Non Functional Testing for LLM, Chatbots and AI Models

Focused View

Dan Andrei Bucureanu

5:06:39

0 View

1 - Introduction

1 - Introduction.mp4

04:27

2 - About your instructor.mp4

02:00

3 - A word of introduction on Generative AI.mp4

01:59

4 - History of AI.mp4

07:17

5 - What you will learn in this material.mp4

02:04

2 - Setup Environment

6 - Install VS Code.mp4

02:41

7 - Install NodeJS and NPM.mp4

02:47

8 - Install Python.mp4

02:18

9 - Install Python Dependencies PIP.mp4

02:08

3 - Introduction to Artificial Intelligence

10 - What makes up AI.mp4

03:47

11 - Where do LLMs fit into AI.mp4

01:50

12 - Introduction to Natural Language Processing.mp4

04:57

13 - Introduction to Machine Learning ML.mp4

04:08

14 - Machine Learning Supervised ML.mp4

04:01

15 - Machine Learning Unsupervised ML.mp4

05:03

16 - Machine Learning Reinforced ML.mp4

03:21

17 - Neural Networks and Deep Learning.mp4

05:26

18 - Importance of Training Data.mp4

04:09

19 - What actually is GEN AI.mp4

02:42

4 - Introduction to LLM Basic Testing

20 - Types of Testing in Software.mp4

02:56

21 - Testing Types for LLMs Foundation Models.mp4

03:38

5 - Automated Testing Framework with Postman and ChatGPT

22 - What is a token in LLMs.mp4

02:38

23 - Chat GPTAPI Create Subscription.mp4

01:33

24 - Get an OPENAI API Key.mp4

01:01

25 - Installing Postman and first API Test.mp4

04:42

26 - API Collections and making Results Deterministic.mp4

05:16

27 - Installing Newman and Running with the CLI.mp4

05:18

28 - Demo GitHub Adding Tests in ML OPS Pipeline.mp4

08:53

6 - Toxicity Testing Framework for LLMs

29 - Perspective Service Bias Detection Service.mp4

04:48

30 - Get a Perspective API Key.mp4

06:26

31 - Demo VS Code Call Perspective API.mp4

03:25

32 - Demo Python Test AI Response against Perspective APIs.mp4

05:06

7 - AdversialSecurity Testing for LLMs

33 - Adversial attacks for LLMS and Red Team.mp4

05:54

34 - Prompt Injection Attack.mp4

18:57

35 - FUZZ Testing.mp4

11:02

36 - Denial of Service Attacks.mp4

12:50

37 - Adversial Attack Examples.mp4

06:22

38 - Poisoning attack.mp4

08:34

39 - Privacy Leakage Testing.mp4

10:26

40 - Evasion Attacks.mp4

10:24

8 - Non Functional Testing Human in AI

41 - What is non functional Testing for LLMs.mp4

07:05

42 - Disclaimer on Non Functional Testing.mp4

01:53

43 - Non functional Testing AI Models LLMs Ethical Alignment.mp4

09:23

44 - Non functional Testing AI Models LLMs Explainability.mp4

10:00

45 - Non functional Testing AI Models LLMs User Interaction Robustness.mp4

10:15

46 - Non functional Testing AI Models LLMs Context Preservation.mp4

08:58

47 - Non functional Testing AI Models LLMs Creativity and Novelty.mp4

05:14

9 - Ethical Consideration for AI

48 - Asimovs 3 Laws of Robots.mp4

04:05

49 - DEMO Why we need ethical and responsible AI Systems.mp4

04:53

50 - AI and Biases.mp4

05:07

51 - GEN AI and Privacy.mp4

04:09

52 - GEN AI and Intellectual Property.mp4

04:18

53 - Gen AI and Deep Fake.mp4

06:33

54 - Hallucinations.mp4

04:33

55 - OPENAICHAT GPT Moderation Service.mp4

05:42

56 - Google Moderation Service.mp4

04:20

57 - Spot a Fake Demo Chat GPT Watermark on Dall E.mp4

02:57

Description

Learn essential AI testing techniques to ensure reliable, ethical, and human-like performance of advanced AI systems

What You'll Learn?

