Using generative AI to write your generative AI prompts for you.
gettyIn today’s column, I am continuing my ongoing coverage of prompt engineering strategies and tactics that aid in getting the most out of using generative AI apps such as ChatGPT, GPT-4, Bard, Gemini, Claude, etc. The focus here is on ingeniously using generative AI to generate prompts for you. This is an important prompting strategy that you should know about. It will definitely be handy from time to time.
For my comprehensive review of nearly two dozen other keystone prompting strategies, see the discussion at the link here.
The emphasis in this discussion will be on a particular prompting best practice that not many people seem to realize exists, namely that you can use generative AI to generate prompts for you.
Say what?
Yes, besides handcrafting prompts, you can use AI to devise your prompts.
Those derived prompts can then in turn be fed into generative AI. That seems at first thought to be unusual or a head-scratcher, but it makes a lot of sense. You have in your hands a tool that can generate useful responses, so why not go ahead and use the same tool to create your prompts?
That being said, I certainly don’t want you to go overboard on this.
You will need to mindfully consider when it is sensible to use generative AI to craft your prompts. Hint: Not all the time. I will be explaining when to consider using generative AI to do so. A set of rules of thumb that I use in my classes on prompt engineering will be presented. There will also be a series of examples, using ChatGPT, illustrating how to leverage generative AI to compose your prompts.
Let’s get started with today’s informative and engaging adventure.
The Background About Prompting And Seeking To Devise Good Prompts
A lot of people struggle to come up with good prompts when using generative AI.
The usual assumption is that writing good prompts is like falling off a log. When you start by writing whatever comes to your mind, the chances are that the prompt will be faulty for a variety of reasons. Sometimes a prompt is convoluted and hard for the generative AI to suitably parse. Other times a prompt is exceedingly vague, and the response will be equally vague in return. On and on the potential issues go.
Another consideration is that prompting has a wide variety of principles or practices that are worthwhile to know. A field known as prompt engineering has arisen to encompass and promulgate good prompting approaches. You can study prompt engineering and seek to improve your prompting strategies and tactics.
There is a decidedly use it or lose it factor that comes into play.
People who regularly use generative AI are bound to remember the numerous prompting best practices. They also will hopefully improve their prompting style as they learn from their good prompts and their not-so-adequate prompts. A daily or weekly use of generative AI is probably enough ongoing effort to keep up to par with your prompting skills.
Not everyone uses generative AI on a frequent basis. Those users are less likely to know about prompt engineering. Even if they do know about prompting strategies, the odds are they will forget the ins and outs due to a lack of routine use. A decay rate of remembering how to best prompt is always looming over your head.
The good news is that generative AI can aid you in your prompting efforts.
You can do lots of things with generative AI about prompting. You can ask general questions and get an immediate tutorial kind of response. You can have generative AI review a draft prompt that you have composed. You can ask generative AI to compose a prompt on your behalf. And so on.
I will be covering each of those approaches.
There is something else you might find of interest in this topic. Some of the generative AI apps are gradually being encompassed within a set of components referred to as a trust layer, see my coverage at the link here. The idea is that we might have a preprocessing component that takes your prompt and spruces it up before feeding it into generative AI. In that case, you are using a form of automation to refine your prompts.
Currently, few generative AI apps have that type of preprocessing. You are pretty much on your own to compose your prompts. Furthermore, you need to keep your fingers crossed that the prompts will achieve what you hope they will produce.
No need to continuously keep your fingers crossed since you can use generative AI to do several handy efforts, including reviewing your prompts, adjusting your prompts, feeding in your prompts, and composing your prompts on your behalf.
That is a nifty combination meal deal.
The Importance Of Prompt Engineering
I’ve been carrying on so far in this discussion as though we’ve already covered what prompt engineering provides. My passion got the better of me. Some of you might not be familiar with the topic. Please allow me a moment to bring everyone up to speed, thanks.
First, please be aware that composing well-devised prompts is essential to getting robust results from generative AI and large language models (LLMs). It is highly recommended that anyone avidly using generative AI should learn about and regularly practice the fine art and science of devising sound prompts. I purposefully note that prompting is both art and science. Some people are wanton in their prompting, which is not going to get you productive responses. You want to be systematic leverage the science of prompting, and include a suitable dash of artistry, combining to get you the most desirable results.
My golden rule about generative AI is this:
The use of generative AI can altogether succeed or fail based on the prompt that you enter.
