Pam Baker

Article / Updated 12-09-2024

As you delve deeper into the realm of prompt engineering, you find out that the effectiveness of a prompt can vary greatly depending on the application. Whether you’re using AI for creative writing, data analysis, customer service, or any other specific use, the prompts you use need to be tailored to fit the task at hand. The art in prompt engineering is matching your form of communication to the nature of the task. If you succeed, you’ll unlock the vast potential of AI. For instance, when engaging with AI for creative writing, your prompts should be open-ended and imaginative, encouraging the AI to generate original and diverse ideas. A prompt like “Write a story about a lost civilization discovered by a group of teenagers” sets the stage for a creative narrative. In contrast, data analysis requires prompts that are precise and data-driven. Here, you might need to guide the AI with specific instructions or questions, such as “Analyze the sales data from the last quarter and identify the top-performing products.” You may need to include that data in the prompt if it isn’t already loaded into the training data, retrieval-augmented generation (RAG), system or custom messages, or a specialized GPT. In any case, this type of prompt helps the AI focus on the exact task, ensuring that the output is relevant and actionable. The key to designing effective prompts lies in understanding the domain you’re addressing. Each field has its own set of terminologies, expectations, and objectives. For example, legal prompts require a different structure and language than those used in entertainment or education. It’s essential to incorporate domain-specific knowledge into your prompts to guide the AI in generating the desired output. Following are some examples across various industries that illustrate how prompts can be tailored for domain-specific applications: Legal domain: In the legal industry, precision and formality are paramount. Prompts must be crafted to reflect the meticulous nature of legal language and reasoning. For instance, a prompt for contract analysis might be, “Identify and summarize the obligations and rights of each party as per the contract clauses outlined in Section 2.3 and 4.1.” This prompt is structured to direct the AI to focus on specific sections, reflecting the detailed-oriented nature of legal work. Healthcare domain: In healthcare, prompts must be sensitive to medical terminology and patient privacy. A prompt for medical diagnosis might be, “Given the following anonymized patient symptoms and test results, what are the potential differential diagnoses?” This prompt respects patient confidentiality while leveraging the AI’s capability to process medical data. Education domain: Educational prompts often aim to engage and instruct. A teacher might use a prompt like, “Create a lesson plan that introduces the concept of photosynthesis to 5th graders using interactive activities.” This prompt is designed to generate educational content that is age-appropriate and engaging. Finance domain: In finance, prompts need to be data-driven and analytical. A financial analyst might use a prompt such as, “Analyze the historical price data of XYZ stock over the past year and predict the trend for the next quarter based on the moving average and standard deviation.” This prompt asks the AI to apply specific financial models to real-world data. Marketing domain: Marketing prompts often focus on creativity and audience engagement. A marketing professional could use a prompt like, “Generate a list of catchy headlines for our new eco-friendly product line that will appeal to environmentally conscious consumers.” This prompt encourages the AI to produce creative content that resonates with a target demographic. Software development domain: In software development, prompts can be technical and require understanding of coding languages. A prompt might be, “Debug the following Python code snippet and suggest optimizations for increasing its efficiency.” This prompt is technical, directing the AI to engage with code directly. Customer service domain: For customer service, prompts should be empathetic and solution oriented. A prompt could be, “Draft a response to a customer complaint about a delayed shipment, ensuring to express understanding and offer a compensatory solution.” This prompt guides the AI to handle a delicate situation with care. By understanding the unique requirements and language of each domain, you can craft prompts to effectively guide AI in producing the desired outcomes. It’s not just about giving commands; it’s about framing them in a way that aligns with the goals, terms, and practices of the industry in question. As AI continues to evolve, the ability to engineer precise and effective prompts becomes an increasingly valuable skill across all sectors. 15 tips and tricks for better AI prompting Although GenAI may seem like magic, it takes knowledge and practice to write effective prompts that will generate the content you’re looking for. The following list provides some insider tips and tricks to help you optimize your prompts to get the most out of your interactions with GenAI tools: Know your goal. Decide what you want from the AI — like a simple how-to or a bunch of ideas — before you start asking. Get specific. The clearer you are, the better the AI can help. Ask “How do I bake a beginner's chocolate cake?” instead of just “How do I make a cake?” Keep it simple. Use easy language unless you’re in a special field like law or medicine where using the right terms is necessary. Add context. Give some background if it's a special topic, like tips for small businesses on social media. Play pretend. Tell the AI to act like someone, like a fitness coach, to get answers that fit that role. Try again. If the first answer isn't great, change your question a bit and ask again. Show examples. If you want something creative, show the AI an example to follow, like asking for a poem like one by Robert Frost. Don't overwhelm. Keep your question focused. If it's too packed with info, it gets messy. Mix it up. Try asking in different ways, like with a question or a command, to see what works best. Embrace the multimodal functionality. Multimodal functionality means that the GenAI model you’re working with can accept more than one kind of prompt input. Typically, that means it can accept both text and images in the input. Understand the model’s limitations. GenAI is not infallible and can still produce errors or “hallucinate” responses. Always approach the AI’s output with a critical eye and use it as a starting point rather than the final word on any subject. Leverage the enhanced problem-solving abilities. GenAI’s enhanced problem-solving skills mean that you can tackle more complex prompts. Use this to your advantage when crafting prompts that require a deep dive into a topic. Keep prompts aligned with AI training. For example, remember that GPT-4, like its predecessors, is trained on a vast dataset up to a certain point in time (April 2023 at the time of this writing). It doesn’t know about anything that happened after that date. If you need to reference more recent events or data, provide that context within your prompt. Experiment with different prompt lengths. Short prompts can be useful for quick answers, while longer, more detailed prompts can provide more context and