Ken Acquah: SQL
SQL: love it or hate it, it's an essential part of almost every enterprise's operations. Ken Acquah, an Undergraduate Researcher at MIT Computer Science and Artificial Intelligence Laboratory & former Chairperson of the MIT chapter of the National Society of Black Engineers, coaxed GPT-3 into translating English instructions into SQL queries.
GPT-3 Does The Work™️ on some business analyst SQL queries given quite a few examples from (https://t.co/65ixaxzdyS). What's wildest is that it knows a few functions like SUBSTR given no examples in that syntax. More to come re: GPT-3 for automating data analytics tasks. pic.twitter.com/3Iwe8WQudD
— ken (@aquariusacquah) July 19, 2020
Although it can be confusing at first, SQL is actually quite "English-like" in its syntax already–even if you're not familiar with it, you can probably figure out what's going on in this example. Of course, you can do much more with it than these quite basic queries, and it will be exciting to see if it can handle more challenging tasks like queries using PostGIS for geographical information data.
It's easy to see, though, how this could revolutionize business analytics: there are already quite a few "natural language" solutions in this field, but the potential for GPT-3 to enable non-technical users to query enterprise or research datasets by writing plain language instructions is huge. Because SQL is so ubiquitous, I think this could become a common feature of BI software very soon.