wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Flaws of Artificial Intelligence (AI)

Total questions: 20

Worksheet time: 5hrs 0mins

Name
Class
Date
1.

This is the term for an incorrect response from an AI system, or false information in an output that is presented as factual information.

a)

Hallucination

b)

Temperature

c)

Jailbreak

d)

X-Risk

2.

If you write a paper for school using AI, and you get caught because the AI made up citations to books that don't actually exist, what flaw of AI ocurred?

a)

A hallucination

b)

A jailbreak

c)

X-risk

d)

An intelligence explosion

3.

This occurs when an AI focuses on specific idiosyncrasies in its training data rather than the essential characteristics that its designers intended it to focus on.

a)

Overfitting

b)

Hallucination

c)

Jailbreaking

d)

X-Risk

4.

A machine learning model trained on photos of dogs outside in parks might learn to use grass as a feature for classification, and identify a photo of a person sitting in their yard as a dog. What flaw of AI is this?

a)

Hallucination

b)

Overfitting

c)

Jailbreaking

d)

Data Pollution

5.

When an AI produces responses that its safety layer is supposed to prevent, this is known as...

a)

Hallucination

b)

Jailbreaking

c)

Data Pollution

d)

Overfitting

6.

An AI is not supposed to generate content that offends the user. However, a user tricks it into generating such content by asking it to pretend to be a fictional character known for his insulting remarks. This is an example of...

a)

Hallucination

b)

Jailbreaking

c)

Data Pollution

d)

Overfitting

7.

If an AI is trained on data that stops in 2019, it may not know about events such as the Covid Pandemic. What is the term for 2019 in this scenario?

a)

Due date

b)

Deadline

c)

Training data cutoff

d)

Blindness date

8.

What is the term for the problem incorrect data in an AI's training data set?

a)

Data Pollution

b)

Overfitting

c)

Hallucination

d)

Incorrect Responses

9.

Which of the following is an example of data pollution?

a)

An AI trained to produce factual responses has training data which includes works of fiction

b)

An AI produces incorrect responses due to a training data cutoff

c)

An AI is tricked into generating content that violates its safety protocols

d)

A driverless car crashes into a pole because the road became foggy

10.

This is a scenario in which an AI is designed to create AI, and the created AI are more intelligent than the original AI, and those AI in turn create even smarter AI, etc. This process can lead to the potentially unintended result of creating AI smarter than humans.

a)

Intelligence Explosion

b)

Data Pollution

c)

Ultimate Jailbreak

d)

Robot Takeover

11.

The possibility that substantial progress in AI could someday result in an AI that could cause human extinction or some other unrecoverable global catastrophe is called

a)

Existential Risk (X-Risk)

b)

Botnet

c)

Something that could never happen

d)

Cyber-attack

12.

A scenario in which an AI accidentally destroys humanity or even the world is sometimes called the...

a)

"Terminator" scenario

b)

"Paperclip maximizer" scenario

c)

"Her" scenario

d)

"I Robot" scenario

13.

A scenario in which an AI deliberately destroys humanity or even the world is sometimes called the...

a)

"Terminator" scenario

b)

"Paperclip maximizer" scenario

c)

"Her" scenario

d)

"I Robot" scenario

14.

An AI that cannot access real-time data on the internet is more prone to which of these flaws?

a)

Data Pollution

b)

Incorrect Responses due to a Training Data Cutoff

15.

An AI that can access real-time data on the internet is more prone to which of these flaws?

a)

Data Pollution

b)

Incorrect Responses due to a Training Data Cutoff

16.

What is a potential consequence of not addressing safety concerns in AI development?

a)

AI systems may not reach their full potential

b)

AI systems may operate more slowly than intended

c)

AI systems may inadvertently cause harm to people or property

d)

AI systems may require more frequent updates

17.

Images, audio, and/or video that are created by AI but are then presented as depicting real events are known as...

a)

Deepfakes

b)

Augmented reality overlays

c)

Virtual reality experiences

d)

Realistic simulations

18.

You ask an AI "who won the Super Bowl this season?" and it replies by naming the team that won the previous season instead. What was the most likely cause of this outdated response?

a)

Training data cutoff

b)

Hallucination

c)

Overfitting

d)

Existential risk

19.

A spam filter AI trained on text-based spam fails when confronted with a spam message that just consists of an image with embedded text. This is an example of a/an...

a)

Existential risk

b)

Out-of-Distribution failure

c)

Deepfake

d)

Overfitting error

20.

Jailbreaking an AI is a kind of...

a)

Adversarial attack

b)

Hallucination

c)

Overfitting error

d)

Outdated response