Developing with Nondeterministic APIs
Focused View
Morten Rand-Hendriksen
27:17
14 View
01 - Developing with nondeterministic APIs.mp4
01:01
01 - What is nondeterminism in AI APIs.mp4
02:27
02 - Prompting for consistency.mp4
01:18
03 - Giving the AI options to choose from.mp4
01:29
04 - Providing reference materials.mp4
01:11
01 - Getting consistency in probablilistic systems.mp4
00:59
02 - Bringing the temperature down.mp4
02:12
03 - Bringing top-p down.mp4
01:44
04 - Setting a seed value.mp4
01:05
05 - Activating JSON output.mp4
02:09
06 - Using an advanced response template.mp4
01:09
07 - Using function calling.mp4
01:45
01 - Finding consistency at scale.mp4
00:56
02 - Creating a fine-tuned model.mp4
03:00
03 - Using a grounded fact source.mp4
01:31
04 - Using semantic cache for optimal performance.mp4
01:22
01 - Using AI only when necessary.mp4
01:59
Description
AI APIs produce nondeterministic output meaning the same prompt may produce different results every time it’s run. This poses unique challenges to developers because traditional software development is based on the premise that systems produce consistent and therefore deterministic outputs. In this course you’ll learn strategies for how to mitigate these unique challenges to meld traditional software development with modern AI tools.
More details
User Reviews
Rating
average 0
Focused display
Morten Rand-Hendriksen
Instructor's CoursesSince joining forces with lynda.com (now LinkedIn Learning) in 2010, I've 60+ published courses on WordPress, front end web design and development, and web standards, reaching hundreds of thousands of viewers from all over the world. I also contribute to the web community as a public speaker, author, educator, web developer, and design philosopher.
I help the web make sense by helping people understand and get the most out of the web, and contribute to the debates about ownership and democratization of information, design philosophy, and the open web.

Linkedin Learning
View courses Linkedin LearningLinkedIn Learning is an American online learning provider. It provides video courses taught by industry experts in software, creative, and business skills. It is a subsidiary of LinkedIn. All the courses on LinkedIn fall into four categories: Business, Creative, Technology and Certifications.
It was founded in 1995 by Lynda Weinman as Lynda.com before being acquired by LinkedIn in 2015. Microsoft acquired LinkedIn in December 2016.
- language english
- Training sessions 17
- duration 27:17
- English subtitles has
- Release Date 2024/05/01