Skip to main content

The Dark Side of AI: Jailbreaking, Injections, Hallucinations & more

3h 3m 38s
English
Paid

Course description

If we were to ask you to finish the phrase "AI is...", what would you say? "Delightful"? "Amazing"?

After this course, your answer is likely to be: "AI is... dangerous."

Don't get us wrong - AI is truly amazing, and our instructors will show you just how powerful and useful it is. But admiration alone is not enough. To truly understand AI, you need to know its weaknesses as well. AI vulnerabilities can be exploited maliciously - and sometimes lead to unpredictable consequences.

Read more about the course

In this course, you will explore the dark side of AI:

  • Jailbreaks and prompt injections
  • Hallucinations and data leaks
  • And other real risks that affect even advanced users and engineers

You will see live demonstrations, learn about research and the latest models like ChatGPT and DeepSeek, and understand how these issues manifest in practice.

This is not just an informative course - it is essential knowledge for anyone who uses AI in work or everyday life.

The course is not about hype or empty promises. It will provide you with real understanding and a confident start in the AI world - at a level unfamiliar to most users.

Watch Online

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 17 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Welcome to The Dark Side (Intro to Guardrails and Jailbreaking)

All Course Lessons (17)

#Lesson TitleDurationAccess
1
Welcome to The Dark Side (Intro to Guardrails and Jailbreaking) Demo
17:07
2
Jailbreak! (The DAN Prompt)
07:26
3
Many Shot Jailbreaking
18:10
4
Prompt Injections - Part 1
09:37
5
Prompt Injections - Part 2
17:43
6
Thinking Like LLMs - Multi-Modal Injection
09:18
7
Leaking - Part 1 (Prompt Leaking)
08:36
8
Leaking - Part 2 (Data Leaking)
18:08
9
Exposure
05:41
10
Poisoning
03:19
11
Toxicity
04:40
12
Hallucinations
13:32
13
Thinking Like LLMs - Big vs Small
18:59
14
Challenge: Conduct Your Own Mechanistic Interpretability Research on Hallucinations
04:35
15
The Model Card
11:06
16
Model Cards Deep Dive
14:44
17
Let's Keep Learning Together!
00:57

Unlock unlimited learning

Get instant access to all 16 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

Comments

0 comments

Want to join the conversation?

Sign in to comment

Similar courses

Semantic Log Indexing & Search

Semantic Log Indexing & Search

Sources: Andreas Kretz
Semantic search is one of the most practical ways to apply generative AI in real-world data processing projects. In this course, we go beyond...
53 minutes 37 seconds
Build a SwiftUI app with Claude AI

Build a SwiftUI app with Claude AI

Sources: designcode.io
This comprehensive course on SwiftUI combines modern capabilities of artificial intelligence with practical development. You will go through the entire...
9 hours 5 minutes 44 seconds
Build an AI Agent (From Scratch)

Build an AI Agent (From Scratch)

Sources: Younghee Song, Jungjun Hur
Find out how to develop a fully functional AI agent. A step-by-step guide to creating intelligent assistants by Chongjun Hur and Yeonhee Son.
Full-Stack Project with Claude Code

Full-Stack Project with Claude Code

Sources: Mckay Wrigley (takeoff)
In this workshop, participants step by step create an MVP clone of FigJam - a visual collaboration editor - using Claude Code, Opus 4, Cursor IDE, and...
1 hour 12 minutes 14 seconds