[Lex Computer & Tech Group/LCTG] Prompt Engineering

Tue Aug 27 08:44:01 PDT 2024

Regardless of where the field is today, it seems logical that to the extent that the activity of the brain can be “read” that eventually it will be understood.  Presumably this will occur slowly but eventually happen.  Who would have believed that “thoughts” can cause an artificial limb to move?

Whether AI can somehow aid in the understanding of a large amount of brain data is beyond my understanding, but I’d opt for information from trusted sources, not, say, facebook  Let’s see what comes out of research labs that is reproducible

John

From: LCTG <lctg-bounces+jjrudy1=comcast.net at lists.toku.us> On Behalf Of Harry Forsdick via LCTG
Sent: Tuesday, August 27, 2024 9:40 AM
To: Robert Primak <bobprimak at yahoo.com>
Cc: lctg at lists.toku.us
Subject: Re: [Lex Computer & Tech Group/LCTG] Prompt Engineering

Bob,

You are right:  I agree with your concern with equating Large Language Models (LLMs) with Artificial Intelligence (AI).  Doing so succumbs to the hype of Wall Street.

Unfortunately to the uninformed, introducing this TLA into the conversation makes the impressive results of LLMs even more mysterious and just for techies.

-- Harry

On Mon, Aug 26, 2024 at 1:58 PM Robert Primak <bobprimak at yahoo.com <mailto:bobprimak at yahoo.com> > wrote:

Very good finds, Harry.

Within the context of reading people's thoughts, a lot of what prompt engineering can and cannot do depends on the size of the data set it is trained on, and the variety of test subjects from whom the training data is collected. Too small a sample size in either regard, and there is a real chance of researcher bias (conscious or unconscious) entering into the picture and affecting the output from the LLM.

I do not equate LLMs with AI, so I restrict my terms to what we are talking about -- LLMS only, not more general AI. 

-- Bob Primak 

On Monday, August 26, 2024 at 11:35:42 AM EDT, Harry Forsdick via LCTG <lctg at lists.toku.us <mailto:lctg at lists.toku.us> > wrote: 

Folks,

Remember when Conor O'Mahony gave his three excellent talks about AI / ML systems?  [see https://docs.google.com/document/d/1fj8FcfD_e-NEi20O3AL_8fg45DdB136fvyCNl7V2gaM/edit?usp=sharing] 

One of the topics he talked about was "prompt engineering".

I interpreted what was said about prompt engineering to refer to the kinds of things we all did with plain old Google to get it to return the kind of results we were after.  

I recently asked https://perplexity.ai  <https://perplexity.ai> the question "What does "prompt engineering" mean in the context of AI search systems?".  I learned that my interpretation was only partially correct.  Instead of being just things an end-user does, prompt engineering is also something that a developer of an AI question/answering system must do to take the query submitted by end-users, and add additional controls to get the AI answer engine to return a reasonable, readable answer.

One of the references in this response, https://mitsloanedtech.mit.edu/ai/basics/effective-prompts/, discusses what an end user should learn to do.  It basically says that this is like learning how to ask questions of an expert who knows a lot about the subject of your query: you can steer the answer to the one you are after if you just ask the question correctly.  To quote from the above reference:

Prompts are your input into the AI system to obtain specific results. In other words, prompts are conversation starters: what and how you tell something to the AI for it to respond in a way that generates useful responses for you. After that, you can build a continuing prompt, and the AI will produce another response accordingly. It’s like having a conversation with another person, only in this case the conversation is text-based, and your interlocutor is AI.

Below is the answer I got back from Perplexity.  If you want to dig deeper than the Perplexity answer, there are references to source material used in the response.

Regards,

-- Harry

What does "prompt engineering" mean in the context of AI search systems?

Prompt engineering is a crucial process in the context of AI search systems, particularly for large language models (LLMs) and generative AI tools. It involves crafting well-structured and effective input queries or instructions to guide AI models in producing desired outputs or responses[1].

Definition and Purpose
Prompt engineering refers to the art and science of designing and optimizing prompts to elicit specific behaviors from AI models[4]. Its primary goal is to bridge the gap between human intention and machine understanding, enabling AI systems to generate accurate, relevant, and contextually appropriate responses[2].

