Read more at:
Code is plentiful
And there is an enormous amount of code out there. Just think of GitHub alone. A back-of-the-envelope calculation says there is around 100 billion lines of open-source code available for training AI. That’s a lot of code. A whole lot of code.
And if you need an explanation of how code works, there are something like 20 million questions and even more answers on Stack Overflow for AI to learn from. There’s a reason that Stack Overflow is a shell of its former self—we all are asking AI for answers instead of our fellow developers.
Code is verifiable
In addition, code is easily verified. First, does it compile? That is always the big first test, and then we can check via testing if it actually does what we want. Unlike other domains, AI’s code output can be checked and verified fairly easily.
If you choose to, you can even have your AI write unit and integration tests beforehand, further clarifying and defining what the AI should do. Then, tell your AI to write code that passes the tests. Eventually, AI will figure out that test-driven development is the best path to writing good code and executing on your wishes, and you won’t even have to ask it to do that.
Welcome, Skynet
And finally, code is a great use case for AI agents because developers are generally unafraid of new technology and always seem ready to try out a new tool. This becomes a virtuous circle as AI companies produce coding agents, and developers embrace those coding agents. Software development is a huge part of the economy, and AI companies are strongly incentivized to lean into lucrative markets that are accepting and enthusiastic about using AI agents.
