With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications. Despite their powers, the intrinsic generative abilities of LLMs may prove insufficient for handling complex tasks, which necessitate a combination of task planning and the usage of external tools. In this paper, we first propose a structured framework tailored for LLM-based AI Agents and then discuss the crucial capabilities necessary for tackling intricate problems. Within this framework, we design two distinct types of agents (i.e., one-step agent and sequential agent) to execute the inference process. Subsequently, we instantiate the framework using various LLMs and evaluate their Task Planning and Tool Usage (TPTU) abilities on typical tasks. By highlighting key findings and challenges, our goal is to provide a helpful resource for researchers and practitioners to leverage the power of LLMs in their AI applications. Our study emphasizes the substantial potential of these models while also identifying areas that need more investigation and improvement. The code and resources will be available on GitHub.

Large Language Models (LLMs) are often misleadingly recognized as having a personality or a set of values. We argue that an LLM can be seen as a superposition of perspectives with different values and personality traits. LLMs exhibit context-dependent values and personality traits that change based on the induced perspective (as opposed to humans, who tend to have more coherent values and personality traits across contexts). We introduce the concept of perspective controllability, which refers to a model's affordance to adopt various perspectives with differing values and personality traits. In our experiments, we use questionnaires from psychology (PVQ, VSM, IPIP) to study how exhibited values and personality traits change based on different perspectives. Through qualitative experiments, we show that LLMs express different values when those are (implicitly or explicitly) implied in the prompt, and that LLMs express different values even when those are not obviously implied (demonstrating their context-dependent nature). We then conduct quantitative experiments to study the controllability of different models (GPT-4, GPT-3.5, OpenAssistant, StableVicuna, StableLM), the effectiveness of various methods for inducing perspectives, and the smoothness of the models' drivability. We conclude by examining the broader implications of our work and outline a variety of associated scientific questions. The project website is available at https://sites.google.com/view/llm-superpositions .

Theory of Mind (ToM) is a critical component of intelligence but its assessment remains the subject of heated debates. Prior research applied human ToM assessments to natural language processing models using either human-created standardized tests or rule-based templates. However, these methods primarily focus on simplistic reasoning and require further validation. Here, we leverage dynamic epistemic logic to isolate a particular component of ToM and to generate controlled problems. We also introduce new verbalization techniques to express these problems in English natural language. Our findings indicate that some language model scaling (from 70M to 6B and 350M to 174B) does not consistently yield results better than random chance. While GPT-4 demonstrates superior epistemic reasoning capabilities, there is still room for improvement. Our code and datasets are publicly available (https://huggingface.co/datasets/sileod/mindgames , https://github.com/sileod/llm-theory-of-mind )

Despite great strides in language-guided manipulation, existing work has been constrained to table-top settings. Table-tops allow for perfect and consistent camera angles, properties are that do not hold in mobile manipulation. Task plans that involve moving around the environment must be robust to egocentric views and changes in the plane and angle of grasp. A further challenge is ensuring this is all true while still being able to learn skills efficiently from limited data. We propose Spatial-Language Attention Policies (SLAP) as a solution. SLAP uses three-dimensional tokens as the input representation to train a single multi-task, language-conditioned action prediction policy. Our method shows an 80% success rate in the real world across eight tasks with a single model, and a 47.5% success rate when unseen clutter and unseen object configurations are introduced, even with only a handful of examples per task. This represents an improvement of 30% over prior work (20% given unseen distractors and configurations). We see a 4x improvement over baseline in mobile manipulation setting. In addition, we show how SLAPs robustness allows us to execute Task Plans from open-vocabulary instructions using a large language model for multi-step mobile manipulation. For videos, see the website: https://robotslap.github.io

Language models have been shown to perform remarkably well on a wide range of natural language processing tasks. In this paper, we propose LEAP, a novel system that uses language models to perform multi-step logical reasoning and incorporates explicit planning into the inference procedure. Explicit planning enables the system to make more informed reasoning decisions at each step by looking ahead into their future effects. Moreover, we propose a training strategy that safeguards the planning process from being led astray by spurious features. Our full system significantly outperforms other competing methods on multiple standard datasets. When using small T5 models as its core selection and deduction components, our system performs competitively compared to GPT-3 despite having only about 1B parameters (i.e., 175 times smaller than GPT-3). When using GPT-3.5, it significantly outperforms chain-of-thought prompting on the challenging PrOntoQA dataset. We have conducted extensive empirical studies to demonstrate that explicit planning plays a crucial role in the system's performance.

