Hi! Just to make sure, this is just a taking-note, storyteller-type log for the AWS Quiz as part of pursuing my career as a Data Engineer (what's really funny is I started from cloud engineering stuff 😅).
I'm the forgetful type, so taking notes is a must.
This answer is really based on the learning at:
https://awseducate.instructure.com/courses/1108
How can I explain Gen-AI to company executive members? Just use simple words and throw away the tech stuff like: creating new content and ideas, conversations, stories, images, videos, and music.
Now the CTO wants to ask about how the technology works, and whether Amazon has experience with Gen AI. Let's start explaining with:
Gen AI is powered by large ML models called foundation models, or FMs.
When using FMs, customers can use the same pretrained model to adapt to multiple tasks.
Ok, now your team wants to have an AI assistant for generating code.
Ask which AWS service can be embedded in an IDE, turns out, Amazon Q Developer can handle this easily. But it's not just your team that wants to be more productive, other employees want to boost productivity too, with things like code generation and conversational search, so Amazon Q Developer is like swiss-army-knife for productivity.
Your team has a machine learning model for a client. The client asks to deploy it on AWS because they really like AWS. So your team does some brainstorming and finds out that AWS Trainium can help host ML training.
The client also needs more ordinary machine learning models, and Amazon SageMaker JumpStart has a list of machine learning use cases that can be deployed readily on the go.
Back to generative AI, in order to generate images from a text prompt, you must use a Foundation Model (FM) called Multimodal FMs. Multimodal FMs can understand and generate both text and images.
What prompt engineering really is: prompt engineering is the process of designing and refining the instructions for a language model to generate specific types of output.
AI can really enhance customer experience — like with chatbots and virtual assistants. These two use cases are just a couple of examples, and there are many more you can try.
Top comments (0)