The tech companies say they are monitoring the use of their tools and have instituted some policies against using them to produce political content. But enforcing those rules may be difficult. In January, OpenAI suspended a developer that had made a bot of the Democratic candidate Dean Phillips, only after a report in The Washington Post. The developer had made similar bots of political candidates in the fall.

OpenAI on Thursday announced Sora, a brand new model that generates high-definition videos up to one minute in length from text prompts. Sora, which means "sky" in Japanese, won't be available to the general public any time soon. Instead, OpenAI is making it available to a small group of academics and researchers who will assess harm and its potential for misuse. "Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background," the company said on its website. "The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world."

Code-completion systems offering suggestions to a developer in their integrated development environment (IDE) have become the most frequently used kind of programmer assistance.1 When generating whole snippets of code, they typically use a large language model (LLM) to predict what the user might type next (the completion) from the context of what they are working on at the moment (the prompt).2 This system allows for completions at any position in the code, often spanning multiple lines at once. AI pair-programming tools such as GitHub Copilot have a big impact on developer productivity. This holds for developers of all skill levels, with junior developers seeing the largest gains. The reported benefits of receiving AI suggestions while coding span the full range of typically investigated aspects of productivity, such as task time, product quality, cognitive load, enjoyment, and learning.

On Thursday, Google unveiled Gemini 1.5 Pro, which the company describes as delivering "dramatically enhanced performance" over the previous model. The company's AI trajectory -- viewed internally as increasingly critical for its future -- follows the unveiling of Gemini 1.0 Ultra last week, alongside the rebranding of the Bard chatbot (to Gemini) to align with the new model's more powerful and versatile capabilities. In an announcement blog post, Google CEO Sundar Pichai and Google DeepMind CEO Demis Hassabis try to balance assuring their audience about ethical AI safety while touting their models' rapidly advancing capabilities. "Our teams continue pushing the frontiers of our latest models with safety at the core," Pichai summarized. The company needs to emphasize safety for AI skeptics (including one former Google CEO) and government regulators.

"We think building models that can understand video, and understand all these very complex interactions of our world, is an important step for all future AI systems," says Tim Brooks, a scientist at OpenAI. OpenAI gave us a preview of Sora (which means sky in Japanese) under conditions of strict secrecy. In an unusual move, the firm would only share information about Sora if we agreed to wait until after news of the model was made public to seek the opinions of outside experts. OpenAI has not released a technical report or demonstrated the model actually working. And it says it won't be releasing Sora anytime soon.

The model was also able to identify moments of humor. When asked by the researchers to find a funny moment in the Apollo transcript, it picked out when astronaut Mike Collins referred to Armstrong as "the Czar." (Probably not the best line, but you get the point). In another demonstration, the team uploaded a 44-minute silent film featuring Buster Keaton and asked the AI to identify what information was on a piece of paper that, at some point in the movie, is removed from a character's pocket. In less than a minute, the model found the scene and correctly recalled the text written on the paper. Researchers also repeated a similar task from the Apollo experiment, asking the model to find a scene in the film based on a drawing, which it completed.

NVIDIA is doing very well for itself, so much so that the chip maker has overtaken Alphabet, Google's parent company, to become the third most valuable company in the United States, Reuters reports. The news comes almost immediately after NVIDIA pushed past Amazon in the rankings, with the company now valued at 1.83 trillion. Worldwide, it sits in fourth, behind American companies Microsoft ( 3.04 trillion) and Apple ( 2.84 trillion) and the Saudi Arabian state-owned oil company Saudi Aramco ( 2.07 trillion). AI's boom over the last year is largely to thank for NVIDIA's jump in valuation, with about 80 percent of the high-end chip market in its hands. It created the H100 chip, which powers LLMs at OpenAI, Amazon, Meta and more.

Machine learning models often excel on in-distribution (ID) data but struggle with unseen out-of-distribution (OOD) inputs. Most techniques for improving OOD robustness are not applicable to settings where the model is effectively a black box, such as when the weights are frozen, retraining is costly, or the model is leveraged via an API. Test-time augmentation (TTA) is a simple post-hoc technique for improving robustness that sidesteps black-box constraints by aggregating predictions across multiple augmentations of the test input. TTA has seen limited use in NLP due to the challenge of generating effective natural language augmentations. In this work, we propose LLM-TTA, which uses LLM-generated augmentations as TTA's augmentation function. LLM-TTA outperforms conventional augmentation functions across sentiment, toxicity, and news classification tasks for BERT and T5 models, with BERT's OOD robustness improving by an average of 4.30 percentage points without regressing average ID performance. We explore selectively augmenting inputs based on prediction entropy to reduce the rate of expensive LLM augmentations, allowing us to maintain performance gains while reducing the average number of generated augmentations by 57.76%. LLM-TTA is agnostic to the task model architecture, does not require OOD labels, and is effective across low and high-resource settings. We share our data, models, and code for reproducibility.

Selecting high-quality pre-training data is important for creating capable language models, but existing methods rely on simple heuristics. We introduce QuRating, a method for selecting pre-training data that captures the abstract qualities of texts which humans intuitively perceive. In this paper, we investigate four qualities - writing style, required expertise, facts & trivia, and educational value. We find that LLMs are able to discern these qualities and observe that they are better at making pairwise judgments of texts than at rating the quality of a text directly. We train a QuRater model to learn scalar ratings from pairwise judgments, and use it to annotate a 260B training corpus with quality ratings for each of the four criteria. In our experiments, we select 30B tokens according to the different quality ratings and train 1.3B-parameter language models on the selected data. We find that it is important to balance quality and diversity, as selecting only the highest-rated documents leads to poor results. When we sample using quality ratings as logits over documents, our models achieve lower perplexity and stronger in-context learning performance than baselines. Beyond data selection, we use the quality ratings to construct a training curriculum which improves performance without changing the training dataset. We extensively analyze the quality ratings and discuss their characteristics, biases, and wider implications.

The rapid advancement of Large Language Models (LLMs) has demonstrated their vast potential across various domains, attributed to their extensive pretraining knowledge and exceptional generalizability. However, LLMs often encounter challenges in generating harmful content when faced with problematic prompts. To address this problem, existing work attempted to implement a gradient ascent based approach to prevent LLMs from producing harmful output. While these methods can be effective, they frequently impact the model utility in responding to normal prompts. To address this gap, we introduce Selective Knowledge negation Unlearning (SKU), a novel unlearning framework for LLMs, designed to eliminate harmful knowledge while preserving utility on normal prompts. Specifically, SKU is consisted of two stages: harmful knowledge acquisition stage and knowledge negation stage. The first stage aims to identify and acquire harmful knowledge within the model, whereas the second is dedicated to remove this knowledge. SKU selectively isolates and removes harmful knowledge in model parameters, ensuring the model's performance remains robust on normal prompts. Our experiments conducted across various LLM architectures demonstrate that SKU identifies a good balance point between removing harmful information and preserving utility.