Scribd
Upload
100 views16 pages

Generative Ai Tools

The document discusses generative AI and how it uses machine learning to create new content such as text, images, and videos. It explains that generative AI models are trained on large amounts of data and can then produce new, never-before-seen content on demand in various forms like text, speech, images and more. The document also provides tips on using prompts to get specific, detailed output from generative AI tools.

Uploaded by

Aarthi E
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
100 views16 pages

Generative Ai Tools

The document discusses generative AI and how it uses machine learning to create new content such as text, images, and videos. It explains that generative AI models are trained on large amounts of data and can then produce new, never-before-seen content on demand in various forms like text, speech, images and more. The document also provides tips on using prompts to get specific, detailed output from generative AI tools.

Uploaded by

Aarthi E
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

GENERATIVE AI

TOOLS
Dr. Aarthi E
Assistant Professor
Department of Computer Science
Faculty of Science and Humanities
SRM IST . KTR
GENERATIVE AI
ChatGPT, Bing, Bard, DallE…

Generative AI, like ChatGPT, uses


machine learning to create new content.
Generative AI tools can help explore
new ideas, write text, and get feedback,
GEN AI …..
• Generative AI is a branch of machine learning focused on creating
AI models that learn from pre-existing content.
• This pre-existing content can include images, video files, text,
and audio.
• The models within the generative AI field ultimately
create new, never-before-seen content on demand.
• There are already many types of generative models. A few of
these include

 Text-to-video
 Text-to-image
 Text-to-speech
 Text-to-3D
 Audio generation
 Video generation
Now, AI can synthesize part or all of a
creative work
McKinsey defines generative
AI as:
… Algorithms (such as
ChatGPT) that can be used to
create new content, including
audio, code, images, text,
simulations, and videos.
Recent breakthroughs in the
field have the potential to
drastically change the way we
approach content creation
HOW DOES AI LEARN FROM DATA ?
In order to understand what it needs to generate, every generative AI model
must be trained on a massive amount of data.

Deep learning algorithms trace these variables across billions of dimensions, and
recognize and organize characteristics.

During training, the model learns what a wide range of specific visual assets and
image contents look like, and how to associate those to natural language
descriptions.

For example, an AI model can be trained to recognize what soda pop looks like. By
being exposed to millions of images of these drinks, the model will grow to know
that soda..Using deep learning algorithm, the AI model is capable of producing a
near infinite amount of net-new soda pictures, each different from the last, even
from the exact same text prompt.
How Generative AI works ?
The system generates text or images using its previously built model of the
statistical distributions of tokens (= “chunks” of words, punctuation marks,
pixels, etc.) created from its very large training datase
How Generative AI works
It might make mistakes or “hallucinate” based on the limitations of its
process, but the output still might look like what you wanted. Ted Chiang’s
analogy = “unreliable photocopier” or a “blurry JPEG”
Prompts
We can ask it questions - but a very specific type of question
known as prompts.
Prompts are the foundation of any conversation with a language
model. They serve as the input to the model, providing context
and direction for the response. Without clear, well-constructed
prompts, language models may provide irrelevant or unhelpful
responses, leading to frustration and a poor user experience.
Prompts in AI Tools
Get deeper understanding
• To clarify or get a deeper understanding of a topic, or any piece of
information, use the following prompts,” explained Cheung. Options
include, “Explain [insert specific topic] in simple terms,” or “Explain
[concept] to me like I’m 11 years old,” and “Explain [topic] to me as
if I’m a beginner in [field].”

Improve without changing the meaning


• When you’re sent testimonials, website or marketing copy, or a first
draft that isn’t quite right, use this prompt to tidy it up while keeping
the essence of the message, according to the “content and language
style” section of the 26 principles. “Revise every paragraph in this
[type of text] sent by [specify who]. You should only improve the
user’s grammar and vocabulary and make sure it sounds natural.
You should not change the writing style, such as making a formal
paragraph casual.”
PROMPTS
Specify detailed output
one criticism of ChatGPT is that its first instinct is to use
flowery, generic, vague language. It makes sense. The tool was
trained on billions of words from across the internet, many of
which will contradict each other. Competing messages water
eachother down until there’s nothing left to do but embellish. A
camel is a horse built by a committee.
• For more detailed output, you only have to ask. Cheung
recommends you use this prompt. “Write a detailed [type of
text] for me on [topic] in detail by adding all the information
necessary,” then add further guidance on the direction this
detail should take. Specify clarity, conciseness, and be clear on
the structure and length required.
Best ChatGPT prompts for
Content Creation
 I need help developing a lesson plan on renewable energy sources for
high school students.
 Generate a creative social media content calendar for the next month
for our [company or product] on [ topic of choice]
 Generate a 2-minute video script for a Facebook ad campaign
promoting our new service [ Service description]
 Write a blog post on the [topic of your choice]
AI tools
• Wiseone AI
• Genni AI
• Quillbot AI
• Dall- e
• ChatGPT
Generative AI Has Limits
• Biases and ‘hallucinations’

• Remember, even though generative AI can


produce compelling content, it doesn't have
human judgement or understanding. It can't
provide personal insights or contextual
awareness, has biases, and it can't replace the
value of your own critical thinking.
• Plus: it sometimes makes things up or
“hallucinates.”
• Stay sharp and use a reliable source (i.e., not
another generative AI tool!) to fact-check any
content produced by AI before incorporating it
into your work.
Be Transparent
Citation and referencing

• If you're allowed to be using AI, make sure you


disclose how and where. Don't forget to correctly
cite all your sources, including any AI-generated
content. Your instructor will explain to you how to
share your use of generative AI.
Key takeaways
● Generative AI tools can be nifty shortcuts to dispose of low-value tasks
and / or to jumpstart creativity.

● Generative AI tools should always be used with your “thinking cap” on


because they are prone to mistakes and “hallucinations.”

Thank you for listening

You might also like