AI-Powered Autocomplete Lets you Code in Natural Language

AI-Powered Autocomplete Lets you Code in Natural Language

Microsoft's Power App Ideas, is the first to come out of Microsoft's partnership with artificial intelligence research company OpenAI, which was announced last year. This is important because it's showing the scale of GPT-3 enabled tools. If you enjoy articles like these, sign up to the Last Futurist, my speculative blog.

In September 2020, Microsoft purchased an exclusive license to the underlying technology behind GPT-3, an AI language tool built by OpenAI. Now in 2021, we're starting to get an idea of how this will first be monetized.

 Microsoft is now using OpenAI’s massive GPT-3 natural language model in its no-code/low-code Power Apps service to translate spoken text into code in its recently announced Power Fx language. Is this another way software development is being automated?

Microsoft's first product features powered by GPT-3 does raise a number of questions. For instance, the new AI-powered features will allow an employee building an e-commerce app to describe a programming goal using conversational language. It shows the huge potential for machine learning to help novice programmers by functioning as an autocomplete tool for code that could evolve.

It’s important to note that while this makes programming easier, Microsoft itself stresses that users still have to understand the logic of the application they are building. This could make coding more accessible to students (and kids!) in ways that weren't possible before.

 It uses OpenAI’s Generative Pre-Trained Transformer-3 (GPT-3) AI model, one of the most advanced natural language AI models in the world today. The long-term promise here, though, is for tools like this to become smarter over time and be able to handle more complicated programming tasks. There’s massive demand for digital solutions but not enough coders out there, so obviously if this can become sophisticated companies will be able to do more with less developers.

While Power Fx is built on Microsoft Excel, and therefore much easier to use than traditional coding languages, creating complex data queries can still be a steep learning curve, and these new features help lower that curve. Microsoft has been pursuing this vision for a while through Power Platform, its suite of “low code, no code” software aimed at enterprise customers. The key is a lower bar to accessibility.

Think about it, these programs run as web apps and help companies that can’t hire experienced programmers tackle basic digital tasks like analytics, data visualization, and workflow automation. GPT-3’s talents have found a home in PowerApps, a program in the suite used to create simple web and mobile apps. Over time it's feasible Microsoft could acquire OpenAI, just as Google acquired DeepMind. Microsoft is in many ways better positioned to monetize AI than Google just based on the diversification and business touchpoints of their software suites.

Instead of having users learn how to make database queries in Power Fx, Microsoft is updating PowerApps so they can simply write out their query in natural language, which GPT-3 then translates into usable code. This is a kind of automation and shows the usefulness of GPT-3 whose applications are many.

Microsoft has seen significant traction with the recent announcement that Power Automate would be included in Windows 10, which means over 1 billion devices now have access to automation initiatives. When even small steps can impact many users and potential products, digital transformation really is moving forwards and Microsoft has seen an epic 2020 and 2021 thus far.

These new features will go live in public preview in English to users in North America by the end of June. The company only supports the English language right now and the product works only for specific formulae within the Power Apps service. What's the future of making coding easier and more accessible like? The long-term promise here, though, is for tools like this to become smarter over time and be able to handle more complicated programming tasks.

We are just in the early innings of artificial intelligence and its intersection with coding and software engineering. Built by OpenAI, an independent AI research and deployment company, GPT-3 is a massive natural language model that runs exclusively on Azure. You can learn more here.

Chandrasekaran K.

The Beast which Eat & Lives in around Healthcare IT

3 年

So, What Next ? Floppy disks, CDS, old type Monitors..in this series (we lost).. The RDBMS & its studies will also be included soon..right Mr.gate?

Heidi Dent

Communication-driven B2B sales and marketing leader focused on technology, AI, communication, and cybersecurity social engineering tactics. Angel Investor. Guest Lecturer Marketing and Entrepreneurship.

3 年

Excellent article. 1 billion devices already having access and the ease of learning offers high hopes for future innovation

Yuri Levchuk

Chief Scientist and Chief Engineer at Intelligent Models Plus

3 年

Would be interesting to see the coding by a human-machine team/tandem (with human's commenting to cue the machine, and machine's offering the coding options for a human to downselect, while in parallel with the autonomous code optimization performed akin to the DeepMind's AI agent's self-play).

Prof. Dr. Frauke Bender

Professor International Management | Trainer for Intercultural & Diversity Topics | Keynote Speaker | Author: A Roadmap to Intercultural Proficiency | Producer: The cultureXchange Podcast

3 年

要查看或添加评论,请登录

社区洞察

其他会员也浏览了