The bill would need companies to file such documents at least 30 days before publicly debuting their AI tools, or face a financial penalty. Such datasets encompass billions of lines of text and images or millions of hours of music and movies. "AI has the disruptive potential of changing our economy, our political system, and our day-to-day lives. We must balance the immense potential of AI with the crucial need for ethical guidelines and protections," Schiff said in a statement. Schiff's bill, which was first reported by Billboard, has received the support of numerous entertainment industry organizations and unions, including the Recording Industry Association of America, Professional Photographers of America, Directors Guild of America and the Screen Actors Guild-American Federation of Television and Radio Artists.

Superhuman artificial intelligence that is smarter than anyone on Earth could exist next year, Elon Musk has said, unless the sector's power and computing demands become unsustainable before then. The prediction is a sharp tightening of an earlier claim from the multibillionaire, that superintelligent AI would exist by 2029. Whereas "superhuman" is generally defined as being smarter than any individual human at any specific task, superintelligent is often defined instead as being smarter than every human's combined ability at any task. "My guess is that we'll have AI that is smarter than any one human probably around the end of next year," Musk said in a live streamed interview on his social network X. That prediction was made with the caveat that increasing demands for power and shortages of the most powerful AI training chips could limit their capability in the near term.

OpenAI is also at the center of several regulatory investigations, which have forced the company to spend even more on legal support. The Securities and Exchange Commission is looking into whether investors were misled during the chaotic period when Altman briefly left the company. The Federal Trade Commission is probing whether it ran afoul of consumer protection laws in a number of areas, including a data leak and ChatGPT's inaccurate claims. And the commission has had talks with the Justice Department about which agency should probe its multibillion-dollar partnership with Microsoft, amid concerns that such deals are dampening competition in the quickly evolving AI market.

Tesla reached a settlement on the eve of its highest-profile trial yet over a crash blamed on Autopilot, the driver-assistance system Elon Musk has billed as crucial to his pursuit of self-driving cars, according to court filings. Terms of the settlement weren't disclosed in filings made public Monday in state court in San Jose, California. The trial that was set to kick off this week centered on Walter Huang, a 38-year-old Apple engineer who was killed on the way to work in 2018 when his Model X veered off the highway and slammed into a roadside barrier at about 71 miles (114 kilometers) per hour. A federal safety agency's investigation of the accident found that Huang was probably distracted with a video game app on his phone, while also pointing to "limitations" of the Autopilot system.

Electric carmaker Tesla has settled a lawsuit brought by the family of an Apple engineer who was killed when his Model X swerved off a California highway while on autopilot. Tesla settled with the family of Wei Lun Huang in the wrongful death suit they filed over the crash in Mountain View, California in 2018, court filings showed on Monday. The settlement means that Tesla will avoid a jury trial that would have focused scrutiny on its self-driving technology months ahead of the scheduled launch of its self-driving Robotaxi in August. The amount Tesla paid to settle the case was not disclosed in court documents after the company asked that it remain under seal. Huang's family filed a negligence and wrongful death lawsuit in 2019 accusing Tesla of liability due to exaggerated claims about the firm's self-driving technology.

Text-to-video generative AI models such as Sora OpenAI have the potential to disrupt multiple industries. In this paper, we report a qualitative social media analysis aiming to uncover people's perceived impact of and concerns about Sora's integration. We collected and analyzed comments (N=292) under popular posts about Sora-generated videos, comparison between Sora videos and Midjourney images, and artists' complaints about copyright infringement by Generative AI. We found that people were most concerned about Sora's impact on content creation-related industries. Emerging governance challenges included the for-profit nature of OpenAI, the blurred boundaries between real and fake content, human autonomy, data privacy, copyright issues, and environmental impact. Potential regulatory solutions proposed by people included law-enforced labeling of AI content and AI literacy education for the public. Based on the findings, we discuss the importance of gauging people's tech perceptions early and propose policy recommendations to regulate Sora before its public release.

Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW) content, particularly in sexual scenarios. Existing countermeasures mostly focus on filtering inappropriate inputs and outputs, or suppressing improper text embeddings, which can block explicit NSFW-related content (e.g., naked or sexy) but may still be vulnerable to adversarial prompts inputs that appear innocent but are ill-intended. In this paper, we present SafeGen, a framework to mitigate unsafe content generation by text-to-image models in a text-agnostic manner. The key idea is to eliminate unsafe visual representations from the model regardless of the text input. In this way, the text-to-image model is resistant to adversarial prompts since unsafe visual representations are obstructed from within. Extensive experiments conducted on four datasets demonstrate SafeGen's effectiveness in mitigating unsafe content generation while preserving the high-fidelity of benign images. SafeGen outperforms eight state-of-the-art baseline methods and achieves 99.1% sexual content removal performance. Furthermore, our constructed benchmark of adversarial prompts provides a basis for future development and evaluation of anti-NSFW-generation methods.

Large Language Models (LLMs) are increasingly being developed and applied, but their widespread use faces challenges. These include aligning LLMs' responses with human values to prevent harmful outputs, which is addressed through safety training methods. Even so, bad actors and malicious users have succeeded in attempts to manipulate the LLMs to generate misaligned responses for harmful questions such as methods to create a bomb in school labs, recipes for harmful drugs, and ways to evade privacy rights. Another challenge is the multilingual capabilities of LLMs, which enable the model to understand and respond in multiple languages. Consequently, attackers exploit the unbalanced pre-training datasets of LLMs in different languages and the comparatively lower model performance in low-resource languages than high-resource ones. As a result, attackers use a low-resource languages to intentionally manipulate the model to create harmful responses. Many of the similar attack vectors have been patched by model providers, making the LLMs more robust against language-based manipulation. In this paper, we introduce a new black-box attack vector called the Sandwich attack: a multi-language mixture attack, which manipulates state-of-the-art LLMs into generating harmful and misaligned responses. GPT-4, and Claude-3-OPUS, show that this attack vector can be used by adversaries to generate harmful responses and elicit misaligned responses from these models. By detailing both the mechanism and impact of the Sandwich attack, this paper aims to guide future research and development towards more secure and resilient LLMs, ensuring they serve the public good while minimizing potential for misuse. Content Warning: This paper contains examples of harmful language. Ethics and Disclosure This paper introduces a new universal attack method for the SOTA LLMs that could potentially be used to elicit harmful content from publicly available LLMs. The adversarial attack method we used in this paper is easy to design and requires low-cost to implement. Despite the associated risks, we firmly believe that sharing the full details of this research and its methodology will be invaluable to other researchers, scholars, and model creators. It encourages them to delve into the root causes behind these attacks and devise ways to fortify and patch existing models. Additionally, it promotes cooperative initiatives centered around the safety of LLMs in multilingual scenarios.

In the financial industry, identifying the location of parties involved in payments is a major challenge in the context of various regulatory requirements. For this purpose address parsing entails extracting fields such as street, postal code, or country from free text message attributes. While payment processing platforms are updating their standards with more structured formats such as SWIFT with ISO 20022, address parsing remains essential for a considerable volume of messages. With the emergence of Transformers and Generative Large Language Models (LLM), we explore the performance of state-of-the-art solutions given the constraint of processing a vast amount of daily data. This paper also aims to show the need for training robust models capable of dealing with real-world noisy transactional data. Our results suggest that a well fine-tuned Transformer model using early-stopping significantly outperforms other approaches. Nevertheless, generative LLMs demonstrate strong zero-shot performance and warrant further investigations.

This work demonstrates two Privacy Policy (PP) summarisation models based on two different clustering algorithms: K-means clustering and Pre-determined Centroid (PDC) clustering. K-means is decided to be used for the first model after an extensive evaluation of ten commonly used clustering algorithms. The summariser model based on the PDC-clustering algorithm summarises PP documents by segregating individual sentences by Euclidean distance from each sentence to the pre-defined cluster centres. The cluster centres are defined according to General Data Protection Regulation (GDPR)'s 14 essential topics that must be included in any privacy notices. The PDC model outperformed the K-means model for two evaluation methods, Sum of Squared Distance (SSD) and ROUGE by some margin (27% and 24% respectively). This result contrasts the K-means model's better performance in the general clustering of sentence vectors before running the task-specific evaluation. This indicates the effectiveness of operating task-specific fine-tuning measures on unsupervised machine-learning models. The summarisation mechanisms implemented in this paper demonstrates an idea of how to efficiently extract essential sentences that should be included in any PP documents. The summariser models could be further developed to an application that tests the GDPR-compliance (or any data privacy legislation) of PP documents.