SlideShare a Scribd company logo
@schachin
Kristine Schachinger
Kristine@SitesWithoutWalls.com
"Unlocking the Power of ChatGPT”
-- without blowing yourself up --
“…they are prone to hallucinating, and crucially they are incapable of justifying their utterances…”
@schachin
Kristine Schachinger
What is a
“Chat Generative Pre-trained
Transformer”?
@schachin
Kristine Schachinger
ChatGPT
“Chat Generative Pre-trained
Transformer”
@schachin
Kristine Schachinger
Generative Pre-Trained Transformer Model.
@schachin
Kristine Schachinger
GPT, ChatGPT, and …
Large Language
Models.
Dalle’s vision of ChatGPT
@schachin
Kristine Schachinger
Why are LLMs So Special?
Unlike embedded based language models LLMs can disambiguate words from the sentence and apply
meaning forward and backward to those words in order to predict a masked word using those applied
contexts. This is SUPER EFFICIENT!
@schachin
Kristine Schachinger
Why are LLMs So Special?
Large Language modeling can determine the meaning of words in context
so it can better predict the next word in the sentence.
These sentences mean two different things forward and backward.
@schachin
Kristine Schachinger
How does this work? Transformers
What are transformers?
A transformer in language processing is a type of computer program
that is designed to understand and generate text.
It does this by using a special type of algorithm called self-attention.
Self-attention allows the program to look at all the words in a
sentence or a piece of text at once, and understand how they relate
to each other, rather than just one word at a time like traditional
methods. This way it can better understand the meaning of the text,
and can generate text that is more similar to how a human would
write.
@schachin
Kristine Schachinger
LLMs can go forward and backwards
to predict an unknown (masked) term and/or sentence.
Also uses root words, so play for player/playing/played are the same
This allows them to derive context for what is being written.
Previous models were based on word vectors (entities and knowledge graphs)
LLM Transformers are Bidirectional
https://blog.google/products/search/search-language-understanding-bert/
@schachin
Kristine Schachinger
Confusing?
@schachin
Kristine Schachinger
Simply language modeling is
“Language modeling – although it sounds formidable –
is essentially just predicting words in a blank.”
@schachin
Kristine Schachinger
Large Language Models?
Some of the more relevant well-known LLMs are:
• OpenAI
 GPT-2/3
 ChatGPT 2 & 3.x
 ChatGPT 4 should be released this year.
 WebGPT
 attempts to resolve the issue of attribution and accuracy
 Google
 BERT
 Used in Search
 LaMDA
 conversational like ChatGPT
 “Unlike GPT-3, which is not configured to perform any specific task, LaMDA is “trained on dialogue”:
 PaLM
 Search relevancy
 it is also trained using a “combination of English and multilingual datasets that include high-quality web documents,
books, Wikipedia, conversations and GitHub code” to drive greater accuracy in responses.
Learn more about these and others  https://seekingalpha.com/article/4563975-google-why-is-no-one-talking-about-palm
@schachin
Kristine Schachinger
What is ChatGPT?
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
What is ChatGPT? Let’s Ask It!
ChatGPT is/was
• a variant of the GPT (Generative Pre-training Transformer) language
model
• introduced by OpenAI in 2018.
• GPT trained on a massive dataset of over 40GB of text data for GPT-2 and 45TB for GPT-3.x
• ChatGPT includes conversational text from books, articles, and websites.
• capable of generating human-like text
• useful for certain tasks
• language translation, text summarization, and question answering.
• fine-tuned on several specific
• writing poetry, composing music, and even coding.
• one of the largest language models currently available
• over 175 billion parameters
• used in several real-world applications
• chatbots, automated customer service, and even writing news articles.
• continuously being updated and improved by OpenAI
• GPT4 will come out this year
@schachin
Kristine Schachinger
TeThje
What is ChatGPT?
In layman’s terms, a large language model (LLM), which generates
convincing sentences by mimicking the statistical patterns of
language in a huge database of text collated from the Internet.
It was trained to sound confident to humans even when it is
wrong.
https://www.nature.com/articles/d41586-023-00107-z
@schachin
Kristine Schachinger
ChatGPT is Predictive Text.
It is predicting the next most likely word in a sentence based on the context of the
other words in the sentence derived from the information it was trained on.
@schachin
Kristine Schachinger
TeThje
What is ChatGPT NOT?
• A Search Engine
• The data was trained only up to 2021
• It is not connected to the Internet, so it cannot retrieve information
• Is based on predictive text NOT information retrieval
• There is no QUALITY check for the accuracy of the content or code
• Creative
• if it was not trained on the information, it cannot generate something as a human
would from inference or imagination.
https://www.nature.com/articles/d41586-023-00107-z
@schachin
Kristine Schachinger
Using ChatGPT for Marketers.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Some ChatGPT Ideas for Marketers
• SEO: Titles and Metas (okayed by Google)
• PPC Landing Pages
• Content Ideas
• Content NOT for Search
• Topical Funnels
• Analyze Competitor Site Content
• Product Descriptions
• Customer Service / Chatbots
• Emails
• Outreach
• Link Building
• Lead Generation
• Newsletters
• Reviews
digital marketer using AI to do SEO Disney style
@schachin
Kristine Schachinger
ALWAYS USE HUMAN REVIEW.