Components of Effective Prompts

1. Instruction: Prompts often require specific and clear requests to receive the desired output[3].

2. Context: Providing relevant background information helps the AI model understand the task better[3].

3. Input Data: This includes any necessary information for the AI to process and generate a response[3].

4. Output Format: Specifying the desired format of the response can improve the accuracy and relevance of the AI's output[3].

Role of Prompt Engineers
AI prompt engineers serve as intermediaries between machine learning models and human users[3]. Their responsibilities include:

1. Developing sets of inputs to train models for optimal outputs
2. Writing text-based prompts for various tasks (e.g., essay writing, blog post generation)
3. Evaluating AI systems for idiosyncrasies
4. Training and fine-tuning emerging AI tools

What does "prompt engineering" mean in the context of AI search systems?
Prompt engineering plays a vital role in AI search systems by:

1. Improving Accuracy: Well-crafted prompts lead to more precise and relevant responses from AI models[4].
2. Enhancing User Experience: Clear and concise prompts make it easier for users to interact effectively with AI models[4].
3. Mitigating Biases: Careful prompt design helps minimize the risk of generating inappropriate or biased content[4].
4. Ensuring Consistency: Proper prompting techniques enable more predictable and reliable AI responses[4].

Skills Required for Prompt Engineering
To excel in prompt engineering, professionals should possess:

1. Understanding of AI, ML, and Natural Language Processing (NLP)
2. Programming skills, particularly in Python
3. Strong communication skills
4. Knowledge of cognitive psychology and linguistics
5. Experience with pre-trained AI models like GPT-3 or GPT-4[3]

In conclusion, prompt engineering is a critical aspect of AI search systems, focusing on optimizing the interaction between humans and AI models to produce high-quality, relevant, and accurate responses.

Citations:
[1] https://en.wikipedia.org/wiki/Prompt_engineering
[2] https://www.datastax.com/guides/what-is-prompt-engineering
[3] https://www.techtarget.com/searchenterpriseai/definition/AI-prompt-engineer
[4] https://cloud.google.com/discover/what-is-prompt-engineering
[5] https://www.ibm.com/topics/prompt-engineering
[6] https://www.akooda.co/blog/what-is-prompt-engineering
[7] https://researchguides.mvc.edu/ai/prompts
[8] https://mitsloanedtech.mit.edu/ai/basics/effective-prompts/

 <http://www.forsdick.com/resume/> Harry Forsdick
 <http://lexingtonphotoscan.com/> Lexington Photo Scanning
 <http://lexingtontmma.org/> Town Meeting Member Precinct 7
 <https://mail.google.com/mail/?view=cm&fs=1&tf=1&to=harry@forsdick.com> harry at forsdick.com
 <http://www.forsdick.com/> www.forsdick.com

 <https://goo.gl/xZXT2F> 46 Burlington St.
Lexington, MA 02420
 <callto:17817996002> (781) 799-6002 (mobile)

 <http://forsdick.weebly.com/home/my-websites> Click to see my websites

Lafayette Returns
200th Anniversary Reenactment
----> September 2, 2024 (Labor Day) 1pm-2pm 

Lexington Battle Green

  <https://forsdick.com/0MyImages/LafayetteReturns.png> 

Procession, Lafayette Reenactor, Minute Men, School Children, Bell Ringing,

Period Costumes, 🔥 Cannon Fire 🔥, and ... cookies shaped like Lafayette

===============================================
::The Lexington Computer and Technology Group Mailing List::
Reply goes to sender only; Reply All to send to list.
Send to the list: LCTG at lists.toku.us <mailto:LCTG at lists.toku.us>       Message archives: http://lists.toku.us/pipermail/lctg-toku.us/
To subscribe: email lctg-subscribe at toku.us <mailto:lctg-subscribe at toku.us>   To unsubscribe: email lctg-unsubscribe at toku.us <mailto:lctg-unsubscribe at toku.us> 
Future and Past meeting information: http://LCTG.toku.us
List information: http://lists.toku.us/listinfo.cgi/lctg-toku.us
This message was sent to bobprimak at yahoo.com. <mailto:bobprimak at yahoo.com.> 
Set your list options: http://lists.toku.us/options.cgi/lctg-toku.us/bobprimak@yahoo.com

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.toku.us/pipermail/lctg-toku.us/attachments/20240827/ad603f18/attachment.htm>