The idea is to use LLMs to generate glue code between applications/APIs; making it easy to connect different apps together (e.g., you can scrape websites directly into google sheets; get it to classify gmails, etc.)
Experience so far -- model quality really matters. Claude Opus does surprisingly a lot better than GPT4Turbo. Creating good abstractions matter. Syntax, type checking matters. Models do get stuck sometimes, and GPT4 often gets lazy (placeholder/comments instead of actual code).
This specialization incorporates hands-on labs. You will need a Google account (a Gmail account will work just fine) and will be required to sign up for a Google Cloud Platform free trial account. Your free trial is limited to 60 days or $300 worth in credits, whichever is reached first. For this reason, our specialization is designed to be completed within four weeks.
These hands on components will let you apply the skills you learn in the video lectures. Projects will incorporate topics such as Google Compute done within the codelabs. what they can expect to get out of those.
=====
This four-course accelerated specialization introduces you to the implementation of application environments and public cloud infrastructure using Google Cloud Platform. Through a combination of video lectures, quizzes, and hands-on labs, you'll learn how to deploy cloud infrastructure components such as networks, systems, and applications. This specialization is designed to give participants a robust hands-on experience and is primarily lab-focused.
This specialization is intended for Systems Operations professionals and Cloud Architects using Google Cloud Platform to design, create, or migrate application environments and infrastructure.
This specialization is unique in that you'll actually get to work within the Google Cloud Platform production environment, develop external applications, and achieve an end-of-specialization certificate.
1. Course Recommendations. We use low rank matrix factorization approaches to do recommendations, and are also looking into integrating other information sources (such as your career goals).
2. Search. Results are relevance ranked based on a variety of signals from popularity to learner preferences.
3. Learning. There's a lot of untapped potential here. We have done some research into peer grading de-biasing [1] and worked with folks at Stanford on studying how people learn to code [2].
We recently co-organized a NIPS workshop on ML for Education: http://ml4ed.cc . There's untapped potential in using ML to improve education.
I'm curious, because this is something that I was interested in doing for brick and mortar universities, what aspects do you use to do your recommendations. That is, is it just a x/5 rating per user that is thrown into a latent factor model, or do you do anything else (like dividing course 'grade' vs. opinion along two axes manually?)
Are you just weighing different scores on 2? That would be heuristics more precisely. Not really learning; Unless you update the weights my minimizing some cost function.
Have you taken a Coursera course? Come join us to make them better and build the future of learning. Your work can have a significant positive impact on the lives of millions.
We use react, scala/play, cassandra, kafka, swift, kotlin, and other technologies across our stack.
Have you taken a Coursera course? Come join us to make them better and build the future of learning.
We are building out our enterprise, learning experience, growth, and infrastructure teams.
We are looking for frontend engineers for both product development and also infrastructure, that will help develop our modular web architecture based on react/flux with isomorphic javascript.
We also use scala/play, cassandra, kafka, swift, kotlin, and other technologies across our stack. If you're interested, apply and we'll be in touch!
Coursera is growing! Have you taken a Coursera course? Come join us to make them better and build the future of learning.
We have a great engineering team and are looking for frontend, backend, and mobile engineers to join us. We use scala/play, react, cassandra, and other technologies across our stack.
Making learning work well online is both challenging and extremely rewarding.
reply