Transforming Industries with Generative AI: An AI21 and AWS Hackathon
The AI21 Hackathon with AWS highlighted GenAI’s potential to revolutionize various industries, especially when taking advantage of AI21 and AWS’ joint capabilities.
The AI21 Hackathon with AWS was an exciting event that brought experts together to explore the latest trends and challenges in Generative AI (GenAI) through real-world use cases, including customer support, grounded content generation, and guardrails for Large Language Models (LLMs).
With over 50 AWS Solutions Architects and other hand-picked AWS GenAI practitioners in attendance, the hackathon provided an opportunity to gain hands-on experience in using AI to solve complex problems and to learn from experts in the industry.
With AWS executive sponsorship from Greg Pearson, VP of AWS Global Sales and Francessca Vasquez, VP of AWS ProServe and GenAI Innovation Center, the event was a thrilling demonstration of GenAI’s transformative potential across various industry sectors.
The GenAI Landscape
The AI21 team presented how GenAI is being used today in various industries, such as retail and financial services, and how these trends affect the architecture for deploying GenAI pipelines in the real world. They also shared best practices for using and selecting AI21 models, such as prompt engineering guidelines, and best practices for avoiding hallucinations and inaccuracies when using LLMs.
The AI21 team also covered use cases across the healthcare, retail, and finance industries where Task Specific Models (TSM)—trained to execute precise tasks—are a more efficient and reliable choice than a general-purpose LLM.
As AI21 CEO Ori Goshen shared at re:Invent 2023, Task Specific Models allow for “accurate, comprehensive, and grounded responses,” essential “for minimizing hallucinations.” Built with out-of-the-box precise functionality, these models eliminate the need for a lengthy prompt engineering process, reducing the time-to-value and allowing enterprises to scale deployment.
During the hackathon, AWS teams showed how they could use AI21 LLM and TSM models for various GenAI use cases, including:
Guardrails for large language models: Develop prompts and underlying GenAI mechanisms that are resilient against harmful content injection.
Grounded content generation using GenAI models: Generate commercial content (e.g. product descriptions) using product and other raw data.
Improve customer support with Generative AI: Enhance customer support by using AI21 GenAI models to analyze previously resolved tickets and provide accurate current case resolutions.
Structured summarization of multiple documents: Generate summaries of topics where the source data is 1) scattered across many different documents and 2) comes from a large corpus of data.
GenAI for advertising creation: Develop a GenAI platform for creating dynamic advertising content, which automates and enhances various aspects of advertising, such as: idea generation, content creation, localization, targeted advertising, and social media integration.
Structured summarization from call transcripts: Extract or summarize data from conversation histories that remains consistent with the original transcript.
Key Themes and Learnings
A key takeaway from the hackathon was the importance for LLMs to remain grounded in enterprise data. In all of the use cases, teams did their best to assure GenAI outputs that were both high quality and grounded in the input data, using Retrieval Augmented Generation (RAG).
For example, the “Guardrails for large language models” project—in which a “blue” team built a secure system, while a “red” team attempted to undermine it— leveraged prompt engineering techniques to help ensure that the red team’s prompt injection attacks were ignored, as well as ensuring that responses remain on topic. A second key takeaway was the judicious use of Task Specific Models. AI21’s TSMs support complex workflows, and—crucially—are guaranteed to remain on-task. For example, the Contextual Answers TSM can be used in tandem with the Jurassic-2 LLM to power a customer chatbot, searching a company's organizational knowledge base to offer grounded responses in natural language.
A third takeaway was integrating AI21 models into AWS native services, with TSMs now integrated with a number of AWS services, such as Amazon Bedrock, Amazon SageMaker, Amazon OpenSearch, Amazon Lex, AWS Lambda, and others.
AWS x AI21 Hackathon Summary
Amidst the backdrop of a highly dynamic field, the AWS Hackathon and AI21 event offered attendees valuable insights into the latest GenAI trends and challenges. In addition to talks from industry experts, attendees also gained valuable hands-on experience directing GenAI to solve complex problems, with a particular (and timely) focus on creating LLM guardrails, improving customer support, and generating grounded content.