ChatGPT is not a search engine, has no fact checking function, and was not trained on
any data past 2021 so make sure someone reviews the output produced for errors,
accuracy, factual information, and tone.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
What It’s NOT For?
Writing content that will be submitted to the search engines.
• AI Content is Detectable
• How?
• AI knows what AI would ”produce” and can estimate how much matches AI
• AI Content from ChatGPT will soon have cryptographic ”watermarks”
• You can’t simply edit the text and know you have removed these.
• This means ChatGPT will also be able to provide these watermarks to its AI detector
which is available to anyone or any company.
• MSFT will have a 49% stake in OpenAI and access to the watermarked information
@schachin
Kristine Schachinger
Detection.
Don’t Blow Yourself Up.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
ChatGPT Detection Tools.
OpenAI
• Professional for Educators and Researchers
• https://chatgpt.pro/gptzero/
Hugging Face
• Built on GPT 2 but still pretty good with GPT 3.x
• https://huggingface.co/spaces/openai/openai-detector
From IBM/Harvard/MIT
• Giant Language model Test Room (GLTR)
• Also built on GPT 2 but still fairly reliable
• http://gltr.io/dist/index.html
Writer
• AI writing tool but detector is pretty solid
• https://writer.com/ai-content-detector/
Stanford Student (SAME AS OpenAI)
• https://gptzero.me/
Some of the known detections tools
Content Detection Tools
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include: Detection.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Detection and Google.
Google says AI Content is okay IF it provides value and it not “spammy”,
But since it is writing what it trained on how does provide value?
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Detection and Google.
How does Google define “Spammy” content?
@schachin
Kristine Schachinger
Play it safe, do not use ChatGPT or AI to write article content.
Use humans to write/edit your content.
They can use ChatGPT as a tool to generate ideas, however.
@schachin
Kristine Schachinger
How to Use ChatGPT.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT.
The Application of ChatGPT
Some of the potential applications of ChatGPT include:
• Text generation: ChatGPT can be used to generate human-like text responses to prompts, which makes it useful for creating
chatbots for customer service, generating responses to questions in online forums, or even creating personalized content for
social media posts.
• Language translation: ChatGPT can also be used for language translation tasks. By providing the model with a text prompt in
one language and specifying the target language, the model can generate accurate and fluent translations of the text.
• Text summarization: ChatGPT can be used to generate summaries of long documents or articles. This can be useful for
quickly getting an overview of a text without having to read the entire document.
• Sentiment analysis: ChatGPT can be used to analyze the sentiment of a given text. This can be useful for understanding the
overall tone and emotion of a piece of writing, or for detecting the sentiment of customer feedback in order to improve
customer satisfaction.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT.
Fine Tuning in ChatGPT Training.
ChatGPT was trained with the following focuses:
• Code
• Content Writing
• Poetry
• Music
This means it tends to create these items well.
Fine tuning allows ChatGPT to focus in on certain types of functions and may
not do as well with others.
@schachin
Kristine Schachinger
Using ChatGPT Prompts.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
InstructGPT: ChatGPT Prompts.
Prompts.
The MOST Important Part of Using ChatGPT.
Prompts provide a starting point for ChatGPT to generate text based on the
input given. They can be used to guide the model's output and control the
context of the generated text.
Prompts? Simply means, how you tell ChatGPT what to write.
This relies on another language model called InstructGPT, which allows you to
give ChatGPT detailed and specific instructions.
https://www.searchenginejournal.com/chatgpt-for-content-and-seo/473823/#close
@schachin
Kristine Schachinger
Using ChatGPT Prompts: Examples.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Content > Articles.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Content > Articles + Style.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Content > FAQs.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Code.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Summarization > URLs.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Summarize URLs.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Write Emails.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Lyrics.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Poetry.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Using ChatGPT Prompts: Ideas.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
ChatGPT Prompts.
Prompts.
How to write ChatGPT Prompts
• Give Context
• Be Clear
• Be Concise
• Be Specific
• Be Descriptive
• Define Format
• Define Length
• Define Style
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
ChatGPT Prompts.
Prompts.
Some great ideas for how you can use ChatGPT
• 100 Best ChatGPT Prompts
• https://mpost.io/100-best-chatgpt-prompts-to-unleash-ais-potential/
• Web Development ChatGPT
• Music ChatGPT
• Business ChatGPT
• Educational ChatGPT
• Comedy ChatGPT
• History ChatGPT
• Health&Medicine ChatGPT
• Art ChatGPT
• Food & Cooking ChatGPT
• Marketing ChatGPT
• Game ChatGPT Prompts
https://www.searchenginejournal.com/chatgpt-for-content-and-seo/473823/#close
@schachin
Kristine Schachinger
Issues with ChatGPT
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
ChatGPT Issues?