yield more comprehensive responses. Incorporate feedback loops. After receiving a response from your GenAI application, assess its quality and relevance. If it hit — or is close to — the mark, click on the thumbs-up icon. If it’s not quite what you were looking for, provide feedback in your next prompt by clicking on the thumbs-down icon. This iterative process can help refine the AI’s understanding of your requirements and improve the quality of future responses. By keeping these tips in mind and staying informed about the latest developments in the capabilities of various GenAI models and applications, you’ll be able to craft prompts that are not only effective but also responsible and aligned with the AI’s strengths and limitations. How to use prompts to fine-tune the AI model The point of prompt engineering is to carefully compose a prompt that can shape the AI’s learning curve and fine-tune its responses to perfection. In this section, you dive into the art of using prompts to refine the GenAI model, ensuring that it delivers the most accurate and helpful answers possible. In other words, you discover how to use prompts to also teach the model to perform better for you over time. Here are some specific tactics: When you talk to the AI and it gives you answers, tell it if you liked the answer or not. Do this by clicking the thumbs up or thumbs down, or the + or – icons above or below the output. The model will learn how to respond better to you and your prompts over time if you do this consistently. If the AI gives you a weird answer, there's a “do-over” button you can press. It's like asking your friend to explain something again if you didn't get it the first time. Look for “Regenerate Response'’ or some similar wording (term varies among models) near the output. Click on that and you’ll instantly get the AI’s second try! Think of different ways to ask the AI the same or related questions. It's like using magic words to get the best answers. If you're really good at it, you can make a list of prompts that others can use to ask good questions too. Prompt libraries are very helpful to all. It’s smart to look at prompt libraries for ideas when you’re stumped on how or what to prompt. Share your successful prompts. If you find a super good way to ask something, you can share it online (at sites like GitHub) with other prompt engineers and use prompts others have shared there too. Instead of teaching the AI everything from scratch (retraining the model), you can teach it a few more new things through your prompting. Just ask it in different ways to do new things. Over time, it will learn to expand its computations. And with some models, what it learns from your prompts will be stored in its memory. This will improve the outputs it gives you too! Redirect AI biases. If the AI says something that seems mean or unfair, rate it a thumbs down and state why the response was unacceptable in your next prompt. Also, change the way you ask questions going forward to redirect the model away from this tendency. Be transparent and accountable when you work with AI. Tell people why you're asking the AI certain questions and what you hope to get from it. If something goes wrong, try to make it right. It's like being honest about why you borrowed your friend's toy and fixing it if it breaks. Keep learning. The AI world changes a lot, and often. Keep up with new models, features, and tactics, talk to others, and always try to get better at making the AI do increasingly more difficult things. The more you help GenAI learn, the better it gets at helping you! What to do when AI goes wrong When you engage with AI through your prompts, be aware of common pitfalls that can lead to biased or undesirable outcomes. Following are some strategies to avoid these pitfalls, ensuring that your interactions with AI are both effective and ethically sound. Recognize and mitigate biases. Biases in AI can stem from the data it was trained on or the way prompts are structured. For instance, a healthcare algorithm in the United States inadvertently favored white patients over people of color because it used healthcare cost history as a proxy for health needs, which correlated with race. To avoid such biases, carefully consider the variables and language used in your prompts. Ensure they do not inadvertently favor one group over another or perpetuate stereotypes. Question assumptions. Wrong or flawed assumptions can lead to misguided AI behavior. For example, Amazon’s hiring algorithm developed a bias against women because it was trained on resumes predominantly submitted by men. Regularly review the assumptions behind your prompts and be open to challenging and revising them as needed. Avoid overgeneralization. AI can make sweeping generalizations based on limited data. To prevent this, provide diverse and representative examples in your prompts. This helps the AI understand the nuances and variations within the data, leading to more accurate and fair outcomes. Keep your purpose in sight. Losing sight of the purpose of your interaction with AI can result in irrelevant or unhelpful responses. Always align your prompts with the intended goal and avoid being swayed by the AI’s responses into a direction that deviates from your original objective. Diversify information sources. Relying on too narrow a set of information can skew AI responses. Ensure that the data and examples you provide cover a broad spectrum of scenarios and perspectives. This helps the AI develop a well-rounded understanding of the task at hand. For example, if the AI is trained to find causes of helicopter crashes and the only dataset the AI has is of events when helicopters crash, it will deduce that all helicopters crash which in turn will render skewed outputs that could be costly or even dangerous. Add data on flights or events when helicopters did not crash, and you’ll get better outputs because the model has more diverse and more complete information to analyze. Encourage open debate. AI can sometimes truncate debate by providing authoritative-sounding answers. Encourage open-ended prompts that allow for multiple viewpoints and be critical of the AI’s responses. This fosters a more thoughtful and comprehensive exploration of the topic. Be wary of consensus. Defaulting to consensus can be tempting, especially when AI confirms our existing beliefs. However, it’s important to challenge the AI and yourself by considering alternative viewpoints and counterarguments. This helps in uncovering potential blind spots and biases. Check your work. Always review the AI’s responses for accuracy and bias. As with the healthcare algorithm that skewed resources toward white patients, unintended consequences can arise from seemingly neutral variables. Rigorous checks and balances are necessary to ensure the AI’s outputs align with ethical standards.

Cheat Sheet / Updated 10-17-2024

The first public release of ChatGPT ignited the world’s demand for increasingly sophisticated Generative AI (GenAI) models and tools, and the market was quick to deliver. But what’s the use of having so many GenAI tools if you get stuck using them? And make no mistake, everyone gets stuck quite often! This cheat sheet helps you get the very best results by introducing you to advanced (but pretty easy) prompting techniques and giving you useful tips on how to choose models or applications that are right for the task.

