DeepLearning.AI is making world-class AI education accessible to people around the globe. Founded by Andrew Ng, a global leader in AI, the company offers online courses and hands-on training in artificial intelligence, deep learning, and machine learning.

DeepLearning.AI

DeepLearning.AI is making a world-class AI education accessible to people around the globe. DeepLearning.AI was founded by Andrew Ng, a global leader in AI. 

When building applications with generative AI, model behavior is less predictable than traditional software. That’s why automated testing makes a big difference in saving you development time and cost. 

We teamed with CircleCI to bring you a new course: Automated Testing for LLMOps.

In this course, you’ll learn to build a continuous integration workflow to evaluate your LLM applications at every iteration, to catch and fix bugs early, and ship faster and more efficiently.  

Instructed by Rob Zuber, CircleCI CTO, this course is free to join! 

Get started: https://hubs.la/Q02hy3KN0


This week’s AI news: 

🔍 A neural network helps detect early signs of pancreatic cancer
📊 Report explores AI's impact on jobs
📐 A new system generates high-level geometry proofs

Plus: Andrew Ng shares insights from his participation at the World Economic Forum.

Read #TheBatch: https://hubs.la/Q02hDh150

Our new course on Automated Testing for LLMOps dropped on DeepLearning.AI today! Learn to apply your CI skills to LLM-based applications.

Making small changes in LLM-based applications, including single words in prompts, can have outsized side effects. For example, what if a teammate updates a prompt to try to make the LLM output sound more interesting, but this causes it to hallucinate more? Continuous Integration with LLM-appropriate automated testing tools helps avoid these problems and lets you ship faster and with greater confidence.

Check it out and learn how to:
👉 Build a CI workflow to automatically evaluate each change to your application
👉 Write model-graded evaluations to expand your toolkit for problems like hallucinations, data drift, and harmful or offensive output
👉 Optimize your CI workflow increase coverage as you get closer to deployment

Everything we've learned about Continuous Integration and rapid delivery can be especially helpful for AI-enabled applications given the potential for unintended side effects from seemingly small changes.

Huge thanks to Andrew Ng, Eddy Shyu, Esmaeil Gargari, Jacob Schmitt, and Michael Webster for making it happen!

Find the course here: https://lnkd.in/gAs9pZ5b

New short course on Automated Testing for LLMOps, by CircleCI's CTO Rob Zuber! This teaches you how to adapt some key ideas from CI (continuous integration), which has been a pillar of efficient software engineering, to building LLM-based applications.

Tweaking an LLM-based app to improve it -- say by modifying a prompt -- can have unexpected side effects. For example, what if a teammate updates a prompt to try to make the LLM output sound more interesting, but this causes it to hallucinate more? Automated testing, as part of your approach to LLMOps (LLM Operations), helps avoid these problems and lets you ship faster and with greater confidence.

In this course, you’ll learn to:
(i) Write LLM evaluations to cover common problems like hallucinations, data drift, and harmful or offensive output.
(ii) Build a CI workflow to automatically evaluate each change to your application.
(iii) Orchestrate your CI workflow to run specific evaluations at different stages of development.

CI is especially helpful for AI applications given the iterative nature of AI development, which means we often want to make many incremental changes. 

Please sign up for this course here! https://lnkd.in/g_24bHka

Our first-ever workshop on aligning LLMs with Direct Preference Optimization (DPO) is happening soon! 

DPO has become a game-changing alignment technique, and we’re happy to invite you to both discuss the theory behind it and get hands-on with the Hugging Face Transformer Reinforcement Learning (TRL) library. 

Join us on February 8 at 11 AM Pacific Time! 

Register now: https://hubs.la/Q02hBFxl0

AI:DEEPLEARNING

DeepLearning.AI