Close

GenAI solves everything - Trust but Validate (Human versus AI)

(TM)

Stream: The Courtyard
Time: 16:45 - 17:30


Presentation

In this session, Michelle will share a real world story of how five humans were set an assessment to modify a sample Java program. Learn how a Large Language Model may not get the assessment answer question right first time! The session will also delve into human versus LLM on assembler code.

Attachments

TM Attachments

Speakers


  • Michelle Harris at Macro 4 Limited
  • Email: michelle.harris@macro4.com

    Feedback

    Click here to give some Feedback so we can make it even better next year!