Article / Updated 10-31-2023

Indeed, prompting is both the easy part and the most difficult part of using a generative artificial intelligence (AI) model, like ChatGPT. Difficulties in the complexity of cues and nuances in text-based prompts are why some organizations have a prompt engineering job role. What is a ChatGPT prompt? It's a phrase or sentence that you write in ChatGPT to initiate a response from the AI. ChatGPT responds based on its existing knowledge base. Don't have time to read the entire article? Jump to the quick read summary. Prompt engineering is the act of crafting an input, which is a deed borne partly of art and partly of logic. And yes, you can do this! However, you might want to practice and polish your prompting skills before you apply for a job. Considering how to prompt ChatGPT, if you have a good command of the subtleties of language and great critical-thinking and problem-solving skills, seasoned with more than a dash of intuitive intelligence, you’ll be amazed at the responses you can tease out of this technology with a single, well-worded prompt. When you prompt ChatGPT, you are embedding the task description in the input (called the prompt) in a natural-language format, rather than entering explicit instructions via computer code. Prompt engineers can be trained AI professionals or people who possess sufficient intuitive intelligence or skills transferrable to crafting the best prompts for ChatGPT (or other generative AI platforms) that solicit the desired outputs. One example of a transferrable skill is a journalist’s ability to tease out the answers they seek in an interview by using direct or indirect methods. Prompt-based learning is a strategy AI engineers use to train large language models. The engineers make the model multipurpose to avoid retraining it for each new language-based task. Currently, the demand for talented writers who know how to write a prompt, or prompt engineers, is very high. However, there is a strong debate as to whether employers should delineate this unique skill as a dedicated job role, a new profession, or a universal skill to be required of most workers, much like typing skills are today. Meanwhile, people are sharing their prompts with other ChatGPT users in several forums. You can see one example on GitHub. How to write a prompt If you enter a basic prompt, you’ll get a bare-bones, encyclopedic-like answer, as shown in the figure below. Do that enough times and you’ll convince yourself that this is just a toy and you can get better results from an internet search engine. This is a typical novice’s mistake and a primary reason why beginners give up before they fully grasp what ChatGPT is and can do. Understand that your previous experience with keywords and search engines does not apply here. To write awesome ChatGPT prompts, you must think of and use ChatGPT in a different way. Think hard about how you’re going to word your prompt. You have many options to consider. You can assign ChatGPT a role or a persona, or several personas and roles if you decide it should respond as a team, as illustrated in the following figure. You can assign yourself a new role or persona as well. Or tell it to address any type of audience, such as a high school graduating class, a surgical team, or attendees at a concert or a technology conference. You can set the stage or situation in great or minimum detail. You can ask a question, give it a command, or require specific behaviors. A prompt, as you can see now, is much more than a question or a command. Your success with ChatGPT hinges on your ability to master crafting a prompt in such a way as to trigger the precise response you seek. Ask yourself these questions as you are writing or evaluating your prompt: Who do you want ChatGPT to be? Where, when, and what is the situation or circumstances you want ChatGPT’s response framed within? Is the question you're entering in the prompt the real question you want it to answer, or were you trying to ask something else? Is the command you're prompting complete enough for ChatGPT to draw from sufficient context to give you a fuller, more complete, and richly nuanced response? And the ultimate question for you to consider: Is your prompt specific and detailed, or vague and meandering? Whichever is the case, that’s what ChatGPT will mirror in its response. ChatGPT’s responses are only as good as your prompt. That’s because the prompt starts a pattern that ChatGPT must then complete. Be intentional and concise about how you present that pattern starter — the prompt. For more details on using ChatGPT, including how to start a chat, reviewing your chat history, and much more, check out my book ChatGPT For Dummies. Thinking in threads Conversations happen when one entity’s expression initiates and influences another entity’s response. Most conversations do not conclude after a simple one-two exchange like this, but rather continue in a flow of responses cued by the interaction with the other participant. The resulting string of messages in a conversation is called a thread. To increase your success with ChatGPT, write prompts as part of a thread rather than as standalone queries. In this way, you'll craft prompts targeted towards the outputs you seek, building one output on another to reach a predetermined end. In other words, you don’t have to pile everything into one prompt. You can write a series of prompts to more precisely direct ChatGPT’s “thought processes.” Basic prompts result in responses that can be too general or vague. When you think in threads, you’re not aiming to craft a series of basic prompts; you’re looking to break down what you seek into prompt blocks that aim ChatGPT’s responses in the direction you want the conversation to go. In effect, you're using serialized prompts to manipulate the content and direction of ChatGPT's response. Does it work all the time? No, of course not. ChatGPT can opt for an entirely different response than expected, repeat an earlier response, or simply hallucinate one. But serialized prompts do work often enough to enable you to keep the conversation