If you provide a prompt that is poorly composed, the odds are that the generative AI will wander all over the map and you won’t get anything demonstrative related to your inquiry. Similarly, if you put distracting words into your prompt, the odds are that the generative AI will pursue an unintended line of consideration. For example, if you include words that suggest levity, there is a solid chance that the generative AI will seemingly go into a humorous mode and no longer emit serious answers to your questions.
Be direct, be obvious, and avoid distractive wording.
Being copiously specific should also be cautiously employed. You see, being painstakingly specific can be off-putting due to giving too much information. Amidst all the details, there is a chance that the generative AI will either get lost in the weeds or will strike upon a particular word or phrase that causes a wild leap into some tangential realm. I am not saying that you should never use detailed prompts. That’s silly. I am saying that you should use detailed prompts in sensible ways, such as telling the generative AI that you are going to include copious details and forewarn the AI accordingly.
You need to compose your prompts in relatively straightforward language and be abundantly clear about what you are asking or what you are telling the generative AI to do.
A wide variety of cheat sheets and training courses for suitable ways to compose and utilize prompts has been rapidly entering the marketplace to try and help people leverage generative AI soundly. In addition, add-ons to generative AI have been devised to aid you when trying to come up with prudent prompts, see my coverage at the link here.
AI Ethics and AI Law also stridently enter into the prompt engineering domain. For example, whatever prompt you opt to compose can directly or inadvertently elicit or foster the potential of generative AI to produce essays and interactions that imbue untoward biases, errors, falsehoods, glitches, and even so-called AI hallucinations (I do not favor the catchphrase of AI hallucinations, though it has admittedly tremendous stickiness in the media; here’s my take on AI hallucinations at the link here).
There is also a marked chance that we will ultimately see lawmakers come to the fore on these matters, possibly devising and putting in place new laws or regulations to try and scope and curtail misuses of generative AI. Regarding prompt engineering, there are likely going to be heated debates over putting boundaries around the kinds of prompts you can use. This might include requiring AI makers to filter and prevent certain presumed inappropriate or unsuitable prompts, a cringe-worthy issue for some that borders on free speech considerations. For my ongoing coverage of these types of AI Ethics and AI Law issues, see the link here and the link here, just to name a few.
All in all, be mindful of how you compose your prompts.
By being careful and thoughtful you will hopefully minimize the possibility of wasting your time and effort. There is also the matter of cost. If you are paying to use a generative AI app, the usage is sometimes based on how much computational activity is required to fulfill your prompt request or instruction. Thus, entering prompts that are off-target could cause the generative AI to take excessive computational resources to respond. You end up paying for stuff that either took longer than required or that doesn’t satisfy your request and you are stuck for the bill anyway.
I like to say at my speaking engagements that prompts and dealing with generative AI is like a box of chocolates. You never know exactly what you are going to get when you enter prompts. The generative AI is devised with a probabilistic and statistical underpinning which pretty much guarantees that the output produced will vary each time. In the parlance of the AI field, we say that generative AI is considered non-deterministic.
My point is that, unlike other apps or systems that you might use, you cannot fully predict what will come out of generative AI when inputting a particular prompt. You must remain flexible. You must always be on your toes. Do not fall into the mental laziness of assuming that the generative AI output will always be correct or apt to your query. It won’t be.
Write that down on a handy snip of paper and tape it onto your laptop or desktop screen.
Handy Tips About Using Generative AI To Generate Your Prompts
I have formulated a set of rules of thumb about how to best use generative AI to generate personalized prompts for you.
Here are my handy tips that I cover during my classes that I teach on prompt engineering:
(1) Find out about good prompting. Use generative AI to explain to you how to write good prompts.
(2) Get feedback on a hand-crafted draft prompt. Show generative AI a prompt you’ve crafted and get feedback about how it can be improved.
(3) Generate a draft prompt. Tell generative AI to go ahead and create a draft prompt for you.
(4) Obtain feedback about a performed prompt. After a prompt has been performed and a result obtained, ask generative AI to evaluate the prompt and ascertain if a better version might produce better results.
(5) Dovetail a prompt draft request into prompt performance. Once you’ve gotten a generative AI drafted prompt, you can go ahead and have generative AI perform the prompt.
(6) Analyze your series of prompts and your prompting strategies. You can ask generative AI to assess a series of prompts that you’ve crafted and used, aiming to see what prompting patterns of improvement might be discovered by the AI in your prompting style and strategy.
I will briefly explain each tip.
