August 2021 Summaries

In this article, we discuss how AI21 Labs' Jurassic-1 language model can be customized to improve its performance on specific tasks such as news article topic classification. We demonstrate that by carefully crafting a prompt and providing the model with examples of correctly labeled articles, we can achieve significantly better accuracy than using the model in a zero-shot setting. Additionally, we show how using a custom model offers safety advantages over general-purpose models when it comes to mitigating prompt injection attacks. Finally, we discuss how even without any labeled data, one can still train a custom model by automatically labeling unlabeled examples with high confidence and using them for training.

The text discusses a multi-expert problem involving green energy companies, where data is fetched from Wiki API, calendar, and a database. It then computes the largest increase in share prices using a calculator and formats the answer with a language model. The process involves challenges such as training discrete experts, interfacing them with neural networks, routing among modules, etc. Further discussion includes advantages of Jurassic-X, like reading and updating databases in free language, enabling joining multiple databases, and updating data using natural language commands.

AI21 Studio and Jurassic-1 can be used to perform various language tasks such as summarization, simplifying text, generating ideas, writing code, working with tables, classification, accessing world knowledge, and more. These tools can be applied in content creation, marketing, ecommerce, creative writing, and other industries. Prompt engineering is a fast, easy, and flexible way to build demos or prototypes using AI models. Jurassic-X, a multi-expert language model, offers additional capabilities such as reading and updating databases, accessing current information, performing math operations, compositionality, handling dynamic information, and ensuring transparency and trust in the system.