targeted and the responses flowing toward the end you seek. You can use this method to shape a single prompt by imagining someone asking for clarification of your thought or question. Write the prompt so that it includes that information, and the AI model will have more of the context it needs to deliver an intelligent and refined answer. ChatGPT will not ask for clarification of your prompt; it will guess at your meaning instead. You’ll typically get better quality responses by clarifying your meaning in the prompt itself at the outset. Chaining prompts and other tips and strategies Here’s a handy list of other tips and refinements to help get you started on the path to mastering the art of the prompt: Plan to spend more time than expected on crafting a prompt. No matter how many times you write prompts, the next one you write won’t be any easier to do. Don’t rush this part. Start by defining the goal. What exactly do you want ChatGPT to deliver? Craft your prompt to push ChatGPT towards that goal; if you know where you want to end up, you’ll be able to craft a prompt that will get you there. Think like a storyteller, not an inquisitor. Give ChatGPT a character or a knowledge level from which it should shape its answer. For example, tell ChatGPT that it's a chemist, an oncologist, a consultant, or any other job role. You can also instruct it to answer as if it were a famous person, such as Churchill, Shakespeare, or Einstein, or a fictional character such as Rocky. Give it a sample of your own writing and instruct ChatGPT to write its answer to your question, or complete the task in the way you would. Remember that any task or thinking exercise (within reason and the law) is fair game and within ChatGPT’s general scope. For example, instruct ChatGPT to check your homework, your kids’ homework, or its own homework. Enter something such as computer code or a text passage in quotation marks and instruct ChatGPT to find errors in it or in the logic behind it. Or skip the homework checking and ask it to help you think instead. Ask it to finish a thought, an exercise, or a mathematical equation that has you stumped. The only limit to what you can ask is your own imagination and whatever few safety rules the AI trainer installed. Be specific. The more details you include in the prompt, the better. Basic prompts lead to basic responses. More specific and concise prompts lead to more detailed responses, more nuanced responses, and better performance in ChatGPT’s responses — and usually well within token limits. Use prompt chains as a way of strategizing. Prompt chaining is a technique used to build chatbots, but we can reimagine it here as a way to develop a strategic plan using combined or serial prompting in ChatGPT. This technique uses multiple prompts to guide ChatGPT through a more complex thought process. You can use multiple prompts as a single input, such as telling ChatGPT it's a team consisting of several members with different roles, all of whom are to answer the one prompt you entered. Or you can use multiple prompts in a sequence in which the output of one becomes the input of the next. In this case, each response builds on the prompt you just entered and the prompts you entered earlier. This type of a prompt chain forms organically, unless you stop ChatGPT from considering earlier prompts in its responses by starting a new chat. Use prompt libraries and tools to improve your prompting. Some examples follows: Check out the Awesome ChatGPT Prompts repository on GitHub at https://github.com/f/awesome-chatgpt-prompts Use a prompt generator to ask ChatGPT to improve your prompt by visiting PromptGenerator. Visit ChatGPT and Bing AI Prompts on GitHub. Use a tool such as Hugging Face’s ChatGPT Prompt Generator. Try specialized prompt templates, such as the curated list for sales and marketing use cases at Tooltester. On GitHub, you can find tons of curated lists in repositories as well as lots of free prompting tools from a variety of sources. Just make sure that you double-check sources, apps, and browser extensions for malware before using or relying on them. Quick Read Summary Writing effective prompts for ChatGPT is both a craft and a science. A prompt is the phrase or sentence that initiates a response from the AI model. To excel in this skill, consider these essential tips. Crafting an artful prompt: A well-crafted prompt is essential to unlock ChatGPT's potential. Think beyond basic questions and commands. You can assign roles or personas to ChatGPT, set the stage, or address different audiences. Prompt engineering: This skill can be highly valuable. It involves creating prompts that draw out the desired responses from the AI. Prompt engineers often have a background in AI, journalism, or other fields where they've honed their ability to solicit specific information. Thinking in threads: Instead of standalone queries, use prompts as part of a conversation thread. This helps you build on previous outputs and guide the AI's responses toward your desired end. Chaining prompts: Connect prompts sequentially to steer ChatGPT's thought process. This approach can lead to more targeted and refined responses. Be patient and put thought into each prompt. Specificity is key: Detailed prompts lead to more detailed and nuanced responses. Avoid vague or meandering instructions, as ChatGPT mirrors the prompt's clarity. Prompt libraries and tools: Leverage existing resources to improve your prompting skills. There are repositories and tools available, like the Awesome ChatGPT Prompts repository on GitHub and Hugging Face's ChatGPT Prompt Generator. The art of imagination Within reasonable and legal limits, you can instruct ChatGPT for various tasks, from checking homework to creative writing. The only boundary is your imagination. In a world where the demand for skilled prompt writers is increasing, your ability to craft the perfect prompt is a valuable asset. By mastering this art, you can unlock the full potential of ChatGPT and guide its responses to meet your specific needs. Hungry for more? Go back and read the article or check out the book.