A handy source of prompting strategies can be found by asking generative AI how to best craft prompts. The responses will likely be relatively generic at the first shot. You can proceed to ask specific questions that might be of particular interest to you. All in all, you can get some great tips and suggestions overall.
Once you’ve drafted a prompt by hand, the next step of using generative AI for prompting would be to ask the AI to assess or review your postulated prompt. The review will usually compare your composed prompt to the typical rubric, such as whether the prompt is clear-cut, sufficiently detailed, and so on. You can adjust the draft accordingly.
Turns out you don’t have to create your prompts by hand. It is relatively easy to ask generative AI to create a prompt for you. The way to do this is by describing what you are trying to accomplish. If you can be specific, this will work best in terms of the generative AI-drafted prompt. Once you see what the draft consists of you can easily either fine-tune it to your tailored needs or ask the AI to do so.
At some point, you’ll be submitting a prompt to be acted upon. After getting a response, you can ask generative AI to review the prompt. The chances are that the review will reveal ways in which the prompt could have been better worded. This gives you insights into how to word your prompts. In addition, you can use the advice about the prompt and redo the prompt, submitting it for another try.
The quickest way to proceed with using generative AI to devise a prompt consists of having the drafted prompt performed by the AI. You can in one fell-swoop ask to have a draft prompt created and then immediately have it performed. Of course, you might want to review the drafted prompt before having it performed, in which case you can do a two-step, namely ask to see it first and then proceed to have it performed.
Another great way to use generative AI to aid in your prompting strategy is to have the AI review an entire series of prompts that you’ve used. The way to do this is by asking generative AI to take a look at a series of prompts that you’ve had in a given conversation. You can request an overall assessment of the prompts, along with getting a prompt-by-prompt review.
I will be showing you examples of each of the rules of thumb in the next section.
Examples Of Using Generative AI To Generate Your Prompts
I will next proceed to showcase the handy use of generative AI to generate your prompts, which I’ll be doing in ChatGPT. ChatGPT is a sensible choice in this case due to its immense popularity as a generative AI app. An estimated one hundred million weekly active users are said to be utilizing ChatGPT. That’s a staggering number.
A few quick comments before we launch into using ChatGPT.
If you are going to try to do the same prompts that I show here, realize that the probabilistic and statistical properties will likely produce slightly different results than what I show here. That’s the nature of generative AI and how it is devised.
You also should expect that different generative AI apps will respond in different ways. Not all generative AI apps are the same. The key is that sometimes a particular prompt will work in one generative AI app and not another. You will need to do a series of trial-and-error attempts to ferret this out.
There is also the timing factor. A prompt that worked today might not work the same way tomorrow. Most of the generative AI apps are continually being updated. The updates might alter internal facets that could change how the AI reacts to your prompting.
We are ready to get underway with ChatGPT.
My opening move in this chess gambit will be to ask what constitutes a good prompt.
My entered prompt: “What constitutes a good prompt in generative AI?”
ChatGPT generated response: “A good prompt in generative AI is crucial for guiding the model to produce relevant and coherent outputs. Here are some characteristics of a good prompt. A good prompt in generative AI should be clear, specific, and relevant to the desired output. It should provide context, examples (if applicable), and any constraints clearly. Engagement, adaptability, and ethical considerations are also important factors to consider. In essence, a good prompt serves as a roadmap for guiding the AI model to produce relevant and high-quality outputs.”
That rendition of how to properly compose prompts seems quite reasonable.
If you wanted to get more details, you could easily ask for clarification about each stated facet. The gist here is that clearly there has been data training associated with prompt engineering and we can leverage that to our advantage. We have essentially gotten a green light to proceed ahead in delving further.
I will next provide a draft prompt that I handcrafted and will ask ChatGPT to critique or review the proposed prompt. I purposely made the prompt very vague. Let’s see if ChatGPT figures out that I should be more specific.
Here we go.
My entered prompt: “I want to find out about the life of Lincoln. My prompt will be this: ‘Tell me about Lincoln.’ Critique that prompt and let me know what you think of how the prompt is composed.”
ChatGPT generated prompt:
“The prompt ‘Tell me about Lincoln’ is quite vague and lacks specificity. While it does provide a general direction by asking for information about Abraham Lincoln, it doesn’t provide any context or guidance on what aspects of Lincoln’s life or accomplishments the AI should focus on.
“To improve the prompt, consider adding more specific details or questions such as:”
"- Please provide a summary of Abraham Lincoln’s early life and political career."
"- Describe Abraham Lincoln’s role during the Civil War and his impact on American history."
