Code is plentiful
And there is a gigantic quantity of code on the market. Simply consider GitHub alone. A back-of-the-envelope calculation says there’s round 100 billion traces of open-source code out there for coaching AI. That’s lots of code. An entire lot of code.
And when you want an evidence of how code works, there are one thing like 20 million questions and much more solutions on Stack Overflow for AI to be taught from. There’s a cause that Stack Overflow is a shell of its former self—all of us are asking AI for solutions as a substitute of our fellow builders.
Code is verifiable
As well as, code is definitely verified. First, does it compile? That’s all the time the large first take a look at, after which we will examine by way of testing if it really does what we wish. Not like different domains, AI’s code output may be checked and verified pretty simply.
In case you select to, you possibly can even have your AI write unit and integration checks beforehand, additional clarifying and defining what the AI ought to do. Then, inform your AI to put in writing code that passes the checks. Finally, AI will determine that test-driven improvement is the very best path to writing good code and executing in your needs, and also you gained’t even must ask it to do this.
Welcome, Skynet
And at last, code is a good use case for AI brokers as a result of builders are typically unafraid of latest expertise and all the time appear able to check out a brand new instrument. This turns into a virtuous circle as AI firms produce coding brokers, and builders embrace these coding brokers. Software program improvement is a big a part of the economic system, and AI firms are strongly incentivized to lean into profitable markets which might be accepting and obsessed with utilizing AI brokers.
