Speaker

Tom Cools
Timefold

Developer Relations Engineer for Timefold, Java Champion and leader of the Belgian Java User Group. Tom has a decade worth of experience delivering systems and loves to share not only knowledge but also passion for our craft.

You can read more at his blog (http://www.tomcools.be) or follow him on Twitter (@TCoolsIT).

View
LLMs can't optimize schedules, but AI can!
Byte size (BEGINNER level)
Zaal 10

GenAI and LLMs are awesome and are perceived by some as the solution for everything. However, when it comes to common tasks like creating schedules they tend to produce unreliable or nonsensical results.

Fortunately, there’s a lesser known branch of AI that excels at complex scheduling: mathematical optimization. We'll discuss why LLMs fail at these tasks, how constraint solving provides a robust alternative and how you can leverage the Open Source Timefold Solver so you don't even have to worry about the math.

You'll see this form of AI in action and walk away with a powerful new tool for your problem-solving toolbox.

More

Searching for speaker images...