"- Discuss Abraham Lincoln’s contributions to abolishing slavery in the United States."
"- Explain the significance of Abraham Lincoln’s presidency and his leadership style."
“By providing more specific prompts, you can guide the AI to generate more relevant and informative responses about Abraham Lincoln’s life and legacy.”
End of ChatGPT response
Overall, I would say that ChatGPT provided a useful critique.
The draft prompt was very general and could have generated a ton of material about Lincoln. You could also claim that the draft should refer to the fuller name of “Abraham Lincoln” since there is a chance that the last name “Lincoln” referenced someone else (admittedly, less likely odds, but you never know).
An especially valid reason to be careful in the wording of a prompt is that you might incur a needless cost by having a prompt that is vague or overly broad. If I was paying for the use of generative AI, and if the vagueness produced a lengthy off-target response, it might cost me extra dough.
I realize that a smarmy retort is that there is a cost associated with asking generative AI to assess a prompt. Sure, I get that. But the chances are that if you do a one-time short cost to get a really good prompt figured out, this is going to be less costly than taking a stab in the dark and getting an off-target verbose response. Plus, of course, you might need to redo that vague prompt anyway, aiming to get a more focused reply.
One small and worthy counterpoint is that you might intentionally at times make use of a vague prompt.
Imagine this. Suppose I know nothing at all about snails. I might begin my series of interactions with generative AI by simply asking generally about snails. Once I get an initial response, I might realize that there are lots of directions I can go when it comes to learning about snails. The initial vague prompt was suitable for the circumstance at hand to get me up-to-speed about snails.
Moving on, in my next step of this process, assume that I now realized that my draft prompt had lots of room for improvement. I could reword the prompt myself. Sometimes I might do so, other times I might have generative AI do so.
Let’s try to ask ChatGPT to improve my draft prompt.
My entered prompt: “Go ahead and refine my draft prompt and reword it so that I can find out about Lincoln’s life when he was a practicing lawyer. Show me the prompt that you have devised.”
ChatGPT generated prompt: “Here is an improved prompt: “Can you provide insight into Abraham Lincoln’s life during his career as a practicing lawyer?"
One thing to observe is that I gave an indication to ChatGPT about the specific area of interest that I have in Abraham Lincoln. Had I not provided that additional specificity, there wouldn’t have been much chance that ChatGPT could improve my prompt.
This brings up an important related point.
Generative AI is not a mind reader.
Well, at least not yet, though work is underway to devise brain-machine interfaces or BMI, see my discussion at the link here.
Right now, you must share with generative AI whatever you have in your mind as to what question or problem you want to explore via generative AI. If you were to say something entirely vacuous like “Tell me”, and then not say anything else, the response is going to be equally nebulous. Being upfront about what you are interested in is a recommended best practice.
Someday, maybe, you can just think your thoughts, and generative AI will be spurred from there. We aren’t there yet.
Back to your journey, I like the proposed prompt that ChatGPT has derived. There isn’t any need for me to hand-type the prompt, nor do I need to copy and paste it, since I can merely tell ChatGPT to go ahead and use that prompt.
Things should work out.
My entered prompt: “Proceed to use that devised prompt and respond to the prompt.”
ChatGPT generated response: “Abraham Lincoln began his career as a practicing lawyer in the early 1830s in Springfield, Illinois. Despite lacking formal education in law, Lincoln possessed a keen intellect and a strong sense of justice, which propelled him into the legal profession. His reputation for honesty and integrity quickly earned him respect among his peers and clients. Throughout his legal career, Lincoln continued to advocate for social and political causes, including the abolition of slavery. His experiences as a lawyer profoundly influenced his approach to governance and shaped his presidency during one of the most tumultuous periods in American history.”
The response is what I was hoping to get.
Do you think that the derived prompt was perfect?
I dare say there isn’t much in life that is perfect, other than perhaps a nice sunny day and the sounds of joyful chirping birds.
We can ask ChatGPT to take a second look at the prompt and identify what other improvements might be made to the prompt.
My entered prompt: “Was there anything about the devised prompt that could still be improved? Tell me what improvements might be made to the prompt and explain why the improvements are worthwhile.”
ChatGPT generated response:
“While the devised prompt "Can you provide insight into Abraham Lincoln’s life during his career as a practicing lawyer?" is more specific than the original prompt, it could still benefit from further refinement to guide the AI more effectively. Here are some improvements.”