Article / Updated 10-30-2023

ChatGPT is a huge phenomenon and a major paradigm shift in the accelerating march of technological progression. Artificial intelligence (AI) research company OpenAI released a free preview of the chatbot in November 2022, and by January 2023, it had more than a million users. So, what is chatgpt? It's a large language model (LLM) that belongs to a category of AI called generative AI , which can generate new content rather than simply analyze existing data. Don't have time to read the entire article? Jump to the quick read summary. Additionally, anyone can interact with ChatGPT (GPT stands for generative pre-trained transformer) in their own words. A natural, humanlike dialog ensues. ChatGPT is often directly accessed online by users, but it is also being integrated with several existing applications, such as Microsoft Office apps (Word, Excel, and PowerPoint) and the Bing search engine. The number of app integrations seems to grow every day as existing software providers hurry to capitalize on ChatGPT’s popularity. What is ChatGPT used for? The ways to use ChatGPT are as varied as its users. Most people lean towards more basic requests, such as creating a poem, an essay, or short marketing content. Students often turn to it to do their homework. Heads up, kids: ChatGPT stinks at answering riddles and sometimes word problems in math. Other times, it just makes things up. In general, people tend to use ChatGPT to guide or explain something, as if the bot were a fancier version of a search engine. Nothing is wrong with that use, but ChatGPT can do so much more. How much more depends on how well you write the prompt. If you write a basic prompt, you’ll get a bare-bones answer that you could have found using a search engine such as Google or Bing. That’s the most common reason why people abandon ChatGPT after a few uses. They erroneously believe it has nothing new to offer. But this particular failing is the user’s fault, not ChatGPT’s. What can ChatGPT do? This list covers just some of the more unique uses of this technology. Users have asked ChatGPT to: Conduct an interview with a long-dead legendary figure regarding their views of contemporary topics. Recommend colors and color combinations for logos, fashion designs, and interior decorating designs. Generate original works such as articles, e-books, and ad copy. Predict the outcome of a business scenario. Develop an investment strategy based on stock market history and current economic conditions. Make a diagnosis based on a patient’s real-world test results. Write computer code to make a new computer game from scratch. Leverage sales leads. Inspire ideas for a variety of things from A/B testing to podcasts, webinars, and full-feature films. Check computer code for errors. Summarize legalese in software agreements, contracts, and other forms into simple laymen language. Calculate the terms of an agreement into total costs. Teach a skill or get instructions for a complex task. Find an error in their logic before implementing their decision in the real world. Much ado has been made of ChatGPT’s creativity. But that creativity is a reflection and result of the human doing the prompting. If you can think it, you can probably get ChatGPT to play along. Unfortunately, that’s true for bad guys too. For example, they can prompt ChatGPT to find vulnerabilities in computer code or a computer system; steal your identity by writing a document in your style, tone, and word choices; or edit an audio clip or a video clip to fool your biometric security measures or make it say something you didn’t actually say. Only their imagination limits the possibilities for harm and chaos. Unwrapping ChatGPT fears Perhaps no other technology is as intriguing and disturbing as generative artificial intelligence. Emotions were raised to a fever pitch when 100 million monthly active users snatched up the free, research preview version of ChatGPT within two months after its launch. You can thank science fiction writers and your own imagination for both the tantalizing and terrifying triggers that ChatGPT is now activating in your head, making you wonder: Is ChatGPT safe? There are definitely legitimate reasons for caution and concern. Lawsuits have been launched against generative AI programs for copyright and other intellectual property infringements. OpenAI and other AI companies and partners stand accused of illegally using copyrighted photos, text, and other intellectual property without permission or payment to train their AI models. These charges generally spring from copyrighted content getting caught up in the scraping of the Internet to create massive training datasets. In general, legal defense teams are arguing the inevitability and unsustainability of such charges in the age of AI and requesting that charges be dropped. The lawsuits regarding who owns the content generated by ChatGPT and its ilk lurk somewhere in the future. However, the U.S. Copyright Office has already ruled that AI-generated content, be it writing, images, or music, is not protected by copyright law. In the U.S., at least for now, the government will not protect anything generated by AI in terms of rights, licensing, or payment. Meanwhile, realistic concerns exist over other types of potential liabilities. ChatGPT and ChatGPT alternatives are known to sometimes deliver incorrect information to users and other machines. Who is liable when things go wrong, particularly in a life-threatening scenario? Even if a business’s bottom line is at stake and not someone's life, risks can run high and the outcome can be disastrous. Inevitably, someone will suffer and likely some person or organization will eventually be held accountable for it. Then, there are the magnifications of earlier concerns, such as data privacy, biases, unfair treatment of individuals and groups through AI actions, identity theft, deep fakes, security issues, and reality apathy, which is when the public can no longer tell what is true and what isn’t and thinks the effort to sort it all out is too difficult to pursue. In short, all of this probably has you wondering: Is ChatGPT safe? The potential to misuse it accelerates and intensifies the need for the rules and standards currently being studied, pursued, and developed by organizations and governments seeking to establish guardrails aimed at ensuring responsible AI. The big question is whether they’ll succeed in time, given ChatGPT’s incredibly fast adoption rate worldwide. Examples of groups working on guidelines, ethics, standards, and responsible AI frameworks include the following: ACM US Technology Committee’s Subcommittee on AI & Algorithms World Economic Forum UK’s Centre for Data Ethics Government agencies and efforts such as the US AI Bill of Rights and the European Council of the European Union’s Artificial Intelligence Act. IEEE and its 7000 series of standards Universities such as New York University’s Stern School of Business The private sector, wherein companies make their own responsible AI policies and foundations How does ChatGPT work? ChatGPT works differently than a search engine. A search engine, such as Google or Bing, or an AI assistant, such as Siri, Alexa, or Google Assistant, works by searching the Internet for matches to the keywords you enter in the search bar. Algorithms refine the results based on any number of factors, but your browser history, topic interests, purchase data, and location data usually figure into the equation. You’re then presented with a list of search results ranked in order of relevance as determined by the search engine’s algorithm. From there, the user is free to consider the sources of each option and click a selection to do a deeper dive for more details from that source. By comparison, ChatGPT generates its own unified answer to your prompt. It doesn't offer citations or note its sources. You ask; it answers. Easy-peasey, right? No. That task is incredibly hard for AI to do, which is why generative AI is so impressive. Generating an original result in response to a prompt is achieved by using either the GPT-3 (Generative Pre-trained Transformer 3) or GPT-4 model to analyze the prompt with context and predict the words that are likely to follow. Both GPT models are extremely powerful large language models capable of processing billions of words per second. In short, transformers enable ChatGPT to generate coherent, humanlike text as a response to a prompt. ChatGPT creates a response by considering context and assigning weight (values) to words that are likely to follow the words in the prompt to predict which words would be an appropriate response. Some ChatGPT basics here: User input is called a prompt rather than a command or a query, although it can take either form. You are, in effect, prompting AI to predict and complete a pattern that you initiated by entering the prompt. If you'd like a comprehensive ChatGPT guide, including more detail on how it works and how to use it, check out my book ChatGPT For Dummies. Peeking at the ChatGPT architecture As its name implies, ChatGPT is a chatbot running on a GPT model. GPT-3, GPT-3.5, and