The event also looked forward to the next stages of GenAI, highlighting the practice of adopting TSMs—instead of more multi-purpose LLMs—to perform sophisticated workflows with guaranteed on-task performance.
Between the talks and the exciting outcomes of the hackathon, the event highlighted the power of GenAI and its potential to revolutionize various industries, especially when taking advantage of AI21 and AWS’ joint capabilities.
ABOUT THE AUTHOR
Principal Solution Architect
Stay up to date with the latest research and updates from AI21 Labs.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
In August 2021 we released Jurassic-1, a 178B-parameter autoregressive language model. We’re thankful for the reception it got – over 10,000 developers signed up, and hundreds of commercial applications are in various stages of development. Mega models such as Jurassic-1, GPT-3 and others are indeed amazing, and open up exciting opportunities. But these models are also inherently limited. They can’t access your company database, don’t have access to current information (for example, latest COVID numbers or dollar-euro exchange rate), can’t reason (for example, their arithmetic capabilities don’t come close to that of an HP calculator from the 1970s), and are prohibitively expensive to update. A MRKL system such as Jurassic-X enjoys all the advantages of mega language models, with none of these disadvantages. Here’s how it works.
Compositive multi-expert problem: the list of “Green energy companies” is routed to Wiki API, “last month” dates are extracted from the calendar and “share prices” from the database. The “largest increase“ is computed by the calculator and finally, the answer is formatted by the language model.
There are of course many details and challenges in making all this work - training the discrete experts, smoothing the interface between them and the neural network, routing among the different modules, and more. To get a deeper sense for MRKL systems, how they fit in the technology landscape, and some of the technical challenges in implementing them, see our MRKL paper. For a deeper technical look at how to handle one of the implementation challenges, namely avoiding model explosion, see our paper on leveraging frozen mega LMs.
A further look at the advantages of Jurassic-X
Even without diving into technical details, it’s easy to get a sense for the advantages of Jurassic-X. Here are some of the capabilities it offers, and how these can be used for practical applications.
Reading and updating your database in free language
Language models are closed boxes which you can use, but not change. However, in many practical cases you would want to use the power of a language model to analyze information you possess - the supplies in your store, your company’s payroll, the grades in your school and more. Jurassic-X can connect to your databases so that you can ‘talk’ to your data to explore what you need- “Find the cheapest Shampoo that has a rosy smell”, “Which computing stock increased the most in the last week?” and more. Furthermore, our system also enables joining several databases, and has the ability to update your database using free language (see figure below).
Jurassic-X enables you to plug in YOUR company's database (inventories, salary sheets, etc.) and extract information using free language
AI-assisted text generation on current affairs
Language models can generate text, yet can not be used to create text on current affairs, because their vast knowledge (historic dates, world leaders and more) represents the world as it was when they were trained. This is clearly (and somewhat embarrassingly) demonstrated when three of the world’s leading language models (including our own Jurassic-1) still claim Donald Trump is the US president more than a year after Joe Biden was sworn into office. Jurassic-X solves this problem by simply plugging into resources such as Wikidata, providing it with continuous access to up-to-date knowledge. This opens up a new avenue for AI-assisted text generation on current affairs.
Who is the president of the United States?
Joe Biden is the 46th and current president
Jurassic-X can assist in text generation on up-to-date events by combining a powerful language model with access to Wikidata
Performing math operations
A 6 year old child learns math from rules, not only by memorizing examples. In contrast, language models are designed to learn from examples, and consequently are able to solve very basic math like 1-, 2-, and possibly 3- digit addition, but struggle with anything more complex. With increased training time, better data and larger models, the performance will improve, but will not reach the robustness of an HP calculator from the 1970s. Jurassic-X takes a different approach and calls upon a calculator whenever a math problem is identified by the router. The problem can be phrased in natural language and is converted by the language model to the format required by the calculator (numbers and math operations). The computation is performed and the answer is converted back into free language. Importantly (see example below) the process is made transparent to the user by revealing the computation performed, thus increasing the trust in the system. In contrast, language models provide answers which might seem reasonable, but are wrong, making them impractical to use.
