Eyyy Code GenAI is here to stay and it's increasing its adoption and perfomance dramatically !!!!

But, are LLMs as good as they seem ? Specially if we are thinking on serious production projects.....

In this talk I will show data about the real state of projects in terms of quality and security, and how 5 different main LLMs perform in code generation in terms of accuracy, quality and complexity.

Finally I will present some good practices that can help your assistants to be "potentially" better in their responses.

Join me in a motivational talk based on reality and facts and not on trends.

Production wise usage of Code GenAI is not a trivial thing. It's important to know the real and whole context about LLMs and how we can help them to help us.