GPT-4 are large language models (LLMs) developed by OpenAPI. When GPT-3 was introduced, it was the largest LLM at 175 billion parameters. An upgraded version called GPT-3.5 turbo is a highly optimized and more stable version of GPT-3 that's ten times cheaper for developers to use. ChatGPT is now also available on GPT-4, which is a multimodal model, meaning it accepts both image and text inputs although its outputs are text only. It's now the largest LLM to date, although GPT-4’s exact number of parameters has yet to be disclosed. Parameters are numerical values that weigh and define connections between nodes and layers in the neural network architecture. The more parameters a model has, the more complex its internal representations and weighting. In general, more parameters lead to better performance on specific tasks. ChatGPT for beginners Here, you'll learn the basics of how to use ChatGPT and why it relies on your skills to optimize its performance. But the real treasure here are the tips and insights on how to write prompts so that ChatGPT can perform its true magic. You can learn even more about writing prompts in my book ChatGPT For Dummies. Writing effective ChatGPT prompts ChatGPT appears deceptively simplistic. The user interface is elegantly minimalistic and intuitive, as shown in the figure below. The first part of the page offers information to users regarding ChatGPT’s capabilities and limitations plus a few examples of prompts. The prompt bar, which resembles a search bar, runs across the bottom of the page. Just enter a question or a command to prompt ChatGPT to produce results immediately. If you enter a basic prompt, you’ll get a bare-bones, encyclopedic-like answer, as shown in the figure below. Do that enough times and you’ll convince yourself that this is just a toy and you can get better results from an Internet search engine. This is a typical novice’s mistake and a primary reason why beginners give up before they fully grasp what ChatGPT is and can do. Understand that your previous experience with keywords and search engines does not apply here. You must think of and use ChatGPT in a different way. Think hard about how you’re going to word your prompt. You have many options to consider. You can assign ChatGPT a role or a persona, or several personas and roles if you decide it should respond as a team, as illustrated in the figure below. You can assign yourself a new role or persona as well. Or tell it to address any type of audience — such as a high school graduating class, a surgical team, or attendees at a concert or a technology conference. You can set the stage or situation in great or minimum detail. You can ask a question, give it a command, or require specific behaviors. A prompt, as you can see now, is much more than a question or a command. Your success with ChatGPT hinges on your ability to master crafting a prompt in such a way as to trigger the precise response you seek. Ask yourself these questions as you are writing or evaluating your prompt. Who do you want ChatGPT to be? Where, when, and what is the situation or circumstances you want ChatGPT’s response framed within? Is the question you're entering in the prompt the real question you want it to answer, or were you trying to ask something else? Is the command you're prompting complete enough for ChatGPT to draw from sufficient context to give you a fuller, more complete, and richly nuanced response? And the ultimate question for you to consider: Is your prompt specific and detailed, or vague and meandering? Whichever is the case, that’s what ChatGPT will mirror in its response. ChatGPT’s responses are only as good as your prompt. That’s because the prompt starts a pattern that ChatGPT must then complete. Be intentional and concise about how you present that pattern starter — the prompt. Starting a chat To start a chat, just type a question or command in the prompt bar, shown at the bottom of the figure below. ChatGPT responds instantly. You can continue the chat by using the prompt bar again. Usually, you do this to gain further insights or to get ChatGPT to further refine its response. Following, are some things you can do in a prompt that may not be readily evident: Add data in the prompt along with your question or command regarding what to do with this data. Adding data directly in the prompt enables you to add more current info as well as make ChatGPT responses more customizable and on point. You can use the Browsing plug-in to connect ChatGPT to the live Internet, which will give it access to current information. However, you may want to add data to the prompt anyway to better focus its attention on the problem or task at hand. However, there are limits on prompting and response sizes, so make your prompt as concise as possible. Direct the style, tone, vocabulary level, and other factors to shape ChatGPT's response. Command ChatGPT to assume a specific persona, job role, or authority level in its response. If you’re using ChatGPT-4, you'll soon be able to use images in the prompt too. ChatGPT can extract information from the image to use in its analysis. When you’ve finished chatting on a particular topic or task, it’s wise to start a new chat (by clicking or tapping the New Chat button in the upper left). Starting a new dialogue prevents confusing ChatGPT, which would otherwise treat subsequent prompts as part of a single conversational thread. On the other hand, starting too many new chats on the same topic or related topics can lead the AI to use repetitious phrasing and outputs, whether or not they apply to the new chat’s prompt. To recap: Don't confuse ChatGPT by chatting in one long continuous thread with a lot of topic changes or by opening too many new chats on the same topic. Otherwise, ChatGPT will probably say something offensive or make up random and wrong answers. When writing prompts, think of the topic or task in narrow terms. For example, don't have a long chat on car racing, repairs, and maintenance. To keep ChatGPT more intently focused, narrow your prompt to a single topic, such as determining when the vehicle will be at top trade-in value so you can best offset a new car price. Your responses will be of much higher quality. ChatGPT may call you offensive names and make up stuff if the chat goes on too long. Shorter conversations tend to minimize these odd occurrences, or so most industry watchers think. For example, after ChatGPT responses to Bing users became unhinged and argumentative, Microsoft limited conversations with it to 5 prompts in a row, for a total of 50 conversations a day per user. But a few days later, it increased the limit to 6 prompts per conversation and a total of 60 conversations per day per user. The limits will probably increase when AI researchers can figure out how to tame the machine to an acceptable — or at least a less offensive — level. Quick Read Summary ChatGPT, a product of OpenAI, represents a groundbreaking advancement in the world of artificial intelligence. Released as a free preview in November 2022, it quickly gained over a million users by January 2023. ChatGPT is a powerful example of generative AI, capable of generating new content instead of just analyzing existing data. This versatile tool is accessible online and is being integrated into various applications like Microsoft Office and Bing search, expanding its utility daily. Users initially engage with ChatGPT for basic tasks like crafting poems, essays, or marketing content. Students use it for homework. But all who use it should be cautious: ChatGPT struggles with riddles and word problems in math. It also has a tendency to make things up. People tend to use ChatGPT to guide or explain something, but its potential goes beyond simple requests. Depending on the quality of your prompt, it can perform a wide range of tasks. Users have leveraged ChatGPT for tasks like conducting interviews with historical figures, recommending color combinations, generating articles, predicting business scenarios, and even diagnosing medical conditions based on patients’ real-world test results. Users can harness ChatGPT’s capabilities for both good and ill, from identifying vulnerabilities in computer systems to creating deepfakes. Therefore, as ChatGPT's popularity soars, concerns about its safety and misuse grow. Legal battles surrounding copyright infringement and accountability for incorrect information continue to emerge. Ethical guidelines and standards are under development by organizations and governments to ensure responsible AI usage. ChatGPT operates differently from search engines and AI assistants. It generates original responses to prompts, making it a valuable tool for diverse tasks. Users must craft prompts effectively to receive meaningful responses, considering factors like context, role assignment, and audience specification. In summary, ChatGPT is a game-changer in AI technology, offering endless possibilities when used responsibly. Its potential for good or harm depends on the user, emphasizing the need for ethical guidelines and responsible AI practices. Hungry for more? Go back and read the article or check out the book.

