Unit 2

 Large Language Models (LLM)

Large language model (LLM) are a subset of Deep Learning and also refer to AI models trained on massive amounts of text and can generate human-like responses on the spot by predicting what words come next in a phrase—like putting together a puzzle. Large language models can perform various natural language tasks such as:

• Classification
• Summarization
• Translation
• Content generation
• Dialogue (for example, virtual assistants)

Large language models are trained on billions of language examples from diverse sources like books, articles, and websites, which help them to respond with facts, grammatically correct text, argumentation, and a semblance of creativity.

When a prompt is specific and detailed, LLMs can generate text, expand on main points, condense information into key points, and answer questions efficiently. The art of creatively defining LLM prompts is an emerging field known as "prompt design" and "prompt engineering." It involves the process of crafting effective and efficient prompts to get the desired response. Educators and learners may need to experiment with choosing the right words, phrases, symbols, and formats that guide the model to generate high-quality and relevant texts.

Some tips for writing effective prompts are:

• Be specific
• Use the right model for the task
• Ask for results from a certain point of view
• Guide the model to generate the desired length
• Use “new topic” when changing topics

My first time using Copilot

Lesson Plan

This is my first time using Copilot and creating a nice prompt. I want to share with you the results and the lesson plan that Copilot create is amazing!!💖

 

My funko version 

In this case, I use Copilot to design images. Here some people find hallucinations because the funko was not the result that they wanted. This part was interesting because it was our first time watching how an AI hallucinates.

Generative AI

Generative AI is a term for AI systems that generate various forms of novel output, including text, code, graphics, or audio. Generative AI uses deep learning techniques to recognize patterns in data and generate content based on these patterns.

Each time a prompt is entered into a generative AI tool, the AI works to create brand-new content, which means generative AI tools may not create the same content twice for the same prompt. The AI-generated content may follow similar patterns based on its models and algorithms, but the content is original because of the models’ continued training and adjustments.

Generative AI can assist educators by:

• Generating essay prompts or comprehension questions that encourage critical thinking
• Summarizing lengthy articles or texts and allowing learners to quickly grasp main ideas
• Providing personalized feedback on assignments, helping to identify areas for improvement
• Creating interactive language learning exercises like fill-in-the-blank or multiple-choice questions
• Generating examples or explanations for complex concepts and making it easier for learners to understand new material

Machine Learning

Machine learning is a subfield of AI. It is a program or system that trains a model from input data. The trained model can make useful predictions from new (never-before-seen) data drawn from the same one used to train the model. This means that Machine Learning gives the computer the ability to learn without explicit programming.

Deep learning models (or machine learning models in general) can be divided into two types – generative and discriminative.

Discriminative models are typically trained on a dataset of labeled data points, and they learn the relationship between the features of the data points and the labels. Once a discriminative model is trained, it can be used to predict the label for new data points.

A generative model generates new data instances based on a learned probability distribution of existing data. Generative models generate new content.

Prompt Engineering

A prompt usually involves instructions and context passed to a LLM to achieve a desired task.

Prompt Design refers to the process of creating prompts that elicit the desired response from a language model

Prompt Engineering is the practice of developing and optimizing prompts to efficiently use language models for a variety of applications.

Hallucinations 

Hallucinations are words or phrases that are generated by the model that are often nonsensical or grammatically incorrect.

Hallucinations can be caused by several factors, like when: The model is not trained on enough data, The model is trained on noisy or dirty data, The model is not given enough context, or The model is not given enough constraints. Hallucinations can be a problem for Transformers because they can make the output text difficult to understand. They can also make the model more likely to generate incorrect or misleading information.

So put simply... hallucinations are bad.

My first time using Nearpod 

I have never heard about Nearpod, and I love this AI because it is easy to use for teachers and students. 

https://app.nearpod.com/?pin=B8DE3B1E4D119D234BE45E926214E1F0-1&&utm_source=link

My first time using Chat GPT + Presentation

In my personal opinion, Chat GPT it was difficult to use because we have to follow more steps to create presentations, in my case the code at the first time was wrong, so I suggest to Chat GPT to create another, there I notice that  Chat GPT hallucinates too.

https://drive.google.com/file/d/1NxD3DaWXikUBmFrEcp73OBNh7rAIT3ar/view?usp=drive_link

https://docs.google.com/presentation/d/1GKlrFs8iXtiOJz-geXaE_XfPk4Tg_MEjz3_sXEKKx5w/edit?usp=sharing