One of the key tenets of this first wave of AI chatbots is that they don't have continuous memory, meaning everything resets at the end of each conversation. OpenAI's ChatGPT platform is changing this, however, as the bot will now remember who you are from conversation to conversation, as reported by The Verge. This is both a tantalizing and risky prospect. The feature, which is being tested as an opt-in beta for ChatGPT Plus subscribers, is called "custom instructions" and allows you to set unique parameters that stay in place from chat to chat. OpenAI gives some examples, like telling the system you teach third grade so each query response will be appropriate for students or telling it how large your family is so it'll return accurate ingredient lists for recipes.

The existential risks posed by artificial intelligence (AI) are now widely recognized. After hundreds of industry and science leaders warned that "mitigating the risk of extinction from AI should be a global priority alongside other societal-scale risks such as pandemics and nuclear war," the U.N. Secretary-General recently echoed their concern. So did the prime minister of the U.K., who is also investing 100 million pounds into AI safety research that is mostly meant to prevent existential risk. Other leaders are likely to follow in recognizing AI's ultimate threat. In the scientific field of existential risk, which studies the most likely causes of human extinction, AI is consistently ranked at the top of the list.

Google is testing an artificial intelligence tool that can write news articles, in the latest evidence that the technology has the potential to transform white-collar professions. The product, known as Genesis, uses AI technology to absorb information such as details of current events and then create news stories. The tool was pitched to the New York Times, the Washington Post, and the Wall Street Journal's owner, News Corp as a "helpmate", according to the New York Times. Google said it was in the early stages of exploring the AI tool, which it said could assist journalists with options for headlines or different writing styles. It stressed that the technology was not intended to replace journalists.

In the early weeks of 2023, as worry about ChatGPT and other artificial intelligence tools was ratcheting up dramatically in the public conversation, a tweet passed through the many interlocking corners of Book Twitter. "Imagine if every Book is converted into an Animated Book and made 10x more engaging," it read. Huge opportunity here to disrupt Kindle and Audible." The tweet's author, Gaurav Munjal, cofounded Unacademy, which bills itself as "India's largest learning platform"--and within the edtech context, where digitally animated books can be effective teaching tools, his suggestion might read a certain way. But to a broader audience, the sweeping proclamation that AI will make "every" book "10x more engaging" seemed absurd, a solution in search of a problem, and one predicated on the idea that people who choose to read narrative prose (instead of, say, watching a film or playing a game) were somehow bored or not engaged with their unanimated tomes.

Apple is working on artificial intelligence (AI) offerings similar to OpenAI's ChatGPT and Google's Bard, Bloomberg News has reported, sending its shares up as much as 2 percent to a record high. The iPhone maker has built its own framework, known as Ajax, to create large language models (LLMs) and is also testing a chatbot that some engineers call "Apple GPT", the report said on Wednesday, quoting people with knowledge of the matter. The company did not respond to a request for comment from the Reuters news agency. Apple has so far held back from any big moves in AI and even avoided mentioning the buzzword at its developer conference in June – in stark contrast to other tech giants such as Alphabet and Microsoft, which have made bold moves to incorporate the breakthrough technology. Shares of Microsoft, Nvidia and Alphabet dropped more than 1 percent after the report.

Author Note We have no known conflict of interest to disclose. Correspondence concerning this article should be addressed to Hyemin Han, University of Alabama, Box 872031, Tuscaloosa, AL 35487, United States. Email: hyemin.han@ua.edu 2 Potential Benefits of Employing Large Language Models in Research in Moral Education and Development Abstract Recently, computer scientists have developed large language models (LLMs) by training prediction models with large-scale language corpora and human reinforcements. The LLMs have become one promising way to implement artificial intelligence with accuracy in various fields. Interestingly, recent LLMs possess emergent functional features that emulate sophisticated human cognition, especially in-context learning and the chain of thought, which were unavailable in previous prediction models. In this paper, I will examine how LLMs might contribute to moral education and development research. To achieve this goal, I will review the most recently published conference papers and ArXiv preprints to overview the novel functional features implemented in LLMs. I also intend to conduct brief experiments with ChatGPT to investigate how LLMs behave while addressing ethical dilemmas and external feedback. The results suggest that LLMs might be capable of solving dilemmas based on reasoning and revising their reasoning process with external input. Furthermore, a preliminary experimental result from the moral exemplar test may demonstrate that exemplary stories can elicit moral elevation in LLMs as do they among human participants. I will discuss the potential implications of LLMs on research on moral education and development with the results. Keywords: Large language models, Artificial intelligence, Moral reasoning, Moral exemplar, Simulation 3 Introduction One of the most impactful recent developments in computer science is large language models (LLMs) (Grossmann et al., 2023), which implement advanced artificial intelligence.