Article / Updated 06-22-2023

ChatGPT is a global phenomenon that sparks fear and excitement worldwide. Because it sounds human but is made of advanced AI software connected to an internet-sized database, people assume that it's better — or worse — than humans. Reactions run the gamut. Maybe this AI is the first machine overlord of sci-fi lore. Maybe it will save mankind. Perhaps it will take all our jobs and eliminate our purpose for living. Maybe it will make everything cheap and banish inflation. But ChatGPT is only a mindless tool. It's as good or as bad as its users’ prompts — notwithstanding a scary or offensive machine rant or hallucination or two. What ChatGPT is, and isn't To give ChatGPT’s seemingly sudden appearance in the world some much needed perspective, think back to past cycles when a new technology was assumed to be the end of a previous one. The advent of radio was going to eradicate newspapers. TV was thought to be a radio slayer. And the internet was supposed to be the TV killer. But that’s not what happened. Although these forms of communication have changed over the years, they all co-exist. ChatGPT is yet another communication medium. It generates narratives in a conversational format. But just like the communication media that came earlier — newspaper, radio, TV and the internet — ChatGPT isn’t going to replace much that came before. It certainly isn’t going to replace search engines. Each serves a distinct purpose the other can't recreate — although at some point, the two technologies might converge. ChatGPT isn’t going to replace people in their jobs, either. Rather, it will eliminate some jobs and create others. This is a cycle you’ve seen more than once. For example, both the invention of the assembly line and modern-day automation replaced some workers but also created jobs. ChatGPT will eventually spark a similar job cycle. ChatGPT is a powerful tool that can assist humans in doing many different kinds of work. And when its use is coupled with something capable of a physical manifestation, such as 3D printers or automated physical infrastructure , the effect in the real world can be astonishing. Workers who become adept at using it to increase their own productivity and creativity will be best positioned to advance in their existing careers or move to new ones. The good & bad in ChatGPT If what I’ve written so far seems reassuring, you're mistaken. ChatGPT is an existential technology, a hard pivot in human experience, a doorway to a far different kind of future. It's the harbinger of the AI Age and a pronounced mark of the arrival of the Fourth Industrial Revolution. If that terrifies you, you're still mistaken. Mankind, not software, is equal parts scary and saintly. AI in its current forms mostly mirrors that duality. ChatGPT certainly does. The most threatening aspect of ChatGPT is its capability to rapidly create and spread harmful disinformation in every aspect of human life, from politics to health care and everything in-between. It can lie, hallucinate, misinform, and make stuff up. How human of it. The most endearing aspect is its capability to help people create things that do not yet exist. ChatGPT can help authors and scriptwriters create stories, filmmakers make incredible special effects and new films on the tiniest of budgets, performance artists to consider new routines, musicians to create new scores, architects to design new kinds of buildings, and photographers to capture realistic images of decidedly unreal subjects. No aspect of human creativity is beyond the scope of ChatGPT’s enhancement and collaborative capabilities. Will ChatGPT replace jobs? Can ChatGPT be used to outright replace the work of creative people? Yes, it can. Note that publishers’ inboxes and self-publishing platforms are already filled to the brim with ChatGPT-generated books. But also note that most of them are truly awful reads. The people who jumped to create works using only ChatGPT were driven by greed, not by any desire to create true art. It takes a true artist to shape a prompt for ChatGPT that will render a magnificently original creative work. The lack of quality coupled with recent events in the U.S. that deny copyright protection of such works — while enforcing copyright protections for any plagiarism ChatGPT and its ilk use in the creation of such works — will soon rob the greedy of their dreams of easy wealth. And like the content farms of yesteryear that tried to game search engines by producing godawful reads full of keywords, those using ChatGPT to create fast content for cash will soon fall into obscurity. But do remember that the fatal fall for content farms came from human hands, in spite of the intense efforts at search engine optimization (SEO). Specifically, owners of search engines didn’t want to render lists of trash results to users, so they drove the work of content farms to the far outer corners of the search universe. Mainstream media, seemingly on its last leg and hemorrhaging badly, began to rebound almost immediately. We’ll likely see that pattern again with ChatGPT content. Human artists and experts will continue to thrive, with ChatGPT taking a permanent place as an important tool in their toolbox. The same will likely hold true for most knowledge workers. Using ChatGPT in place of or without the direct supervision of workers who possess the necessary knowledge will prove to be a horrendous and expensive mistake. Such careless reliance on ChatGPT alone will also open companies to a slew of liabilities while producing little in the way of efficiencies or revenue. Sampling the disruptions ahead That said, it’s time to look at the ways ChatGPT and its generative AI ilk are likely to further disrupt our world: Public trust will be further eroded. Generative AI can produce fake voice tracts that are identical to the original voice, provide tons of disinformation on nearly every subject, and manipulate human behavior through carefully formed narratives. It will be much harder for citizens in any country to discern reality from deception and truth from untruth. Even the results of fact-checking will be suspicious given that generative AI can mimic trustworthy sources. Security teams will be pushed to the limit to keep pace. Fortunately, AI models can be trained to help spot and stop these threats. Unfortunately, it’ll take much longer to rebuild public trust. The rise of superapps will begin. Until