OpenAI GPT-3, AI Professional

How far is the idea of human-like AI from becoming a reality? A pedestal where AI can talk like a person, give advice, share thoughts, and more.

This fiction could well turn into reality with the coming of OpenAI’s Generative Pre-trained Transformer 3 (GPT-3).

It is a new language model that can generate high-quality texts that are very difficult for humans to differentiate human-to-human conversation from AI-to-human.

In an article on “The Future is Here! Have you checked OpenAI’s GPT-3 Yet?” ARTiBA discusses the secrets of this titan technology. We take a few excerpts from that and try to understand what is GPT-3, how it works, a few examples of its usage, and its significance for AI professionals. For the complete article, check ARTiBA’s Blogs.

Just like humans

It can efficiently complete any English language task. It has been dubbed as one of the most significant advancements in the field of AI. GPT-3 has raised the bar for AI and its potential. For AI professionals, it is a big opportunity to create applications and software operating like human intelligence.

GPT-3: A Few Examples

Human: Hi, how are you?

AI: I am great! What would you like to talk about?

Human: Have you done any coding with Python?

AI: Yes! I’ve done plenty of Python coding since it’s my favorite.

Human: Nice, mine too! What all have you done with it?

AI: Oh, a lot! I have done everything — from creating Python modules to creating micro-websites.

Human: What web framework do you use?

AI: I used Django, but it was difficult for me. I found Flask a better option as it’s lighter and simpler.

Human: Wow. I agree 100%. Have you used WebSocket?

AI: Yes. I have written a chatbot using it.

Interesting! Isn’t it?

The text and conversation generated by GPT-3 is next-level. It is virtually indistinguishable! Here is another example. These paragraphs were written by a GPT-3 engine after training by showing just the first paragraph about GPT-3 on Wikipedia. This is the unedited version of what it produced:

GPT-3 is a deep neural network that uses the attention mechanism to predict the next word in a sentence. It is trained on a corpus of over 1 billion words, and can generate text at character level accuracy. GPT-3’s architecture consists of two main components: an encoder and a decoder. The encoder takes as input the previous word in the sentence and produces a vector representation of it, which is then passed through an attention mechanism to produce the next word prediction. The decoder takes as input both the previous word and its vector representation, and outputs a probability distribution over all possible words given those inputs.

GPT-3’s performance is on par with the best language models for text generation, which is significantly better than previous GPT models. Microsoft’s Turing NLG model can generate text at character level accuracy on a test set of Wikipedia articles, but requires an enormous amount of training data to do so. OpenAI claims that GPT-3 can achieve this level of performance without any additional training data after its initial pre-training period. In addition, GPT-3 is capable of generating longer sentences and paragraphs than earlier models such as Google’s BERT and Stanford NLP’s Transformer.

Know how GPT-3 works in detail, and its benefits for AI professionals, on ARTiBA’s blog. We reproduce a few bits from the blog piece below.

Working of GPT-3

It can be used as a writing assistant.

It can be used for compositions by writers, marketers, among others.

Other than its uses, what’s even more interesting to know is how it does all of that.

GPT-3 generates text using already trained algorithms. The data that drives this titan comes from over 570GB of information from OpenAI, and Common Crawl data. The latter is a publicly available dataset.

What’s more? It works on over 175 billion parameters. Good news for engineers is this technology is prepped with all the data it can need to complete tasks efficiently. To understand, how the publicly available information is interpreted by GPT-3, visit ARTiBA’s blogs.

OpenAI GPT-3 is a 3rd generation prediction model for language that use deep learning.

What’s in it for AI Engineers?

Unlike other AI systems that are developed for single use-case, OpenAI GPT-3 provides a general-purpose text in and text out interface that enables users to try it on any English language task.

It’s one in a kind advancement in the discipline of AI. For AI engineers, there can be no better time to create brilliant applications powerful enough to sway the world of work and people’s everyday lives.

AI is getting stronger. Are you ready to jump on the bandwagon?

Artificial Intelligence field is hard pressed for talent (LinkedIn). Be the solution that industry and the world needs. Get latest knowledge on AI, and learn how to apply it with a professional certification as offered by ARTiBA — Artificial Intelligence Engineer — to empower yourself to innovate business with AI.

Complete article here:

AI Researcher, Writer, Tech Geek. Working on Deep Learning & Neural Networks. #cobots #coding #algorithms