+ Programmed to Avoid Certain Kinds of Content
• ChatGPT is specifically programmed to not generate text on the
topics of graphic violence, explicit sex, and content that is harmful
such as instructions on how to build an explosive device.
• And swearing
+ Unaware of Current Events
• not aware of any content that is created after 2021.
 Has Built-in Biases
• This can be just in the writing style, not necessarily cultural or
racial though they can exist as well
+ ChatGPT Requires Highly Detailed Instructions
• You must be very specific with ChatGPT Prompts to really get
good output
+ Mediocre Content
• ChatGPT is designed to sound confident, but the content it writes
is not high quality.
+ Suffers from “Hallucinations”
• Makes stuff up
https://www.searchenginejournal.com/chatgpt-for-content-and-seo/473823/#close
@schachin
Kristine Schachinger
“Hallucinations”: Machine Learning for Making Stuff Up
@schachin
Kristine Schachinger
https://www.wired.com/story/chatgpt-fluent-bs/
All of this makes playing around with ChatGPT incredibly fun, charmingly addictive, and—as
someone who writes for a living—really quite worrying. But you soon start to sense a lack of
depth beneath ChatGPT’s competent prose. It makes factual errors, conflating events and
mixing people up. It relies heavily on tropes and cliché, and it echoes society’s worst
stereotypes. Its words are superficially impressive but largely lacking in substance—
ChatGPT mostly produces what The Verge has described as
“fluent bullshit.”
But that kind of makes sense. ChatGPT was trained on real-world text, and the real world
essentially runs on fluent bullshit.
“Bovine Feces”
@schachin
Kristine Schachinger
Google
https://ai.google/static/documents/exploring-6-myths.pdf
@schachin
Kristine Schachinger
Google
https://www.semanticscholar.org/paper/Rethinking-Search%3A-Making-Domain-Experts-out-of-Metzler-Tay/e3d7065d6196437259483ed8b9b70ba4b4bb76ad
“…they do not have a true
understanding of the world, they are
prone to hallucinating, and crucially
they are incapable of justifying their
utterances by referring to supporting
documents in the corpus they were
trained over.”
Image from DALL-E
@schachin
Kristine Schachinger
Google
https://www.semanticscholar.org/paper/Rethinking-Search%3A-Making-Domain-Experts-out-of-Metzler-Tay/e3d7065d6196437259483ed8b9b70ba4b4bb76ad
“…they do not have a true
understanding of the world, they are
prone to hallucinating, and crucially
they are incapable of justifying their
utterances by referring to supporting
documents in the corpus they were
trained over.”
Image from DALL-E
“…they are prone to hallucinating, and crucially they are incapable of justifying their utterances…”
@schachin
Kristine Schachinger
https://gizmodo.com/cnet-ai-chatgpt-news-robot-1849996151
@schachin
Kristine Schachinger
ALWAYS USE HUMAN REVIEW.
ChatGPT is not a search engine, has no fact checking function, and was not trained on
any data past 2021 so make sure someone reviews the output produced for errors,
accuracy, factual information, and tone.
@schachin
Kristine Schachinger
ChatGPT Resources.
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
ChatGPT Docs.
ChatGPT Guide
• All the basics you need to know about how to use ChatGPT
• https://www.digitaltrends.com/computing/how-to-use-openai-chatgpt-text-generation-chatbot/#google_vignette
OpenAI ChatGPT API Guide.
• Everything you need to know about using the API version
• https://beta.openai.com/docs/guides/completion/inserting-text
Some cool things people have done with ChatGPT
• https://www.bleepingcomputer.com/news/technology/openais-new-chatgpt-bot-10-coolest-things-you-can-do-with-it/
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
ChatGPT PRO Tools.
Full List of ChatGPT PRO Tools.
Cost will be $42 a month as of January 22, 2023
• https://chatgpt.pro/chatgpt-plugins/
Partial List
• WebChatGPT
• ChatGPT Writer
• Whatsapp GPT
• Search GPT Shortcut
• YouTube Summary
• ChatGPT in google docs
• TweetGPT
• ChatGPT for Search Engines
• Everywhere
• ChatGPT History
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
ChatGPT Marketing/SEO Tool.
Google Chrome Extensions
AIPRM
https://www.aiprm.com/
Once added to your browser it will show up in
your ChatGPT page when you login.
It has ChatGPT Tools for
• SEO
• Marketing
• Sales/SASS
@schachin
Kristine Schachinger
What About Google?
@schachin
Kristine Schachinger
Some of the general parameters that are used to train language models include:
Google Suite of AI Tools
LaMDA is Google’s version of ChatGPT
& built on the same technology as ChatGPT
“…. there is no official word whether will call it
LaMDA or any other name, but Google is
expected to show more than 20 similar AI
products including 'Shopping Try-on' for
YouTube (to help users try on new clothes),
Maya: (3D image generator), video
summarization tool, a Pixel exclusive wallpaper
generator, an AI tool for enterprise customers
to developer their own ChatGPT-like bot, Colab
+ Android Studio (to help software
programmers to detect and fix bugs) …and
more at upcoming annual Google I/O...”