Anomaly detection (AD) plays a crucial role in many safety-critical application domains. The challenge of adapting an anomaly detector to drift in the normal data distribution, especially when no training data is available for the "new normal", has led to the development of zero-shot AD techniques. In this paper, we propose a simple yet effective method called Adaptive Centered Representations (ACR) for zero-shot batch-level AD. Our approach trains off-the-shelf deep anomaly detectors (such as deep SVDD) to adapt to a set of inter-related training data distributions in combination with batch normalization, enabling automatic zero-shot generalization for unseen AD tasks. This simple recipe, batch normalization plus meta-training, is a highly effective and versatile tool. Our theoretical results guarantee the zero-shot generalization for unseen AD tasks; our empirical results demonstrate the first zero-shot AD results for tabular data and outperform existing methods in zero-shot anomaly detection and segmentation on image data from specialized domains.

The newest model is capable of accepting much longer inputs than previous versions -- up to 300 pages of text, compared to the current limit of 50. This means that theoretically, prompts can be a lot longer and more complex, and responses might be more meaningful. OpenAI has also updated the data that GPT-4 Turbo is trained on. The company claims that the newest model now has knowledge about the world until April 2023. The previous version was only caught up until September 2021, although recent updates to the non-Turbo GPT-4 did include the ability to browse the internet to get the latest information. GPT-4 Turbo will also accept images as prompts directly in the chat box, wherein it can generate captions or provide a description of what the image depicts.

Artificial intelligence has predicted the majority of the world will be vegan by 2075. This is due to the record numbers of environmentally conscious Gen Z and Millennials ditching meat for plant-based options. Now, OpenAI's ChatGPT has shared details for the end of meat and dairy consumption after being asked to ' provide a timeline of the world going vegan starting in 2024 when Gen Z and Millennials raise awareness on animal agriculture.' The chatbot said the term'flexitarian' will become more common by 2027 as people adopt a more plant-based diet worldwide. And by 2073, 'the world is almost entirely vegan' because it is the typical diet among the current generation in 2055.

Users of the free version of ChatGPT or ChatGPT were not included. OpenAI is not the first to offer such legal protection, though as the creator of the wildly popular ChatGPT, which Altman said has 100 million weekly users, it is a heavyweight player in the industry. Google, Microsoft and Amazon have made similar offers to users of their generative AI software. Getty Images, Shutterstock and Adobe have extended similar financial liability protection for their image-making software. Altman made the announcement at OpenAI's first ever developer conference, meant to attract programmers working with ChatGPT.

It's been nearly a year since ChatGPT's public debut and its evolution since then has been nothing short of extraordinary. In just over 11 months, OpenAI's chatbot has gained the ability to write programming code, process information between multiple modalities and expand its reach across the internet with APIs. During OpenAI's 2023 Dev Day keynote address Monday, CEO Sam Altman and other executives took to the stage in San Francisco to unveil the chatbot's latest iteration, ChatGPT-4 Turbo, as well as an exciting new way to bring generative AI technology to everybody, regardless of their coding capability: GPTs! GPTs are small, task-specific iterations of ChatGPT. Think of them like the single-purpose apps and features on your phone but instead of them maintaining a timer or stop watch, or a digital assistant transcribing your voice instructions into a shopping list, GPTs will do, basically anything you train them to. OpenAI offers up eight examples of what GPT's can be used for, anything from a digital kitchen assistant that suggests recipes based on whats in your pantry to a math mentor to help your kids through their homework to a Sticker Wiz that will, "turn your wildest dreams into die-cut stickers, shipped right to your door."