“Specify the timeframe: Adding a timeframe to the prompt could help narrow down the focus to a particular period of Lincoln’s legal career. For example, "Can you provide insight into Abraham Lincoln’s life during his early years as a practicing lawyer in Springfield, Illinois?" This helps the AI understand which phase of Lincoln’s legal career to focus on, as his experiences and impact may have varied over time.”
“Clarify the aspect of Lincoln’s legal career: The prompt could be clearer about the aspect of Lincoln’s legal career the user is interested in. For instance, if the user wants to know about Lincoln’s notable cases, it could be phrased as, "Can you provide insight into some of the notable cases Abraham Lincoln handled during his career as a practicing lawyer?" This guides the AI to emphasize Lincoln’s legal work rather than broader aspects of his life during that time.”
“Include specific areas of interest: If the user has particular areas of interest within Lincoln’s legal career, those could be mentioned in the prompt. For example, "Can you provide insight into Abraham Lincoln’s approach to defending clients in criminal cases during his career as a practicing lawyer?" This prompts the AI to focus specifically on Lincoln’s legal strategies in criminal defense cases.”
“By incorporating these improvements, the prompt becomes more targeted and precise, helping the AI generate responses that align more closely with the user’s interests and expectations regarding Abraham Lincoln’s life as a practicing lawyer.”
End of ChatGPT response
Okay, we got quite a lesson in improving prompts by that answer.
The points made are certainly sensible. Once again, the generative AI wouldn’t have any idea of which direction I wanted to go. It is up to me to clue in the generative AI on the areas of interest to me.
You might be thinking that if I have to give clues to generative AI to generate a suitable prompt, why don’t I just write the prompt myself? It almost seems on the surface like double duty is taking place. I tell ChatGPT what I want, and ChatGPT generates the prompt. Maybe I should simply cut out the middleman, as it were, and write the prompts directly.
The correct answer is that it is complicated.
Here’s the deal.
In a sense, writing a good prompt is almost like knowing a programming language. You have to be familiar with how generative AI tends to parse and interpret sentences. Of course, the computational fluency is so high that you can pretty much rely upon generative AI to deal with whatever sentences you concoct. Nonetheless, if you want on-target prompts that will tend to be less costly and more fulfilling in terms of a response, composing them in a proper prompt engineering mindset does make a notable difference.
The nice thing about using generative AI is that it is relatively easy to describe what you want and then let the AI identify how to compose your indications into a suitable prompt. You aren’t really doing double duty
Allow me to explain why. First, I am loath to make comparisons to humans because it might be seen as anthropomorphizing AI but imagine that I go to a restaurant, and it is the first time I’ve ever visited the establishment. I know how to eat. I know what foods I like. I do not know much about their cuisine. One approach would be to take a wild shot at what I will order. Another approach involves describing what I like, and I let the server place my order for me.
You are having generative AI place your order for you.
When I say this at my speaking engagements, invariably, someone raises their hand and says that if it is handy to have generative AI write your prompts, why not always go that route? I certainly grasp that sentiment. If you find a good thing, keep using it. No sense in returning to the old ways of composing your own prompts.
Turns out that there are good reasons to not always rely upon generative AI to craft your prompts for you.
Let’s ask ChatGPT about this.
My entered prompt: “Can I have you always write my prompts for me?”
ChatGPT generated response: “While I’m here to assist you with writing prompts and providing guidance, it’s essential for you to develop your own ability to craft effective prompts. Writing prompts allows you to express your specific interests, questions, or goals, which helps tailor the AI’s responses to your needs more accurately. However, if you need assistance or guidance in formulating prompts, feel free to ask! I’m here to help refine your prompts and ensure they are clear, specific, and effective in guiding the AI to generate the desired content.”
I would generally agree with that response.
By and large, if you are an ongoing user of generative AI, you would be wise to learn about prompting and develop your prompt engineering skills. The caveat there is that if you rarely use generative AI or are a one-time user, I could absolutely see merit in tossing in the towel and letting generative AI do the heavy lifting for you. My analogy to the restaurant somewhat applies, such that if I am never or rarely going back to that restaurant, relying upon the server in that instance is probably okay.
As a final question for ChatGPT, we can find out what kinds of prompts are lousy and should be avoided when hand-crafting prompts. I think you already sense or know that prompts of a non-specific nature are going to be considered poorly composed. Another angle would be prompts that do not make grammatical sense. A nonsensical prompt won’t get the wheels on the bus rolling along. And so on.
Here’s what I asked of ChatGPT.
My entered prompt: “What are some examples of badly written prompts?”