Read more at:
https://www.deccanherald.com/business/technology/google-to-
demo-chatgpt-altenative-at-i/o-2023-1183735.html
@schachin
Kristine Schachinger
Kristine@SitesWithoutWalls.com
"Unlocking the Power of ChatGPT”
-- without blowing yourself up --
“…they are prone to hallucinating, and crucially they are incapable of justifying their utterances…”

More Related Content

PDF
Everything to know about ChatGPT
PDF
How People Are Leveraging ChatGPT
PDF
20 prompts for chatGPT that make life easier for developers.pdf
PDF
Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present...
PDF
ChatGPT-the-revolution-is-coming.pdf
PPTX
ChatGPT 101.pptx
PDF
ChatGPT and the Future of Work - Clark Boyd
PPTX
Introduction to ChatGPT
Everything to know about ChatGPT
How People Are Leveraging ChatGPT
20 prompts for chatGPT that make life easier for developers.pdf
Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present...
ChatGPT-the-revolution-is-coming.pdf
ChatGPT 101.pptx
ChatGPT and the Future of Work - Clark Boyd
Introduction to ChatGPT

What's hot (20)

PPTX
Webinar on ChatGPT.pptx
PDF
ChatGPT ChatBot
PDF
Deep dive into ChatGPT
PDF
ChatGPT Use- Cases
PPTX
Praneet’s Pre On ChatGpt edited.pptx
PDF
Chat GPT Intoduction.pdf
PDF
ChatGPT Evaluation for NLP
PDF
Uses of AI text bot.pdf
PDF
ChatGPT 101 - Vancouver ChatGPT Experts
PDF
Let's talk about GPT: A crash course in Generative AI for researchers
PDF
intro chatGPT workshop.pdf
PPTX
ChatGPT in Education
PPTX
ChatGPT Deck.pptx
PPTX
ChatGPT ppt.pptx
PDF
How AI is going to change the world _M.Mujeeb Riaz.pdf
PPTX
5 BENIFITES OF CHAT GPT.pptx
PDF
ChatGPT OpenAI Primer for Business
PPTX
Blueprint ChatGPT Lunch & Learn
PPTX
Jawad's presentation on GPT.pptx
PPTX
chatGPT.txt
Webinar on ChatGPT.pptx
ChatGPT ChatBot
Deep dive into ChatGPT
ChatGPT Use- Cases
Praneet’s Pre On ChatGpt edited.pptx
Chat GPT Intoduction.pdf
ChatGPT Evaluation for NLP
Uses of AI text bot.pdf
ChatGPT 101 - Vancouver ChatGPT Experts
Let's talk about GPT: A crash course in Generative AI for researchers
intro chatGPT workshop.pdf
ChatGPT in Education
ChatGPT Deck.pptx
ChatGPT ppt.pptx
How AI is going to change the world _M.Mujeeb Riaz.pdf
5 BENIFITES OF CHAT GPT.pptx
ChatGPT OpenAI Primer for Business
Blueprint ChatGPT Lunch & Learn
Jawad's presentation on GPT.pptx
chatGPT.txt
Ad

Similar to Unlocking the Power of ChatGPT (20)

PPTX
ChatGPT: The Hype vs Reality
PPTX
PPTX
Google, Machine Learning, Algorithms, and You.
PDF
ChatGPT-GTR 22-9-23.pdf
PPTX
Google Machine Learning Algorithms and SEO
PDF
LangChain Intro by KeyMate.AI
PDF
LanGCHAIN Framework
PPTX
Chatgpt.pptx
PDF
The World of ChatGPT.pdf
PDF
ChatGPT and OpenAI.pdf
PPTX
Presentation 4 1 REDY ok.pptx
PDF
ifcckt-230213075839-984324cc.pdf
PDF
Generative AI leverages algorithms to create various forms of content
PPTX
chatgpt.pptx
PDF
ChatGPT 4o for social media step by step Guide.pdf
PDF
ChatGPT Shaping Tomorrow's Conversations
PDF
What is Chatgpt Complete Guide
DOCX
ChatGPT – What’s The Hype All About
PPTX
chatgpt by harsh verma ppt.pptx ece by arun parmar
ChatGPT: The Hype vs Reality
Google, Machine Learning, Algorithms, and You.