Reconstructing accurate 3D scenes from images is a long-standing vision task. Due to the ill-posedness of the single-image reconstruction problem, most well-established methods are built upon multi-view geometry. State-of-the-art (SOTA) monocular metric depth estimation methods can only handle a single camera model and are unable to perform mixed-data training due to the metric ambiguity. Meanwhile, SOTA monocular methods trained on large mixed datasets achieve zero-shot generalization by learning affine-invariant depths, which cannot recover real-world metrics. In this work, we show that the key to a zero-shot single-view metric depth model lies in the combination of large-scale data training and resolving the metric ambiguity from various camera models. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problems and can be effortlessly plugged into existing monocular models. Equipped with our module, monocular models can be stably trained with over 8 million images with thousands of camera models, resulting in zero-shot generalization to in-the-wild images with unseen camera settings. Experiments demonstrate SOTA performance of our method on 7 zero-shot benchmarks. Notably, our method won the championship in the 2nd Monocular Depth Estimation Challenge. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images, paving the way for plausible single-image metrology. The potential benefits extend to downstream tasks, which can be significantly improved by simply plugging in our model. For example, our model relieves the scale drift issues of monocular-SLAM (Fig. 1), leading to high-quality metric scale dense mapping. The code is available at https://github.com/YvanYin/Metric3D.

Language models, primarily transformer-based ones, obtained colossal success in NLP. To be more precise, studies like BERT in NLU and works such as GPT-3 for NLG are very crucial. DNA sequences are very close to natural language in terms of structure, so if the DNA-related bioinformatics domain is concerned, discriminative models, like DNABert, exist. Yet, the generative side of the coin is mainly unexplored to the best of our knowledge. Consequently, we focused on developing an autoregressive generative language model like GPT-3 for DNA sequences. Because working with whole DNA sequences is challenging without substantial computational resources, we decided to carry out our study on a smaller scale, focusing on nucleotide sequences of human genes, unique parts in DNA with specific functionalities, instead of the whole DNA. This decision did not change the problem structure a lot due to the fact that both DNA and genes can be seen as 1D sequences consisting of four different nucleotides without losing much information and making too much simplification. First of all, we systematically examined an almost entirely unexplored problem and observed that RNNs performed the best while simple techniques like N-grams were also promising. Another beneficial point was learning how to work with generative models on languages we do not understand, unlike natural language. How essential using real-life tasks beyond the classical metrics such as perplexity is observed. Furthermore, checking whether the data-hungry nature of these models can be changed through selecting a language with minimal vocabulary size, four owing to four different types of nucleotides, is examined. The reason for reviewing this was that choosing such a language might make the problem easier. However, what we observed in this study was it did not provide that much of a change in the amount of data needed.

We investigate the mathematical capabilities of two iterations of ChatGPT (released 9-January-2023 and 30-January-2023) and of GPT-4 by testing them on publicly available datasets, as well as hand-crafted ones, using a novel methodology. In contrast to formal mathematics, where large databases of formal proofs are available (e.g., the Lean Mathematical Library), current datasets of natural-language mathematics, used to benchmark language models, either cover only elementary mathematics or are very small. We address this by publicly releasing two new datasets: GHOSTS and miniGHOSTS. These are the first natural-language datasets curated by working researchers in mathematics that (1) aim to cover graduate-level mathematics, (2) provide a holistic overview of the mathematical capabilities of language models, and (3) distinguish multiple dimensions of mathematical reasoning. These datasets also test whether ChatGPT and GPT-4 can be helpful assistants to professional mathematicians by emulating use cases that arise in the daily professional activities of mathematicians. We benchmark the models on a range of fine-grained performance metrics. For advanced mathematics, this is the most detailed evaluation effort to date. We find that ChatGPT can be used most successfully as a mathematical assistant for querying facts, acting as a mathematical search engine and knowledge base interface. GPT-4 can additionally be used for undergraduate-level mathematics but fails on graduate-level difficulty. Contrary to many positive reports in the media about GPT-4 and ChatGPT's exam-solving abilities (a potential case of selection bias), their overall mathematical performance is well below the level of a graduate student. Hence, if your goal is to use ChatGPT to pass a graduate-level math exam, you would be better off copying from your average peer!

Open-domain question answering (QA) tasks usually require the retrieval of relevant information from a large corpus to generate accurate answers. We propose a novel approach called Generator-Retriever-Generator (GRG) that combines document retrieval techniques with a large language model (LLM), by first prompting the model to generate contextual documents based on a given question. In parallel, a dual-encoder network retrieves documents that are relevant to the question from an external corpus. The generated and retrieved documents are then passed to the second LLM, which generates the final answer. By combining document retrieval and LLM generation, our approach addresses the challenges of open-domain QA, such as generating informative and contextually relevant answers. GRG outperforms the state-of-the-art generate-then-read and retrieve-then-read pipelines (GENREAD and RFiD) improving their performance at least by +5.2, +4.2, and +1.6 on TriviaQA, NQ, and WebQ datasets, respectively. We provide code, datasets, and checkpoints \footnote{\url{https://github.com/abdoelsayed2016/GRG}}