26 Apr Featured Article : Want to be a ‘Prompt Engineer’?
No – it’s doesn’t mean engineers that are punctual! In this article, we will explore the role of prompt engineers in the AI industry, why the job is necessary, why it’s suddenly a sought-after role, and what the future prospects are for prompt engineers.
What is Prompt Engineering?
A prompt engineer is a specialist who designs effective instructions for AI models. Prompt engineering is the ‘art’ of crafting effective instructions for AI models, such as ChatGPT, Google Bard, or Baidu.
With generative AI models (such as language models like ChatGPT or image generation systems, e.g. Dalle-E or MidJourney), successful creations (outputs) can be amazing, yet they can only really happen if the model or system has the right input/guidance to work with. An untrained user’s results can be flawed or even wrong, hence the need for the ‘prompt engineer’.
The goal of a prompt engineer is, therefore, to coax and guide AI models into generating content that is relevant, coherent and consistent with the desired output.
The Rise of Prompt Engineers in the AI Industry
As the AI industry continues to grow exponentially and more LLMs and competitors to ChatGPT seem to be hitting the market in what is a chatbot revolution, new job roles are emerging to meet the demands of this rapidly evolving sector.
Why The Need for Prompt Engineers?
Generative AI models respond to natural language, which is notoriously imprecise. The same sentence can have different meanings depending on the context, making it difficult for the AI model to understand what the user wants it to generate. Also, natural language prompts may not provide enough context for the AI to understand the user’s intent fully, which can lead to the AI generating responses that are not relevant to the user’s needs or expectations.
As Microsoft says, “GPT-3, GPT-3.5, and GPT-4 models from OpenAI are prompt-based” and the user interacts with the model by entering a text prompt, to which the model responds with a text completion. However, whilst these models are immensely powerful, as Microsoft explains “their behaviour is also very sensitive to the prompt.” This makes prompt construction an important skill to develop.
It’s also important to remember that generative AI models are typically trained on large amounts of text data, but the training data may not contain the examples that match the specific intent of the user’s prompt, limiting the AI’s ability to generate responses that accurately reflect the user’s needs.
Why the Sudden Interest?
With the increasing sophistication of AI algorithms and more businesses adopting tools like ChatGPT as an important part of their work tools, it is becoming more feasible for AI systems to take over the role of coding, leaving software engineers to focus on higher-level tasks such as formulating intent and logical sequences to guide the code generator. This shift will likely require software engineers to have a more profound understanding of AI algorithms and how they operate. As a result, they will be able to craft prompts that can direct the AI to generate code that meets the desired specifications accurately.
The role of software engineers will evolve into one of guiding and overseeing the AI’s work, providing input and feedback, and ensuring that the generated code meets the project’s requirements.
A Critical Role
Prompt engineering will be critical in using automated code generators as prompts must be carefully crafted to accurately capture the intent of the desired code. Additionally, prompt engineering can help ensure that the generated code aligns with industry best practices, standards, and guidelines.
How Much Can A Prompt Engineer Earn?
Some online prompt engineer job ads quote six-figure salaries.
What Experience Do You Need?
Since the role is more about effectively communicating with an algorithm using conversational language and gradually teaching it how to respond and follow specific guidelines, a tech background is not absolutely necessary, although it may help to provide the context to guide the work.
The Future Prospects for Prompt Engineers
Robin Li (cofounder and CEO of Chinese AI giant Baidu) for example, has predicted that prompt engineering will be one of the most important jobs in the future, with half of the world’s jobs being in prompt engineering in ten years!
While this may be hyperbole, it is clear that the role of prompt engineers will continue to be in high demand. Already, prompt engineering experts are popping up all over the place, startups are offering prompt engineering services, and companies are starting to list “prompt engineer” as a job title.
The development of prompt libraries is making it easier for anyone, including prompt engineers, to create effective prompts that get the best out of generative AI models.
Prompt libraries, like libraries of pre-written code or software components that can be reused in different programs or applications, contain components which allow the user to save time rather than creating new prompts from scratch.
Whether you’re prompt engineer or a business wanting to get the best and most relevant outputs from generative AI and perhaps save yourself the cost of hiring a prompt engineer, or even to help train yourself as a prompt engineer, prompt libraries can help.
Examples of prompt libraries and tools to help with prompts for ChatGPT include:
– Promptvine.com – a site offering a variety of prompts for ChatGPT.
– Everyprompt.com – descibes itself as “good playground for large language models like GPT-3″.
– Flowgpt.com – A platform for finding prompts for ChatGPT and business analysis and market research.
– Awesomegptprompts.com – a resource for prompts and tools to help you get the most out of ChatGPT.
– Prompto.chat – A prompt resource that says it can “turn you into a ChatGPT superhero.”
– Promptbase.com/chatgpt – A platform offering a range of prompts and other resources for ChatGPT user.
OpenAI’s Own Guidance And Tools
ChatGPT’s creator OpenAI offers its own “Best practices for prompt engineering with OpenAI API” online where it gives rules of thumb, examples of prompts that work well with GPT-3 and Codex, and a list of additional resources. See: https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-openai-api.
OpenAI also give instructions about how to create a good prompt here: https://help.openai.com/en/articles/4936848-how-do-i-create-a-good-prompt
Also, Zapier gives examples of how to write an effective ChatGPT prompt here: https://zapier.com/blog/gpt-prompt/.
In addition, there is also a growing number of tools such as a Google browser extension offering to help with prompts and improving productivity, e.g. with ChatGPT.
Specialisation In Prompt Engineering
It seems we’re already at the stage where prompt specialisations are emerging for code generation, output testing, text generation, and art generation.
What Does This Mean For Your Business?
The implication is that in less than 6 months of the general release of ChatGPT, generative AI is already serving an important role in businesses and the Prompt Engineer’s role is an example of one of the new jobs that have been created by automation, rather than lost to it. The fact that large salaries are being offered for this role shows how vital the use of generative AI is to businesses, while the number of prompt libraries and the Prompt Engineer’s job show how businesses are looking to maximise the advantages that generative AI can provide by looking for specialisation.
Being able to guide these powerful algorithms in a way that optimises outputs and overcomes the known limitations of chatbots as they stand now is an emerging as a valued job in itself with businesses indicating that the value it provides is worth a large salary. It remains to be seen, however, as generative AI chatbots improve and more are introduced, how quickly this role changes and what other roles are developed and created.