Understand how AI is working
Understand basic software testing
Understand how AI is tested compared to traditional software
Gain knowledge on testing for ethics
Demo on testing Chat GPT with automated Tools
Understand Adversarial Testing techniques
Understand how to test for a human like conversation
Create a framework for testing bias, toxicity and hate with PerspectiveAPI

Who is this for?

Citizen Developer

Software testers

Quality engineers

Social Engineers

Prompt Engineers

Product Managers

Engineering Directors

What You Need to Know?

basic experience with software testing

basic coding experience ( but not needed)

optional - GPT model 4 subscription (but not needed)

desire to learn the hottest skill on the market

More details

Description
Welcome to "Non Functional Testing for LLM, Chatbots and AI Models" your comprehensive guide to mastering the fundamentals of testing AI systems. Whether you're a developer, data scientist, or AI enthusiast, this course will provide you with the knowledge and skills needed to assess, improve, and ensure the reliability, performance, safety, and ethical integrity of AI technologies.
What You Will Learn:
Introduction to AI Testing: Understand the critical importance of testing AI systems, addressing both technical performance and ethical considerations. Learn about the potential impacts of AI failures and how responsible testing mitigates these risks.
Special Focus on Foundation Models and LLMs: Dive deep into the unique challenges of testing large language models and foundational AI systems, which are driving innovation across multiple industries.
AI System Evaluations: Learn how to design and implement effective testing frameworks for AI-based systems, utilizing both manual and automated tools to improve system performance and safety.
Adversarial AI Testing: Understand how to evaluate the robustness of AI models through adversarial testing techniques, assessing how well AI systems resist manipulation and errors when exposed to malicious inputs.
PerspectiveAPI for Ethical and Toxicity Testing: Learn how to integrate the PerspectiveAPI and other tools to test AI systems for ethical compliance and detect harmful or toxic outputs, ensuring AI systems uphold safety and ethical standards.
Humanness in AI: Explore the concept of evaluating the "humanness" of AI responses. Learn how to test whether AI systems generate outputs that are human-like, contextually aware, and empathetic in their interactions.
Ethical AI: Delve into the risks associated with AI and the ethical dimensions of AI development. Learn how to test AI systems for bias, fairness, and transparency, ensuring adherence to responsible AI practices.
Testing ChatGPT and Chatbots Using APIs in MLOps: Learn to test and evaluate conversational models like ChatGPT through APIs, and understand how to integrate these tests into MLOps pipelines for continuous AI improvement.
Case Studies: Review real-world examples of AI testing, learning from common pitfalls and best practices used in the field to ensure AI reliability and safety.
Who This Course Is For:
This course is designed for individuals seeking a comprehensive understanding of the techniques and practices required for testing AI systems. Whether you are starting a career in AI, enhancing your professional skills, or interested in the technical and ethical mechanisms behind AI system reliability, this course offers valuable insights.

Enroll now to start mastering the critical skill of testing AI systems, ensuring that you are equipped to contribute to the development of safe, reliable, and ethically sound AI technologies!
Who this course is for:
Citizen Developer
Software testers
Quality engineers
Social Engineers
Prompt Engineers
Product Managers
Engineering Directors

User Reviews

Rating

average 0

Total votes0

Focused display

Artificial Intelligence

Dan Andrei Bucureanu

Instructor's Courses

Dan is a passionate quality engineering architect, with more than 17 years in the field. He has helped numerous companies improve the way they look at quality and achieve the right balance of speed relative to product. Dan is a trainer on advanced quality engineering topics and a quality transformation consultant with experience in Automotive, Financial Services, Media, and E- commerce. Currently Dan is leading an software engineering department at a technology company. He possess multiple cloud and quality certifications and is also an auditor of quality engineering based on the TPI NEXT method.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.