this point, apps were embedded with AI to make them faster and better at performing tasks requiring immense amounts of information. But ChatGPT can be considered a superapp in that it can do tasks that formerly required several separate apps, and it can do so by automatically selecting plug-ins to augment its own performance as needed. ChatGPT integrations will eventually be replaced with connected AI. ChatGPT is being integrated with search engines, apps, and other technologies that may or may not have other AI embedded or integrated. Soon, various forms of AI will be connected directly rather than indirectly through app integrations. Some think this is the path to the infamous singularity, while others see it as little different than integrating multiple apps. Smart automation will become more intelligent and versatile. Smart homes, smart phones, smart TVs, smart things of all kinds will become more helpful as virtual assistants like Siri and Alexa become supercharged with generative AI capable of understanding and even anticipating user needs. Knowledge work will be augmented. Workers will spend less time handling mundane functions in knowledge work and more time focused on creating more knowledge. For example, data analysts can use ChatGPT to do the needed analysis as well as write final reports. This will free data analysts to look deeper into the data for more refined insights and to unearth knowledge that may have been missed earlier. Likewise, lawyers can use ChatGPT to write legal briefs, contracts, and other legal documents. The signers can use ChatGPT to condense all the legal forms into an easy-to-understand summary. Opposing attorneys can do likewise, and thus free their time to develop a strategy to counter any challenges or sticking points that ChatGPT uncovers in evidence or legal agreements. Marketers and advertisers will produce more content in a continuous delivery cycle. Because companies seek to stay ahead of emerging trends and be the first-to-market on new ideas, marketers and advertisers will use ChatGPT and its siblings to produce content and ads extremely fast to sell in the moment. As the product changes with the moment, so too will the ads. Education will be disrupted. Long teetering on obsolescence, education as we know it will be disrupted by ChatGPT and generative AI of all forms. The nine-month education model designed to let farmer’s children out of school for planting and harvesting is no longer needed or useful. Neither is the mass conveyor-belt-like grade system or formalized testing. ChatGPT will enable educators to move to more customized learning models wherein students progress according to their competency with the subject rather than their age, school grade, or time spent on the subject matter. How can it do that? By enabling educators to analyze each student’s data and create a customized learning plan for each student. Homework, tests, and other measures of subject competence can also be assessed and reported by generative AI. Media will use ChatGPT to break news faster. ChatGPT can't do investigative reporting. That task requires human reporters to find hidden information and conduct interviews. However, ChatGPT can help fill in the background info for color and context and get the final piece to audiences faster. Journalists will be valued more for their ability to dig up or create additional insights rather than for simply reporting existing and often easily found facts. Customer service will become far more personalized and instantaneous. ChatGPT can discuss issues with customers, offer solutions, give instructions in product support, facilitate returns that fit the customer’s circumstances, and resolve issues faster and with less friction than typical customer service processes. For example, rather than a shopper searching a company's website for a given product, ChatGPT can become a personal shopper and deliver product selections that fit the taste, size, and style preferences of each individual shopper. Health care will improve. ChatGPT can provide doctors with information from the latest research and recommendations based on the probability of success for a specific patient. ChatGPT can act as a physician’s assistant in other ways too. In addition, ChatGPT can save lives by providing information for laypeople to help them prevent health issues, deliver emergency treatment, and accurately assess whether a doctor’s attention is warranted. ChatGPT and generative AI will change our daily lives and the future human experience in many more ways than this already long list, though not all of them can be foreseen.

Cheat Sheet / Updated 06-01-2023

ChatGPT took the world by storm shortly after its debut. If you’re feeling at a loss as to what to do, too excited to decide where to start, or uncertain about how to react to artificial intelligence (AI) entering your space, this cheat sheet will help you make some quick and meaningful headway that you can build on as you go. Read a brief explanation of what ChatGPT is before checking it out either directly online or by connecting with it in one of many software applications. Then learn the keys to mastering ChatGPT: perfecting the prompt and using the right ChatGPT plug-ins. Using ChatGPT will significantly increase your productivity, but you must always fact-check its responses before relying on them. Don’t worry if you make a mistake along the way or find yourself stumped over what to do next. You're not alone. ChatGPT is completely new and mysterious for most people. Keep this cheat sheet handy and dive right in!

Cheat Sheet / Updated 12-09-2021

Decision intelligence is a new way of incorporating formulas from established sciences into a framework in a specific order to tether all subsequent actions to an intended result. By making the decision first and then selecting one's processes, tools, and data, the user is ensuring that the entire effort renders a predetermined business value. In short, decision intelligence flips the traditional data mining process so that the action dictates the data rather than the data recommends the action. This technique moves companies away from the previous data driven model to a decision driven model. The reasoning behind this approach is to stop high fail rates in AI and data driven projects by predetermining the outcome and working toward it rather than trying to milk value from a completed and cost-spent process.