ChatGPT to GPTs: Fine-tuning AI models for specific downstream Tasks

Introducing GPTs; You can now create custom versions of ChatGPT that combine instructions, extra knowledge, and any combination of skills. OpenAI's new GPT builder is a huge opportunity for early adopters. GPTs are a new way for anyone to create a tailored version of ChatGPT to be more helpful in their daily life, at specific tasks, at work, or at home—and then share that creation with others.

Here is a simplified guide to help you through each step of the process:

𝗦𝘁𝗲𝗽 𝟭:

Access the GPT Builder through OpenAI's interface, available to ChatGPT Plus subscribers. Imagine you’re creating a GPT to assist with cooking recipes. Start by navigating to the "Create a GPT" section.

𝗦𝘁𝗲𝗽 𝟮:

Use conversational input to describe the GPT you want to build. This helps generate a basic draft. Keep your description clear and simple. For example, "I want to create a GPT that gives cooking tips and recipes." Think about the core function of your GPT. Do you want it to provide quick tips, detailed guides, or something else?

𝗦𝘁𝗲𝗽 𝟯:

Customize your GPT by changing its name, and profile picture, and adding specific knowledge through file uploads. Start with basic configurations. Choose a name that reflects your GPT's purpose, like "ChefGPT." If you’re making a cooking GPT, you might upload popular recipes or the latest dietary guidelines. Upload guides or articles to make your GPT more knowledgeable in the field.

𝗦𝘁𝗲𝗽 𝟰:

Interact with your GPT to see how well it follows instructions and performs its intended function. Test with simple queries first, like “How do I make a chocolate cake?” Pay attention to how your GPT responds and make notes for potential improvements.

𝗦𝘁𝗲𝗽 𝟱: 🚀

Launch!

Once satisfied, save your GPT and choose to publish it, making it available to others.

𝗧𝗶𝗽𝘀:

𝗦𝘁𝗮𝗿𝘁 𝗦𝗶𝗺𝗽𝗹𝗲: Begin with basic concepts and gradually add complexity.

𝗙𝗲𝗲𝗱𝗯𝗮𝗰𝗸 𝗮𝗻𝗱 𝗜𝘁𝗲𝗿𝗮𝘁𝗶𝗼𝗻: Use feedback from your interactions to improve your GPT.

𝗘𝘅𝗽𝗹𝗼𝗿𝗲 𝗮𝗻𝗱 𝗘𝘅𝗽𝗲𝗿𝗶𝗺𝗲𝗻𝘁: Don’t be afraid to try different configurations and see what works best.

𝗖𝗿𝗲𝗮𝘁𝗶𝗻𝗴 𝗮 𝗚𝗣𝗧 𝗶𝘀 𝗳𝘂𝗻

Learn more about AI HERE

This post was initially posted by Steve Nouri

GPT-4 Can Score 99% on Graduate Record Examination Verbal (GRE-Verbal)

GPT-4, is the latest milestone in OpenAI’s effort in scaling up deep learning. GPT-4 is a large multimodal model (accepting image and text inputs, emitting text outputs) that, while less capable than humans in many real-world scenarios, exhibits human-level performance on various professional and academic benchmarks.

For example, it passes a simulated bar exam with a score around the top 10% of test takers; in contrast, GPT-3.5’s score was around the bottom 10%. OPEN AI spent 6 months iteratively aligning GPT-4 to produce their best-ever results (though far from perfect) on factuality, steerability, and refusing to go outside of guardrails.

Over the past two years, they rebuilt our entire deep learning stack and, together with Azure, co-designed a supercomputer from the ground up for the workload. A year ago, they trained GPT-3.5 as a first “test run” of the system. They found and fixed some bugs and improved on theoretical foundations. As a result, the GPT-4 training run was unprecedentedly stable, becoming the first large model whose training performance we were able to accurately predict ahead of time. As they continue to focus on reliable scaling, we aim to hone our methodology to help us predict and prepare for future capabilities increasingly far in advance.

Enroll at HURU School's for the Artificial Intelligence Picodegree