ChatGPT-GTR 22-9-23.pdf
Google Machine Learning Algorithms and SEO
LangChain Intro by KeyMate.AI
LanGCHAIN Framework
Chatgpt.pptx
The World of ChatGPT.pdf
ChatGPT and OpenAI.pdf
Presentation 4 1 REDY ok.pptx
ifcckt-230213075839-984324cc.pdf
Generative AI leverages algorithms to create various forms of content
chatgpt.pptx
ChatGPT 4o for social media step by step Guide.pdf
ChatGPT Shaping Tomorrow's Conversations
What is Chatgpt Complete Guide
ChatGPT – What’s The Hype All About
chatgpt by harsh verma ppt.pptx ece by arun parmar
Ad

More from Kristine Schachinger SEO and Online Marketing (19)

PPTX
Google, Updates, AI, Algorithms, and You.
PPTX
Technical SEO: How Anomalies Are Your New Best Friend."
PPTX
Core Updates: What are they? How do you recover from one?
PPTX
Social Media in the Age of Disinformation
PPTX
Core Updates: Google's New Spam and How to Recover Your Traffic.
PPTX
How Did We Get to Sesame Street? Google's Search for NLP.
PPTX
The Death of the Keyword: In Search of NLP -- Presented at Ungagged London Ap...
PPTX
In Search of Natural Language Processing: Rank Brain, Google, SEO, and You.
PPTX
Ungagged UK Talk - Google in a Post Update and Mobile First World.
PPTX
Search Leeds Talk - Entities, Search, and Rank Brain: How it works and why it...
PPTX
Links: Where We Are. Where We Are Going. A Look at Google Algorithms, SEO, an...
PPTX
Pubcon Las Vegas Mobile First / Mobile Last
PPTX
Pubcon Las Vegas Technical SEO
PPTX
Ungagged - Busting Google's Blackbox 2017
PPTX
Intro to Google, SEO, and You in 2017
PPTX
Pubcon Vegas Session - WordPress Site Security Audits
PPTX
Solving Complex SEO Problems When Standard Fixes Do Not Appl
PPT
GOOGLE PLUS, AUTHORSHIP, IDENTITY, RANK & WHAT'S NEXT.
Google, Updates, AI, Algorithms, and You.
Technical SEO: How Anomalies Are Your New Best Friend."
Core Updates: What are they? How do you recover from one?
Social Media in the Age of Disinformation
Core Updates: Google's New Spam and How to Recover Your Traffic.
How Did We Get to Sesame Street? Google's Search for NLP.
The Death of the Keyword: In Search of NLP -- Presented at Ungagged London Ap...
In Search of Natural Language Processing: Rank Brain, Google, SEO, and You.
Ungagged UK Talk - Google in a Post Update and Mobile First World.
Search Leeds Talk - Entities, Search, and Rank Brain: How it works and why it...
Links: Where We Are. Where We Are Going. A Look at Google Algorithms, SEO, an...
Pubcon Las Vegas Mobile First / Mobile Last
Pubcon Las Vegas Technical SEO
Ungagged - Busting Google's Blackbox 2017
Intro to Google, SEO, and You in 2017
Pubcon Vegas Session - WordPress Site Security Audits
Solving Complex SEO Problems When Standard Fixes Do Not Appl
GOOGLE PLUS, AUTHORSHIP, IDENTITY, RANK & WHAT'S NEXT.

Recently uploaded (20)

PDF
CIFDAQ's Market Insight: SEC Turns Pro Crypto
PDF
GamePlan Trading System Review: Professional Trader's Honest Take
PDF
solutions_manual_-_materials___processing_in_manufacturing__demargo_.pdf
PPTX
Understanding_Digital_Forensics_Presentation.pptx
PDF
Empathic Computing: Creating Shared Understanding
PDF
Shreyas Phanse Resume: Experienced Backend Engineer | Java • Spring Boot • Ka...
PDF
Network Security Unit 5.pdf for BCA BBA.
PDF
Diabetes mellitus diagnosis method based random forest with bat algorithm
PPTX
PA Analog/Digital System: The Backbone of Modern Surveillance and Communication
PDF
Review of recent advances in non-invasive hemoglobin estimation
PPTX
Cloud computing and distributed systems.
PDF
Chapter 3 Spatial Domain Image Processing.pdf
PPT
Teaching material agriculture food technology
PPTX
Big Data Technologies - Introduction.pptx
PDF
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
PDF
Advanced methodologies resolving dimensionality complications for autism neur...
PDF
cuic standard and advanced reporting.pdf
PDF
7 ChatGPT Prompts to Help You Define Your Ideal Customer Profile.pdf
PDF
[발표본] 너의 과제는 클라우드에 있어_KTDS_김동현_20250524.pdf
PDF
Reach Out and Touch Someone: Haptics and Empathic Computing
CIFDAQ's Market Insight: SEC Turns Pro Crypto
GamePlan Trading System Review: Professional Trader's Honest Take
solutions_manual_-_materials___processing_in_manufacturing__demargo_.pdf
Understanding_Digital_Forensics_Presentation.pptx
Empathic Computing: Creating Shared Understanding
Shreyas Phanse Resume: Experienced Backend Engineer | Java • Spring Boot • Ka...
Network Security Unit 5.pdf for BCA BBA.
