OpenAI whistleblowers have urged the US financial watchdog to investigate non-disclosure agreements at the startup after claiming the contracts included restrictions such as requiring employees to seek permission before contacting regulators. Non-disclosure agreements (NDAs) typically bar an employee from sharing company information with outside parties but a group of whistleblowers are arguing that OpenAI's agreements could have led to workers being punished for raising concerns about the company to federal authorities. San Francisco-based OpenAI is the developer of the ChatGPT chatbot and a key player in the artificial intelligence boom, which has been accompanied by expressions of concern from experts about the potential dangerous capabilities of the technology. "Given the well-documented potential risks posed by the irresponsible deployment of AI, we urge the Commissioners to immediately approve an investigation into OpenAI's prior NDAs, and to review current efforts apparently being undertaken by the company to ensure full compliance with SEC rules," the letter to Gary Gensler, the chair of the US Securities and Exchange Commission (SEC), said. The letter from whistleblower representatives was sent on 1 July and published by the Washington Post on Saturday after the news organisation obtained it from the office of the US senator Chuck Grassley.

OpenAI's NDAs are once again under scrutiny after whistleblowers penned a letter to the SEC alleging that employees were made to sign "illegally restrictive" agreements preventing them from speaking out on the potential harms of the company's technology. The letter, which was obtained and published online by The Washington Post, accuses OpenAI of violating SEC rules meant to protect employees' rights to report their concerns to federal authorities and prevent retaliation. It follows an official complaint that was filed with the SEC in June. In the letter, the whistleblowers ask the SEC to "take swift and aggressive steps" to enforce the rules they say OpenAI has violated. The alleged violations include making employees sign agreements "that failed to exempt disclosures of securities violations to the SEC" and requiring employees obtain consent from the company before disclosing confidential information to the authorities.

OpenAI reportedly made exiting employees choose between keeping their vested equity and being able to speak out against the company. According to Vox, which viewed the document in question, employees could "lose all vested equity they earned during their time at the company, which is likely worth millions of dollars" if they didn't sign a nondisclosure and non-disparagement agreement, thanks to a provision in the off-boarding papers. OpenAI CEO Sam Altman confirmed in a tweet on Saturday evening that such a provision did exist, but said "we have never clawed back anyone's vested equity, nor will we do that if people do not sign a separation agreement (or don't agree to a non-disparagement agreement)." An OpenAI spokesperson echoed this in a statement to Vox, and Altman said the company "was already in the process of fixing the standard exit paperwork over the past month or so." But as Vox notes in its report, at least one former OpenAI employee has spoken publicly about sacrificing equity by declining to sign an NDA upon leaving.

We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). The key idea and primary advantage of GoT is the ability to model the information generated by an LLM as an arbitrary graph, where units of information ("LLM thoughts") are vertices, and edges correspond to dependencies between these vertices. This approach enables combining arbitrary LLM thoughts into synergistic outcomes, distilling the essence of whole networks of thoughts, or enhancing thoughts using feedback loops. We illustrate that GoT offers advantages over state of the art on different tasks, for example increasing the quality of sorting by 62% over ToT, while simultaneously reducing costs by >31%. We ensure that GoT is extensible with new thought transformations and thus can be used to spearhead new prompting schemes. This work brings the LLM reasoning closer to human thinking or brain mechanisms such as recurrence, both of which form complex networks.

Performing classification on noisy, crowdsourced image datasets can prove challenging even for the best neural networks. Two issues which complicate the problem on such datasets are class imbalance and ground-truth uncertainty in labeling. The AL-ALL and AL-PUB datasets - consisting of tightly cropped, individual characters from images of ancient Greek papyri - are strongly affected by both issues. The application of ensemble modeling to such datasets can help identify images where the ground-truth is questionable and quantify the trustworthiness of those samples. As such, we apply stacked generalization consisting of nearly identical ResNets with different loss functions: one utilizing sparse cross-entropy (CXE) and the other Kullback-Liebler Divergence (KLD). Both networks use labels drawn from a crowd-sourced consensus. This consensus is derived from a Normalized Distribution of Annotations (NDA) based on all annotations for a given character in the dataset. For the second network, the KLD is calculated with respect to the NDA. For our ensemble model, we apply a k-nearest neighbors model to the outputs of the CXE and KLD networks. Individually, the ResNet models have approximately 93% accuracy, while the ensemble model achieves an accuracy of > 95%, increasing the classification trustworthiness. We also perform an analysis of the Shannon entropy of the various models' output distributions to measure classification uncertainty. Our results suggest that entropy is useful for predicting model misclassifications.