ChatGPT generated response:
“Certainly, badly written prompts often lack clarity, specificity, or coherence, making it challenging for the AI to generate relevant and meaningful responses. Here are some examples.”
“Vague Prompt: “Tell me stuff." This prompt is too vague and doesn’t provide any direction or context for the AI to generate a coherent response. It’s unclear what "stuff" the user is interested in, making it difficult for the AI to understand the user’s intent.”
“Ambiguous Prompt: "What’s the deal with it?" This prompt is ambiguous and lacks specificity. It’s unclear what "it" refers to, leaving the AI to guess the topic or context of the user’s query.”
“Unclear Prompt: "Do the thing." This prompt is ambiguous and lacks clarity. It doesn’t specify what "the thing" is, making it difficult for the AI to understand what action or information the user is requesting.”
“Incomplete Prompt: "Lincoln?" This prompt is incomplete and lacks context. It only consists of a single word, "Lincoln," without providing any additional information or guidance for the AI to generate a response.”
“Contradictory Prompt: "Tell me everything in one sentence." This prompt is contradictory as it asks for "everything" but limits the response to "one sentence." It sets unrealistic expectations and makes it impossible for the AI to fulfill the request adequately.”
“In summary, badly written prompts often suffer from vagueness, ambiguity, lack of clarity, incompleteness, or contradictions, making it challenging for the AI to generate relevant and coherent responses.”
End of ChatGPT response
Those are words to live by.
You might enjoy a bit of a side note at this juncture.
I had an attendee at one of my prompt engineering courses indicate that everything they need to know about prompting they learned in fifth grade. It got a good laugh. We are customarily taught in elementary school to be good communicators. This consists of at least avoiding undue vagueness, ambiguity, and the other stated faltering possibilities.
In truth, I would suggest that the fifth-grade remark is valid only with respect to the overall wording of a prompt. I note in my course that there are many more prompting strategies and tactics that even to a fifth grader would not be obvious and require instructive assistance to garner.
For an indication of the variety and power of prevailing prompting strategies and tactics, see the link here.
Conclusion
Benjamin Franklin famously said this: “The best investment is in the tools of one’s own trade.”
If you are going to be using generative AI on an ongoing basis, you ought to know the tools of the trade. I urge you to come up to speed about the keystones of prompt engineering. They will readily pay off and you’ll be glad you took the time to learn what works.
One such tool of the trade consists of using the tool itself to help you get the tool to boost its results. That seems like the popular movie Inception in which there is a dream within a dream. In this case, it is straightforward to use generative AI to generate prompts, such that you can then feed those prompts into generative AI to get your hoped-for results.
I have a mind-bender for you to consider before I close out today’s discussion.
Suppose we use one generative AI app to generate our prompts and feed those prompts into a completely different generative AI.
Does that seem to be a good idea?
You’ll be perhaps happy to know that I have tried doing so. By and large, I would suggest that you are just as likely to get suitable results by using the same generative AI rather than having to turn to another generative AI. There are some situations where using a separate generative AI is quite useful, especially when trying to verify the output of one generative AI by feeding it into another to do a double-check.
For the matter of generative AI prompt generation, you are okay to go the easier route of using the same generative AI to produce the prompts and feed those prompts into that same generative AI.
Thanks for playing along on that bit of a thought experiment and some interesting whimsy.
As a final comment, I’d like to quote Abraham Lincoln, especially since I so extensively referred to him in today’s discussion. I tee up the quote by first emphasizing that if you are going to avidly use generative AI, you should do so with gusto and learn as much as you can about how to leverage generative AI. This applies to prompt engineering and being an honorary and proud prompt engineer.
Now, we are ready for Lincoln to speak.
Per Abraham Lincoln: “Whatever уоu are, be а good one.”
{Categories} _Category: Inspiration,*ALL*{/Categories}
{URL}https://www.forbes.com/sites/lanceeliot/2024/03/14/latest-prompt-engineering-trend-uses-generative-ai-to-generate-your-prompts-for-you/{/URL}
{Author}Lance Eliot, Contributor{/Author}
{Image}https://imageio.forbes.com/specials-images/imageserve/65efc210478f43108f00c437/0x0.jpg?format=jpg&crop=5792,3865,×272,y0,safe&height=600&width=1200&fit=bounds{/Image}
{Keywords}AI,/ai,Innovation,/innovation,AI,/ai,Business,/business,Business,standard{/Keywords}
{Source}Inspiration{/Source}
{Thumb}{/Thumb}