Diabetes mellitus diagnosis method based random forest with bat algorithm
PA Analog/Digital System: The Backbone of Modern Surveillance and Communication
Review of recent advances in non-invasive hemoglobin estimation
Cloud computing and distributed systems.
Chapter 3 Spatial Domain Image Processing.pdf
Teaching material agriculture food technology
Big Data Technologies - Introduction.pptx
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
Advanced methodologies resolving dimensionality complications for autism neur...
cuic standard and advanced reporting.pdf
7 ChatGPT Prompts to Help You Define Your Ideal Customer Profile.pdf
[발표본] 너의 과제는 클라우드에 있어_KTDS_김동현_20250524.pdf
Reach Out and Touch Someone: Haptics and Empathic Computing

Unlocking the Power of ChatGPT

  • 1. @schachin Kristine Schachinger Kristine@SitesWithoutWalls.com "Unlocking the Power of ChatGPT” -- without blowing yourself up -- “…they are prone to hallucinating, and crucially they are incapable of justifying their utterances…”
  • 2. @schachin Kristine Schachinger What is a “Chat Generative Pre-trained Transformer”?
  • 5. @schachin Kristine Schachinger GPT, ChatGPT, and … Large Language Models. Dalle’s vision of ChatGPT
  • 6. @schachin Kristine Schachinger Why are LLMs So Special? Unlike embedded based language models LLMs can disambiguate words from the sentence and apply meaning forward and backward to those words in order to predict a masked word using those applied contexts. This is SUPER EFFICIENT!
  • 7. @schachin Kristine Schachinger Why are LLMs So Special? Large Language modeling can determine the meaning of words in context so it can better predict the next word in the sentence. These sentences mean two different things forward and backward.
  • 8. @schachin Kristine Schachinger How does this work? Transformers What are transformers? A transformer in language processing is a type of computer program that is designed to understand and generate text. It does this by using a special type of algorithm called self-attention. Self-attention allows the program to look at all the words in a sentence or a piece of text at once, and understand how they relate to each other, rather than just one word at a time like traditional methods. This way it can better understand the meaning of the text, and can generate text that is more similar to how a human would write.
  • 9. @schachin Kristine Schachinger LLMs can go forward and backwards to predict an unknown (masked) term and/or sentence. Also uses root words, so play for player/playing/played are the same This allows them to derive context for what is being written. Previous models were based on word vectors (entities and knowledge graphs) LLM Transformers are Bidirectional https://blog.google/products/search/search-language-understanding-bert/
  • 11. @schachin Kristine Schachinger Simply language modeling is “Language modeling – although it sounds formidable – is essentially just predicting words in a blank.”
  • 12. @schachin Kristine Schachinger Large Language Models? Some of the more relevant well-known LLMs are: • OpenAI  GPT-2/3  ChatGPT 2 & 3.x  ChatGPT 4 should be released this year.  WebGPT  attempts to resolve the issue of attribution and accuracy  Google  BERT  Used in Search  LaMDA  conversational like ChatGPT  “Unlike GPT-3, which is not configured to perform any specific task, LaMDA is “trained on dialogue”:  PaLM  Search relevancy  it is also trained using a “combination of English and multilingual datasets that include high-quality web documents, books, Wikipedia, conversations and GitHub code” to drive greater accuracy in responses. Learn more about these and others  https://seekingalpha.com/article/4563975-google-why-is-no-one-talking-about-palm
  • 14. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: What is ChatGPT? Let’s Ask It! ChatGPT is/was • a variant of the GPT (Generative Pre-training Transformer) language model • introduced by OpenAI in 2018. • GPT trained on a massive dataset of over 40GB of text data for GPT-2 and 45TB for GPT-3.x • ChatGPT includes conversational text from books, articles, and websites. • capable of generating human-like text • useful for certain tasks • language translation, text summarization, and question answering. • fine-tuned on several specific • writing poetry, composing music, and even coding. • one of the largest language models currently available • over 175 billion parameters • used in several real-world applications • chatbots, automated customer service, and even writing news articles. • continuously being updated and improved by OpenAI • GPT4 will come out this year
  • 15. @schachin Kristine Schachinger TeThje What is ChatGPT? In layman’s terms, a large language model (LLM), which generates convincing sentences by mimicking the statistical patterns of language in a huge database of text collated from the Internet. It was trained to sound confident to humans even when it is wrong. https://www.nature.com/articles/d41586-023-00107-z
  • 16. @schachin Kristine Schachinger ChatGPT is Predictive Text. It is predicting the next most likely word in a sentence based on the context of the other words in the sentence derived from the information it was trained on.