Prediction of protein-ligand interactions (PLI) plays a crucial role in drug discovery as it guides the identification and optimization of molecules that effectively bind to target proteins. Despite remarkable advances in deep learning-based PLI prediction, the development of a versatile model capable of accurately scoring binding affinity and conducting efficient virtual screening remains a challenge. The main obstacle in achieving this lies in the scarcity of experimental structure-affinity data, which limits the generalization ability of existing models. Here, we propose a viable solution to address this challenge by introducing a novel data augmentation strategy combined with a physics-informed graph neural network. The model showed significant improvements in both scoring and screening, outperforming task-specific deep learning models in various tests including derivative benchmarks, and notably achieving results comparable to the state-of-the-art performance based on distance likelihood learning. This demonstrates the potential of this approach to drug discovery.

Non-disclosure agreements (NDAs) are some of the most commonly drafted agreements at any company. While they may be common, however, that doesn't mean they're unimportant – in fact, they're critical to protecting a company's business strategies and trade secrets. Most companies use the same form NDA in almost every situation, changing only party names and the description of the confidential information involved, leaving the rest of the agreement to a series of standard terms. This means that, even though they're important, NDAs are very repetitive and routine in terms of drafting. Corporate legal departments have long been bogged down in routine contracts. Preparing NDAs can take up a significant amount of lawyers' time, taking them away from other important work that can bring more value to the organization.

Suggesting that budget cuts have rendered mere human police incapable of doing their jobs without cybernetic help, project lead Iain Donnelly claims working with an AI system will allow the force to do more with less. He insists that the National Data Analytics Solution, as it's called, will target only those individuals already known to have criminal tendencies, sniffing out likely offenders to divert them with therapeutic "interventions," including individuals who are stopped and searched but never arrested or charged. Donnelly claims the program is not designed to "pre-emptively arrest" anyone, but to provide "support from local health or social workers," giving the example of an individual with a history of mental health problems being flagged as a likely violent offender, then contacted by social services. Given that a violent mental case would almost certainly react negatively to being contacted out of nowhere by a mysterious social worker – and that a history of mental health problems is not in itself criminal – Donnelly was wise to end his example there. "Interventions" will be offered only to potential offenders, but the NDAS claims to be able to pick their victims as well.

Data augmentation is often used to enlarge datasets with synthetic samples generated in accordance with the underlying data distribution. To enable a wider range of augmentations, we explore negative data augmentation strategies (NDA) that intentionally create out-of-distribution samples. We show that such negative out-of-distribution samples provide information on the support of the data distribution, and can be leveraged for generative modeling and representation learning. We introduce a new GAN training objective where we use NDA as an additional source of synthetic data for the discriminator. We prove that under suitable conditions, optimizing the resulting objective still recovers the true data distribution but can directly bias the generator towards avoiding samples that lack the desired structure. Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities. Further, we incorporate the same negative data augmentation strategy in a contrastive learning framework for self-supervised representation learning on images and videos, achieving improved performance on downstream image classification, object detection, and action recognition tasks. These results suggest that prior knowledge on what does not constitute valid data is an effective form of weak supervision across a range of unsupervised learning tasks. Data augmentation strategies for synthesizing new data in a way that is consistent with an underlying task are extremely effective in both supervised and unsupervised learning (Oord et al., 2018; Zhang et al., 2016; Noroozi & Favaro, 2016; Asano et al., 2019).

A flagship artificial intelligence system designed to predict gun and knife violence in the UK before it happens had serious flaws that made it unusable, local police have admitted. The error led to large drops in accuracy, and the system was ultimately rejected by all of the experts reviewing it for ethical problems. This story originally appeared on WIRED UK. The prediction system, known as Most Serious Violence (MSV), is part of the UK's National Data Analytics Solution (NDAS) project. The Home Office has funded NDAS with at least £10 million ($13 million) during the past two years, with the aim to create machine learning systems that can be used across England and Wales.