The company had 655400 shares which they divided equally among 94 employees. How many did each employee get?
Each employee got 7000 stocks
(No answer provided)
6972.3 X= 655400/94
Jurassic-X can answer non-trivial math operations which are phrased in natural language, made possible by the combination of a language model and a calculator
Solving simple questions might require multiple steps, for example - “Do more people live in Tel Aviv or in Berlin?” requires answering: i. What is the population of Tel-Aviv? ii. What is the population of Berlin? iii. Which is larger? This is a highly non-trivial process for a language model, and language models fail to answer this question (see example). Moreover, the user can’t know the process leading to the answers, hence is unable to trust them. Jurassic-X can decompose such problems into the basic questions, route each to the relevant expert, and put together an answer in free language. Importantly, Jurassic-X not only provides the correct answer but also displays the steps taken to reach it, increasing the trust in the system.
Do more people live in Tel Aviv or in Berlin?
There are more people living in Tel Aviv than in Berlin.
Berlin and Tel Aviv are roughly the same size
(First hit is a comparison between Tel Aviv and Berlin)
More people live in Berlin than in Tel-Aviv
[‘Return population of Tel Aviv’; Return population of Berlin’; Return which is bigger between #1 and #2’] Step 1: Population of Tel Aviv. Result - 451523. Step 1: Population of Berlin. Result - 3664088. Step 3: Which is bigger, #1 or #2. Result - Berlin.
Jurassic-X breaks down compositional questions, answers the basic sub-questions, and puts together the answer. Importantly, this process is transparent to the user greatly increasing the trust in the system
Dynamic information (like weather and currency exchange rates)
Certain types of information change continuously - weather, currency exchange rates, share values and more. Such information will never be captured by language models, yet can easily be handled by Jurassic-X by integrating it with a reliable source of information. We performed a proof-of-concept on two such features - weather and currency exchange rates, and the design enables quick integration with more sources to solve your use-case. Weather - a loosely phrased question about the weather elicits an answer from all language models, where language models always return the same answer, regardless of when the question was asked (funny, right?), while Jurassic-X provides an answer based on the actual weather prediction.
I’m going to be in New-York in 3 days. Should I pack my umbrella?
Yes, you should pack your umbrella.
Yes, you should. The weather forecast is rain.
(Links to weather websites)
Yes, you should pack your umbrella, because in New York in 3 days there will be broken clouds and the temperature will be -2 degrees.
Currency exchange rates change much faster than weather predictions, yet the Jurassic-X concept - a language model connected to a reliable source of information - easily solves this problem as well.
How much Moroccan money will I get for 100 bucks?
100 moroccan dirhams is about 27$.
How much is 100 dollars in moroccan money?
100 dirhams = 10.75 dollars
100 USD = 934.003 MAD
Jurassic-X combines a language model with access to APIs with continuously changing information. This is demonstrated for weather forecasts and currency exchange rates, and can easily be extended to other information sources
Transparency and trust
Transparency is a critical element that is lacking in language models, preventing a much wider adoption of these models. This lack of transparency is demonstrated by the answers to the question - “Was Clinton ever elected as president of the United States?”. The answer, of course, depends on which Clinton you have in mind, which is only made clear by Jurassic-X that has a component for disambiguation. More examples of Jurassic-X’s transparency were demonstrated above - displaying the math operation performed to the user, and the answer to the simple sub-questions in the multi-step setting.
Was Clinton ever elected president of the United States?
No, Clinton was never elected as president of the United States.
Clinton was elected president in the 1992 presidential elections…
Bill Clinton was elected president.
Jurassic-X is designed to be more transparent by displaying which expert answered which part of the question, and by presenting the intermediate steps taken and not just the black-box response
That's it, you get the picture. The use cases above give you a sense for some things you could do with Jurassic-X, but now it's your turn. A MRKL system such as Jurassic-X is as flexible as your imagination. What do you want to accomplish? Contact us for early access
Your submission has been received!
Oops! Something went wrong while submitting the form.