Generative AI enables powerful new capabilities, but they come with some serious limitations that you'll have to tackle to ship a reliable application or agent. Luckily, experts in the field are already hard at work compiling a library of tried-and-true design patterns to address the challenges you're likely to encounter when building applications using LLMs and other GenAI models--hallucinations, nondeterministic answers, and knowledge cutoffs among them. You'll find 31 of the most essential here.
Authors Valliappa Lakshmanan and Hannes Hapke codify advances in research and real-world experience into advice that you can readily incorporate into your projects. Each detailed explanation includes a description of the problem, a proven pattern to solve it, an example, and a discussion of potential trade-offs. Whether you read it cover to cover for inspiration or use it as a daily reference, this practical guide will help you troubleshoot whatever problems may arise.
- Design around the limitations of LLMs, such as hallucination and nondeterminism
- Force LLMs to generate text that follows a specific style or grammar
- Maximize creativity while balancing different types of risk
- Extend the capability of an LLM beyond just content creation
- Use patterns together to solve a variety of different use cases
Sprache
Verlagsort
Produkt-Hinweis
Broschur/Paperback
Klebebindung
ISBN-13
979-8-3416-2266-1 (9798341622661)
Copyright in bibliographic data and cover images is held by Nielsen Book Services Limited or by the publishers or by their respective licensors: all rights reserved.
Schweitzer Klassifikation
Valliappa (Lak) Lakshmanan works closely with management teams across a range of enterprises to help them employ data and AI-driven innovation to grow their businesses. Previously, he was the Director for Data Analytics and AI Solutions on Google Cloud and a Research Scientist at NOAA. He co-founded Google's Advanced Solutions Lab and is the author of several O'Reilly books and Coursera courses. He was elected a Fellow of the American Meteorological Society (the highest honor offered by the AMS) for pioneering machine learning algorithms in severe weather prediction.