4 Methods of Prompt Engineering

Explore watsonx → ibm.biz/explore-ibm-watsonx
Dig Deeper: What is prompt engineering? → ibm.biz/prompt-engineering
Learn generative AI → ibm.biz/generative-ai-for-dev...
Have you heard of these AI prompt engineering methods?
• Retrieval Augmented Generation (RAG)
• Chain-of-Thought (COT)
• ReACT (Reason + Act)
• Directional Stimulus Prompting (DSP)
Wondering what the differences and values of each are?
In this video, IBM Distinguished Engineer Suj Perepa explains those differences and values, provides an example of each method, and tells how they can be best used and even combined.
Introduction 0:00
RAG 1:16
Chain of Thought (COT) 3:33
ReACT 6:30
Directional Stimulus Prompting (DSP) 10:48
Combinations 12:05
Get started for free on IBM Cloud → ibm.biz/sign-up-now
Subscribe to see more videos like this in the future → ibm.biz/subscribe-now
#ai #neuralnetworks #promptengineering #genai

[@DataScienceAI-rf4kx]

Summary 1. **RAG (Retrieval Augmented Generation):** Augmenting the knowledge base (db) to enhance responses by combining language models. 2. **Chain of Thoughts:** Promoting ideas using 'thoughts' 💭 in the form of chunks one by one to obtain actual answers. Language models arrive at your desired answers through reasoning and logic. 3. **ReAct (Thought, Action, and Observation):** Different from the chain of thoughts, this involves both private knowledge base (db) and public language model (llm) data. If information isn't in the knowledge base, it goes back to the public llm data (trained data) for results. 4. **DSP (Direct Stimulus Prompting):** The latest method involves hinting the prompt with a specific hint to get the answers.

[@DanAlvard]

@IBM Technology I got the theory but I want to see an example of the actual resulting prompt in each of the 4 methods. Nothing beats learning by example

[@HojaUno]

I like they are labeling every interaction with the LLMs. Prompt engineering, rag, cot, react, dsp. These are the basic blocks and as a developer I share what many are already seen and working on it. A higher programing language where it is no longer constrained to direct the physical and structured layer to compute the results. This programming language will skip those layers 100% to work directly on the business problems. It may be named as mayeutic. Supporting in a new way critical questions; fast no longer will be the measure. Fast will be just side effect. The key will be the transition from RDBs, repositories, rudimentary data input, rudimentary finance procedures, to the next abstractions that would facilitate this smart agility using it.

[@egemengulpinar379]

So simple and focused on the main idea and key points. Thank you for your straightforward explanation!

[@UVTimeTraveller]

I understand the main idea, but I think the examples and explanations weren't clearly thought through and felt vague. I didn't get a clear sense of how to apply these techniques effectively in real-life situations. However, I appreciate the intention and the effort put into it.

[@GibranCastillo]

A prompt is a specific instruction or query given to an LLM (Large Language Model) to perform a task. A task can be: Providing information, summarizing, analyzing, planning, reasoning, coding, generating, etc. Effective prompt engineering involves iteratively refining these instructions or questions to achieve a more accurate, relevant, or desired outcome from the LLM.

[@saadowain3511]

Absolutely amazing

[@osamaa.h.altameemi5592]

simple, direct, and on point. Thx a ton

[@vanir23]

It is wild to me how engineers view the research process. Honestly, they make it more complicated than it needs to be.

[@bowneeb4986]

Beautiful explanation!!

[@things799]

Love you guys

[@storyteller_prashant]

Really nice 👍

[@marquesjones3411]

Does this apply to all practical language models currently? This is how I should rizzz up my chat4 bot?

[@karthickwork3296]

Woule be helpful if you can come up with realime example and usuage. May be in parts..

[@MrVengngy]

That amazing

[@SB-vj5sn]

Nice, short clip, explaining such mega-areas in 12 minutes

[@ifeanyiidiaye1889]

Nice video, thanks guys! Quick question: are all your engineers at IBM left-handed? You seem to have a bias for left-handed engineers 😅

[@daveqr]

The image is reversed. They have a video explaining how they make lightboard videos.

[@yesblahblah]

The view you are seeing it from has been flipped. There is a video on this channel or steve brutons where they explain how they make these videos. Also, if you assume the rule of wearing your wedding band on your left hand ring finger applies then you are looking at the marker being in his right hand.

[@ethanfogarty9540]

They are all right-handed. The camera is behind them and is recording them facing and writing on some sort of mirror that makes their markers glow. Almost like an old school SmartBoard, but as a mirror.

[@diptarshi1234]

How it is generating responses if I only have to train it with all actual data.

[@jabee81]

The lady explanation always confused me, but still appreciate the intention.

[@maikvanrossum]

So basically this about ‘structuring’ your prompts in a way the LLM has to process your input…? And who is expected to formulate these ‘natural language’ questions…?

[@gkennedy_aiforsocialbenefit]

Excellent presentattion

[@ChuckNorris-lf6vo]

Im sorry I don't get it at all? What does the computer do exactly ?

[@j.maginnenu6291]

Lol

[@riteshranjan3260]

Good short/focused content. But example/context could have been lot better.

[@yasmineclaire5299]

But but they all sound the same essentially? Please tell me the nuanced difference between the four.

[@jonesbbq307]

So ReACT is just RAG with two databases?

[@faketrump3605]

sorry for my slowness. but the only thing I could understand is the RAG. the other ones are not clear.

[@alexanderepifani2657]

top

[@darrenwastestime]

example prompts would've been helpful

[@davepowder4020]

I have two questions. One, is IBM going to "decouple" from any dependency or vulnerability via China? Two, could IBM get back into the PC market? They were in rough times when they divested from their old PC, and sold it off as Lenovo. But they could really bring a high-end machine to market, and keep it U.S. developed.

[@WilliamStonerock]

The US dependency by IBM is also problematic. The pervasive and unethical spying by the American govt should have any company that relies on AI worried.

[@techwithjesus8263]

She's good 👍

[@side54723]

😮Giving the same example for dsp and cop makes it confusing React isnt helping with prompt but with results... Misleading title

[@sapiomancer]

Instantly confusing and unclear. The example didn't even flow in relation to what she was saying.

[@lordlee6473]

That was confusing due to inferior examples given. No you didn’t succeed in explaining to a 8 year old

[@user-eu5in1gw2h]

This is really terrible! RAG is not a method of prompt engineering, it's an architecture! And as far as the prompt explanations, they are also really poor. No wonder nobody uses IBM anymore

[@made432]

[@made432]

[@user-jf5uv9ir5k]

Awful video for beginners

[@krisrusso5900]

i never even thumb downed a video before. content was lacking. no prompt examples.

[@j.maginnenu6291]

Lol😂

[@galengkm]

Agreed this was very lame, terrible examples and explanation lacking in specificity and clarity

[@app8414]

It's click bait.

[@AdamPippert]

These videos are not for AI engineers, they are for business people that need to understand the tools and techniques used in generative AI. If you want real media AI content, go check out machine learning Street talk. This is not the channel for you.

[@kboyle1127]

This is completely inaccurate and confusing. IBM should take this down and check for accuracy of their content before putting this out there

[@WilliamStonerock]

Can you outline, briefly, the inaccuracy?

[@2010RSHACKS]

They trying to simplify it

[@eatyourt0fu]

I'm confused. Isn't RAG and prompt engineering two fundamentally different concepts?