Skip to main content

AI and prompt engineering

[PLACEHOLDER]

On this occasion we would like to present our take and summary about prompt engineering.

Like everyone else, at Beolle we have been researching the AI space lately, running experiments. On this occasion, our investigation has made us present our take and summary about prompt engineering.

(Skip Ahead note: If you like to get right to it then skip to the section What are prompts.)

Generated image with Microsoft Designer and DALL-E 3 + Modified by Beolle team

 

(Parenthesis)

 AI has disrupted all industries, and it will continue to do so as we explore new territories. We are still in discovery mode. Sectors and industries are building their know-how, evolving and using this technology;  determining the value it brings to the business.

The investment by tech players and executives, in traditional and Gen AI (Generative AI) capabilities, continues rising. The consequence has been an accelerated growth in a short matter of time. Venture capital investment in AI has grown 13x over the last ten (10) years.

Mckinsey partial image from report on GenAI impact on business


If you like to read more about the Mckinsey report, and get the full images then go to The economic potential of generative AI: The next productivity frontier. 

(Parenthesis - end) 


What are prompts?

Prompts are queries that users can provide to the Large Language Model (LLM) in order to bring forth responses. They enable us to interact with the model in plain, natural language. 

Prompt Engineering is asking the right question to get the best output from the LLM. 

Good Prompt Engineers will allow companies to get the best out of the AI models. They are creative and persistent, with good technical knowledge, an understanding of the models and the domain, as well as they are great at experimentation (exploring different parameters and settings for fine-tuning the prompts). Even though it would be a plus, you don’t need to know how to code.

By looking at the NLP progression, you can see how things have evolved to where we are (Well, at least at the time of this article creation as things continue evolving constantly and quickly in this space), which is prompt engineering:

Models/patterns Engineering progression
Initially we had supervised learning (Non-Neural Networks).
This could use SVM (Support Vector Machine), which is a type of supervised learning algorithm that can be leveraged, as an example, for classification and regression tasks.
Here is where Feature Engineering comes. This is when transforming the raw data into Features that can be used by ML models.
A Feature is a variable/attribute that serves as input.
Following, Supervised learning (Neural Networks).
Neural Networks are based on a collection of Artificial Neurons, called units. The units are organised within layers. The units are connected, passing signals (inputs) between them.
Architecture Engineering.
A way to look at this Engineering is the Long Short-Term Memory (LSTM). In LSTM the information (data) is gated by the layers, determining what data will be passing through the workflow, and which will be discarded.
Within this engineering you can leverage embeddings + LSTM for processing tasks such as classification and sentiment analysis.
Pre-train and fine-tuning.
Using pre-trained LMs.
Objective Engineering.
The model gets trained for an objective, meaning to perform a specific task.
The fine-tuning technique becomes handy, as you gain efficiency by taking an existing model and specialising it by feeding it the new datasets based on the needs of your specialisation.
Pre-train, prompt, predict.

Defining inputs that fits the model.

Prompt Engineering.

How to Structure your prompt 

  • Instruction. A statement that tells the model what is required. You can also frame the instruction as a question. 
  • Context. Information that can guide the model in a desired direction. 
  • Constraints. (Optional). This can be used to limit the scope by being explicit, keeping the focus on the context. 
  • Input data. (Optional). 
  • Examples. (Optional) The model will have further guidance regarding the answer, and its format, when examples are part of the prompt. Example: Provide a list with the 7 wonders of the world. Only use reliable sources, and list those sources.

Prompt Types

  • Direct prompting or Zero shot. It only contains the instruction in the prompt. 
    • Prompt: Can you give me a list of ideas for blog posts for tourists visiting New York City for the first time? 
  • Prompting with examples. 
    • One-shot. Instruction + one clear example. 
      • Prompt: Come up with a list of ideas for blog posts for visitors to South America. 
        • 1. Have you visited Machu Picchu? Here are a few tips
    • Few-shots. Instruction + more than one example. 
  • Chain-of-thought prompting: This type of prompt provides a series of related prompts to the model. 

Last thoughts

  1. Provide as many details as needed within your prompt. 
  2. Include the majority of the elements explained within the “How to structure your prompt” section. 
  3. Be mindful of hallucinations. Hallucinations are responses with contradictions or inconsistencies, plain and simple the responses are incorrect, either completely, or partially. Chain-of-thought-prompting can help reduce this risk as you request the LLM to explain its reasoning. 
  4. Play with the temperature parameter when prompting and working with LLMs. A higher temperature can move the model response farther from context as it yields to be more creative and open. While a lower one makes things more factual and accurate.

Trending posts

AGILE For DIGITAL AGENCIES

Introduction Some Digital agencies have a project process where waterfalls still plays a big part of it, and as far as I can tell, the tech team is usually the one suffering as they are at the last part of the chain left with limited budget and time for execution. I do believe that adopting an Agile approach could make a Digital Agency better and faster. In this article I’m presenting you just another point of view of why it make sense looking at Agile Methodology.  Why Agile for a Digital Agency? The Agile movement started in the software development industry, but it has being proven to be useful in others as well. It becomes handy for the type of business that has changing priorities, changing requirements and flexible deliverables. In the Digital Agency of today you need a different mindset. Creative will always play a huge role (“the bread and butter”). But the “big guys” need to understand that without technology there is no Digital Agency. Technical resources are

AI with great power comes responsibility

Generative AI continues to be front and centre of all topics. Companies continue to make an effort for making sense of the technology, investing in their teams, as well as vendors/providers in order to “crack” those use cases that will give them the advantage in this competitive market, and while we are still in this phase of the “AI revolution” where things are still getting sorted.   Photo by Google DeepMind on Unsplash I bet that Uncle Ben’s advise could go beyond Peter Parker, as many of us can make use of that wisdom due to the many things that are currently happening. AI would not be the exception when using this iconic phrase from one of the best comics out there. Uncle Ben and Peter Parker - Spiderman A short list of products out there in the space of generated AI: Text to image Dall.E-2 Fotor Midjourney NightCafe Adobe Firefly

Demystifying OKR Scoring

You have probably read that one of the many good things about OKRs is that it provides structure and clarity to work towards common goals. It helps connect company, teams and individuals’ objectives to measurable results.   Photo by Garreth Brown via Pexels In a previous Beolle article, Herak wrote about HOSKR and OKRs. In this iteration we will focus on the OKR scoring. Measuring the “How” The KRs in OKRs are the Key Results. With them we measure the progress towards the Objectives we have set. So how do we score them in a way that makes sense, and measure the success? Few “gotchas” before we start Grades are an indication where you're going. In OKRs, scoring between .6 to .7 is your target. Scores between .8 and 1.0 are rare, meaning they are not the usual. If you find yourself completing all your OKRs within this range then something is not correct, for example, your Objectives are not Ambitious enough, meaning you always knew you (or your company or your team) were going to ach

This blog uses cookies to improve your browsing experience. Simple analytics might be in place for pageviews purposes. They are harmless and never personally identify you.

Agreed