  • 17. @schachin Kristine Schachinger TeThje What is ChatGPT NOT? • A Search Engine • The data was trained only up to 2021 • It is not connected to the Internet, so it cannot retrieve information • Is based on predictive text NOT information retrieval • There is no QUALITY check for the accuracy of the content or code • Creative • if it was not trained on the information, it cannot generate something as a human would from inference or imagination. https://www.nature.com/articles/d41586-023-00107-z
  • 19. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Some ChatGPT Ideas for Marketers • SEO: Titles and Metas (okayed by Google) • PPC Landing Pages • Content Ideas • Content NOT for Search • Topical Funnels • Analyze Competitor Site Content • Product Descriptions • Customer Service / Chatbots • Emails • Outreach • Link Building • Lead Generation • Newsletters • Reviews digital marketer using AI to do SEO Disney style
  • 20. @schachin Kristine Schachinger ALWAYS USE HUMAN REVIEW. ChatGPT is not a search engine, has no fact checking function, and was not trained on any data past 2021 so make sure someone reviews the output produced for errors, accuracy, factual information, and tone.
  • 21. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: What It’s NOT For? Writing content that will be submitted to the search engines. • AI Content is Detectable • How? • AI knows what AI would ”produce” and can estimate how much matches AI • AI Content from ChatGPT will soon have cryptographic ”watermarks” • You can’t simply edit the text and know you have removed these. • This means ChatGPT will also be able to provide these watermarks to its AI detector which is available to anyone or any company. • MSFT will have a 49% stake in OpenAI and access to the watermarked information
  • 23. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: ChatGPT Detection Tools. OpenAI • Professional for Educators and Researchers • https://chatgpt.pro/gptzero/ Hugging Face • Built on GPT 2 but still pretty good with GPT 3.x • https://huggingface.co/spaces/openai/openai-detector From IBM/Harvard/MIT • Giant Language model Test Room (GLTR) • Also built on GPT 2 but still fairly reliable • http://gltr.io/dist/index.html Writer • AI writing tool but detector is pretty solid • https://writer.com/ai-content-detector/ Stanford Student (SAME AS OpenAI) • https://gptzero.me/ Some of the known detections tools Content Detection Tools
  • 24. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Detection.
  • 25. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Detection and Google. Google says AI Content is okay IF it provides value and it not “spammy”, But since it is writing what it trained on how does provide value?
  • 26. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Detection and Google. How does Google define “Spammy” content?
  • 27. @schachin Kristine Schachinger Play it safe, do not use ChatGPT or AI to write article content. Use humans to write/edit your content. They can use ChatGPT as a tool to generate ideas, however.
  • 29. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT. The Application of ChatGPT Some of the potential applications of ChatGPT include: • Text generation: ChatGPT can be used to generate human-like text responses to prompts, which makes it useful for creating chatbots for customer service, generating responses to questions in online forums, or even creating personalized content for social media posts. • Language translation: ChatGPT can also be used for language translation tasks. By providing the model with a text prompt in one language and specifying the target language, the model can generate accurate and fluent translations of the text. • Text summarization: ChatGPT can be used to generate summaries of long documents or articles. This can be useful for quickly getting an overview of a text without having to read the entire document. • Sentiment analysis: ChatGPT can be used to analyze the sentiment of a given text. This can be useful for understanding the overall tone and emotion of a piece of writing, or for detecting the sentiment of customer feedback in order to improve customer satisfaction.
  • 30. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT. Fine Tuning in ChatGPT Training. ChatGPT was trained with the following focuses: • Code • Content Writing • Poetry • Music This means it tends to create these items well. Fine tuning allows ChatGPT to focus in on certain types of functions and may not do as well with others.
  • 32. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: InstructGPT: ChatGPT Prompts. Prompts. The MOST Important Part of Using ChatGPT. Prompts provide a starting point for ChatGPT to generate text based on the input given. They can be used to guide the model's output and control the context of the generated text. Prompts? Simply means, how you tell ChatGPT what to write. This relies on another language model called InstructGPT, which allows you to give ChatGPT detailed and specific instructions. https://www.searchenginejournal.com/chatgpt-for-content-and-seo/473823/#close
  • 34. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Content > Articles.
  • 35. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Content > Articles + Style.
  • 36. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Content > FAQs.
  • 37. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Code.
  • 38. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Summarization > URLs.
  • 39. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Summarize URLs.
  • 40. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Write Emails.
  • 41. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Lyrics.
  • 42. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Poetry.
  • 43. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Using ChatGPT Prompts: Ideas.
