Nine months since the launch of OpenAI’s first commercial product, the OpenAI API, more than 300 applications are now using GPT-3, and tens of thousands of developers around the globe are building on the GPT-3 platform. GPT-3 currently generates an average of 4.5 billion words per day, and continue to scale production traffic.

Given any text prompt like a phrase or a sentence, GPT-3 returns a text completion in natural language. Developers can “program” GPT-3 by showing it just a few examples or “prompts.” OpenAI designed the API to be both simple for anyone to use but also flexible enough to make machine learning teams more productive.

Applications and industries

To date, over 300 apps are using GPT-3 across varying categories and industries, from productivity and education to creativity and games. These applications utilize a suite of GPT-3’s diverse capabilities (and have helped OpenAI discover new ones!). A few of these include:

Viable helps companies better understand their customers by using GPT-3 to provide useful insights from customer feedback in easy-to-understand summaries.  Using GPT-3, Viable identifies themes, emotions, and sentiment from surveys, help desk tickets, live chat logs, reviews, and more. It then pulls insights from this aggregated feedback and provides a summary in seconds.

For example, if asked, “What’s frustrating our customers about the checkout experience?”, Viable might provide the insight: “Customers are frustrated with the checkout flow because it takes too long to load. They also want a way to edit their address in checkout and save multiple payment methods.”

“GPT-3’s ability to identify themes from natural language and generate summaries allows Viable to give product, customer experience, and marketing teams at companies across industries a better understanding of their customers’ wants and needs,” said Daniel Erickson, CEO of Viable.

Fable Studio is creating a new genre of interactive stories and using GPT-3 to help power their story-driven “Virtual Beings.”

Lucy, the hero of Neil Gaiman and Dave McKean’s Wolves in the Walls, which was adapted by Fable into the Emmy Award-winning VR experience, can have natural conversations with people thanks to dialogue generated by GPT-3. Lucy appeared as a guest at Sundance Film Festival 2021 and presented her own movie, Dracula.

“GPT-3 has given us the ability to give our characters life,” said Fable Studio CEO Edward Saatchi, adding, “We’re excited to combine an artist’s vision, AI, and emotional intelligence to create powerful narratives, and believe that one day, everyone will know a Virtual Being.”

Algolia uses GPT-3 in their Algolia Answers product to offer relevant, lightning-fast semantic search for their customers.

When the OpenAI API launched, Algolia partnered with OpenAI to integrate GPT-3 with their advanced search technology in order to create their new Answers product that better understands customers’ questions and connects them to the specific part of the content that answers their questions. Algolia Answers helps publishers and customer support help desks query in natural language and surface nontrivial answers. After running tests of GPT-3 on 2.1 million news articles, Algolia saw 91% precision or better and Algolia was able to accurately answer complex natural language questions four times more often than BERT.

“We’ve seen great results from Algolia Answers on questions that are difficult to answer with textual search alone,” said Peter Buffington, Product Manager at ABC Australia. “It was able to return very relevant, evergreen content from our news archives for questions such as ‘Why does a volcano erupt?’”

“GPT-3 allows Algolia to answer more complex queries than ever before with our Algolia Answers product, identifying deeper contextual information to improve the quality of results and deliver them in seconds,” said Dustin Coates, Product and GTM Manager at Algolia.

Platform improvements

As OpenAI scales access, their team is continually improving the platform—from implementing a content filter to offering new features for developers including their recently launched:

  • Answers endpoint: Searches provided information (documents, knowledge bases etc.) for relevant context to be added to the prompt before completing with GPT-3. Can be used to build applications like customer support bots with no fine-tuning.
  • Classifications endpoint: Can leverage labeled training data without fine-tuning. By searching for the closest examples with respect to the input query and adding them to prompt, it often matches the performance of state of the art fine-tuned models, providing an autoML solution that is easy to configure and adapt.
  • Enhanced search endpoint: Provides the backbone for the Answers and Classifications endpoints that scales to a large number of documents while also being cheap and fast.
  • Safety: Bias and misuse are important, industry-wide problems we take very seriously. We review all applications and approve only those for production that use GPT-3 in a responsible manner. We require developers to implement safety measures such as rate limits, user verification and testing, or human-in-the-loop requirements before they move into production. We also actively monitor for signs of misuse as well as “red team” applications for possible vulnerabilities. Additionally, we have developed and deployed a content filter that classifies text as safe, sensitive, or unsafe. We currently have it set to err on the side of caution, which results in a higher rate of false positives.
  • Prompt library: Provides starter prompt design examples for dozens of use cases that users can begin programming with directly in Playground, like a Spreadsheet Generator, Grammar Corrector, or Airport Code Extractor.

Source: OpenAI Blog @ https://openai.com/blog/gpt-3-apps/