as well as in-depth interviews with technology leaders, this report explores the foundations being built and leveraged across industries to democratize data and AI.

This article was featured in the One Story to Read Today newsletter. Every day or two for the past seven months, I've received a "personalized" email containing a bunch of recent, user-generated questions from the website Quora. "I caught my son playing his Xbox at 12:00 in the morning on a school night. As a result, I broke his console and now he won't talk to me. How can I tell him that it is his fault?"

Amid the growing clamor in Congress to regulate AI, the company is bringing in reinforcements. After years of outreach to lawmakers, OpenAI in fall 2023 disclosed its first in-house lobbyist, and reported that it is working with global law firm DLA Piper, according to federal disclosures. OpenAI to date has not advocated for or against any specific bill, Makanju says, but she anticipates that will change in 2024, especially with the Schumer effort that is underway. Makanju's team is also growing around the world, with more than 20 people in the United Kingdom, Germany, Japan and Brazil.

And based on what OpenAI told the House of Lords Communications and Digital Select Committee, we might see more lawsuits against the companies in the future. It added that "[l]imiting training data to public domain books and drawings created more than a century ago might yield an interesting experiment, but would not provide AI systems that meet the needs of today's citizens." In a new post on its blog made in response to the The New York Times' lawsuit, it said the use of publicly available internet materials to train AI falls under fair use doctrine. It admitted, however, that there is "still work to be done to support and empower creators." The company talked about the ways it's allowing publishers to block the GPTBot web crawler from being able to access their websites. It also said that it's developing additional mechanisms allowing rightsholders to opt out of training and that it's engaging with them to find mutually beneficial agreements.

Of the many events that stand out as noteworthy in online discussions across Chinese social media in 2023, it's perhaps the rise of ChatGPT that will prove to be the most significant. Although the chatbot made by the US-based OpenAI was officially launched in late 2022, it took until 2023 for its unprecedented growth to raise eyebrows in China, where the government has set the goal of becoming the global AI leader by 2030. Over the past decade, the focus on AI in Chinese society and digital culture has grown. Since the Covid-19 outbreak, AI implementations in schools, office buildings and factories have rolled out in fast forward. AI facial recognition is employed in everything from public security to payment technology; smart glasses and helmets make it easier for many workers to perform their tasks; and intelligent robots have become a common sight in China's service industry, in malls, restaurants, and banks. There seemed little doubt over who would win the tech race between the eagle and the dragon; but then came ChatGPT.

Foundation models such as large language models (LLMs) have shown remarkable capabilities redefining the field of artificial intelligence. At the same time, they present pressing and challenging socio-technical risks regarding the trustworthiness of their outputs and their alignment with human values and ethics [Bommasani et al., 2021]. Evaluating LLMs is therefore a multi-dimensional problem, where those risks are assessed across diverse tasks and domains [Chang et al., 2023]. In order to quantify these risks, Liang et al. [2022], Wang et al. [2023], Huang et al. [2023] proposed benchmarks of automatic metrics for probing the trustworthiness of LLMs. These metrics include accuracy, robustness, fairness, toxicity of the outputs, etc. Human evaluation benchmarks can be even more nuanced, and are often employed when tasks surpass the scope of standard metrics. Notable benchmarks based on human and automatic evaluations include, among others, Chatbot Arena [Zheng et al., 2023], HELM [Bommasani et al., 2023], MosaicML's Eval, Open LLM Leaderboard [Wolf, 2023], and BIG-bench [Srivastava et al., 2022], each catering to specific evaluation areas such as chatbot performance, knowledge assessment, and domain-specific challenges. Traditional metrics, however, sometimes do not correlate well with human judgments.

Critique, as a natural language description for assessing the quality of model-generated content, has been proven to play an essential role in the training, evaluation, and refinement of Large Language Models (LLMs). However, there is a lack of principled understanding in evaluating the quality of the critique itself. In this paper, we pioneer the critique of critique, termed MetaCritique, which is a framework to evaluate the critique from two aspects, i.e., factuality as precision score and comprehensiveness as recall score. We calculate the harmonic mean of precision and recall as the overall rating called F1 score. To obtain a reliable evaluation outcome, we propose Atomic Information Units (AIUs), which describe the critique in a more fine-grained manner. MetaCritique takes each AIU into account and aggregates each AIU's judgment for the overall score. Moreover, given the evaluation process involves intricate reasoning, our MetaCritique provides a natural language rationale to support each judgment. We construct a meta-evaluation dataset containing 300 critiques (2653 AIUs) across four tasks (question answering, reasoning, entailment, and summarization), and we conduct a comparative study to demonstrate the feasibility and effectiveness. Experiments also show superior critique judged by MetaCritique leads to better refinement, indicating generative artificial intelligence indeed has the potential to be significantly advanced with our MetaCritique. We will release relevant code and meta-evaluation datasets at https://github.com/GAIR-NLP/MetaCritique.

Abstract--Spectrum sharing allows different protocols of the same standard (e.g., 802.11 family) or different standards (e.g., LTE and DVB) to coexist in overlapping frequency bands. Third, it utilizes an extensive 66 GB dataset of over-the-air (OTA) WiFi transmissions for training, which is released along with the code for community use. Legacy protocol detection methods are integrated into the RF receiver network interface card, enabling fast preamble I. However, updating the system for new protocols leads to backward compatibility issues and The increasing demand for wireless services has caused a potential detection errors in challenging wireless channels. This results in congested the other hand, software-defined radio (SDR) systems offer wireless spectrum environments as various communication flexibility but introduce higher latencies due to data transfer protocols coexist in the same frequency bands [2]. This paper transmissions further raise security concerns, posing demonstrates that using edge devices with CPU and GPU risks to critical operations [3]. Detecting diverse protocols in on a system-on-a-module (SOM), along with careful software crowded spectrums allows for intelligent strategies to mitigate design, can overcome the these limitations and enable realtime interference, improve spectral efficiency, and enhance overall processing for complex ML wireless applications on an wireless system performance, benefiting regulatory bodies, SDR-based edge device.

In this paper, we introduce Uni3D-LLM, a unified framework that leverages a Large Language Model (LLM) to integrate tasks of 3D perception, generation, and editing within point cloud scenes. This framework empowers users to effortlessly generate and modify objects at specified locations within a scene, guided by the versatility of natural language descriptions. Uni3D-LLM harnesses the expressive power of natural language to allow for precise command over the generation and editing of 3D objects, thereby significantly enhancing operational flexibility and controllability. By mapping point cloud into the unified representation space, Uni3D-LLM achieves cross-application functionality, enabling the seamless execution of a wide array of tasks, ranging from the accurate instantiation of 3D objects to the diverse requirements of interactive design. Through a comprehensive suite of rigorous experiments, the efficacy of Uni3D-LLM in the comprehension, generation, and editing of point cloud has been validated. Additionally, we have assessed the impact of integrating a point cloud perception module on the generation and editing processes, confirming the substantial potential of our approach for practical applications.