  • 44. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: ChatGPT Prompts. Prompts. How to write ChatGPT Prompts • Give Context • Be Clear • Be Concise • Be Specific • Be Descriptive • Define Format • Define Length • Define Style
  • 45. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: ChatGPT Prompts. Prompts. Some great ideas for how you can use ChatGPT • 100 Best ChatGPT Prompts • https://mpost.io/100-best-chatgpt-prompts-to-unleash-ais-potential/ • Web Development ChatGPT • Music ChatGPT • Business ChatGPT • Educational ChatGPT • Comedy ChatGPT • History ChatGPT • Health&Medicine ChatGPT • Art ChatGPT • Food & Cooking ChatGPT • Marketing ChatGPT • Game ChatGPT Prompts https://www.searchenginejournal.com/chatgpt-for-content-and-seo/473823/#close
  • 47. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: ChatGPT Issues? + Programmed to Avoid Certain Kinds of Content • ChatGPT is specifically programmed to not generate text on the topics of graphic violence, explicit sex, and content that is harmful such as instructions on how to build an explosive device. • And swearing + Unaware of Current Events • not aware of any content that is created after 2021.  Has Built-in Biases • This can be just in the writing style, not necessarily cultural or racial though they can exist as well + ChatGPT Requires Highly Detailed Instructions • You must be very specific with ChatGPT Prompts to really get good output + Mediocre Content • ChatGPT is designed to sound confident, but the content it writes is not high quality. + Suffers from “Hallucinations” • Makes stuff up https://www.searchenginejournal.com/chatgpt-for-content-and-seo/473823/#close
  • 49. @schachin Kristine Schachinger https://www.wired.com/story/chatgpt-fluent-bs/ All of this makes playing around with ChatGPT incredibly fun, charmingly addictive, and—as someone who writes for a living—really quite worrying. But you soon start to sense a lack of depth beneath ChatGPT’s competent prose. It makes factual errors, conflating events and mixing people up. It relies heavily on tropes and cliché, and it echoes society’s worst stereotypes. Its words are superficially impressive but largely lacking in substance— ChatGPT mostly produces what The Verge has described as “fluent bullshit.” But that kind of makes sense. ChatGPT was trained on real-world text, and the real world essentially runs on fluent bullshit. “Bovine Feces”
  • 51. @schachin Kristine Schachinger Google https://www.semanticscholar.org/paper/Rethinking-Search%3A-Making-Domain-Experts-out-of-Metzler-Tay/e3d7065d6196437259483ed8b9b70ba4b4bb76ad “…they do not have a true understanding of the world, they are prone to hallucinating, and crucially they are incapable of justifying their utterances by referring to supporting documents in the corpus they were trained over.” Image from DALL-E
  • 52. @schachin Kristine Schachinger Google https://www.semanticscholar.org/paper/Rethinking-Search%3A-Making-Domain-Experts-out-of-Metzler-Tay/e3d7065d6196437259483ed8b9b70ba4b4bb76ad “…they do not have a true understanding of the world, they are prone to hallucinating, and crucially they are incapable of justifying their utterances by referring to supporting documents in the corpus they were trained over.” Image from DALL-E “…they are prone to hallucinating, and crucially they are incapable of justifying their utterances…”
  • 54. @schachin Kristine Schachinger ALWAYS USE HUMAN REVIEW. ChatGPT is not a search engine, has no fact checking function, and was not trained on any data past 2021 so make sure someone reviews the output produced for errors, accuracy, factual information, and tone.
  • 56. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: ChatGPT Docs. ChatGPT Guide • All the basics you need to know about how to use ChatGPT • https://www.digitaltrends.com/computing/how-to-use-openai-chatgpt-text-generation-chatbot/#google_vignette OpenAI ChatGPT API Guide. • Everything you need to know about using the API version • https://beta.openai.com/docs/guides/completion/inserting-text Some cool things people have done with ChatGPT • https://www.bleepingcomputer.com/news/technology/openais-new-chatgpt-bot-10-coolest-things-you-can-do-with-it/
  • 57. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: ChatGPT PRO Tools. Full List of ChatGPT PRO Tools. Cost will be $42 a month as of January 22, 2023 • https://chatgpt.pro/chatgpt-plugins/ Partial List • WebChatGPT • ChatGPT Writer • Whatsapp GPT • Search GPT Shortcut • YouTube Summary • ChatGPT in google docs • TweetGPT • ChatGPT for Search Engines • Everywhere • ChatGPT History
  • 58. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: ChatGPT Marketing/SEO Tool. Google Chrome Extensions AIPRM https://www.aiprm.com/ Once added to your browser it will show up in your ChatGPT page when you login. It has ChatGPT Tools for • SEO • Marketing • Sales/SASS
  • 60. @schachin Kristine Schachinger Some of the general parameters that are used to train language models include: Google Suite of AI Tools LaMDA is Google’s version of ChatGPT & built on the same technology as ChatGPT “…. there is no official word whether will call it LaMDA or any other name, but Google is expected to show more than 20 similar AI products including 'Shopping Try-on' for YouTube (to help users try on new clothes), Maya: (3D image generator), video summarization tool, a Pixel exclusive wallpaper generator, an AI tool for enterprise customers to developer their own ChatGPT-like bot, Colab + Android Studio (to help software programmers to detect and fix bugs) …and more at upcoming annual Google I/O...” Read more at: https://www.deccanherald.com/business/technology/google-to- demo-chatgpt-altenative-at-i/o-2023-1183735.html
  • 61. @schachin Kristine Schachinger Kristine@SitesWithoutWalls.com "Unlocking the Power of ChatGPT” -- without blowing yourself up -- “…they are prone to hallucinating, and crucially they are incapable of justifying their utterances…”