How is it useful to you?

It feels like the majority of my coding consists of translating extremely complex business requirements that neither the business people nor me understand 100% into highly specific code that appears to do what we want it to do. How can Copilot help me here?

I can only speak for Tabnine, which is like a single-line mini-Copilot, but I find it just saves me keystrokes. It doesn't help me design things.

For example - code quality aside; just for the sake of demonstration - if I have a line `name = data.get("name")` and then press enter and write "ad", it'll likely suggest `address = data.get("address")`, so I can type "[Enter]ad[Tab]" and save myself a few seconds.

Repeat this for every line in a program, and those seconds add up. I'm a fast typist, but it's still nice to have intelligent autocomplete that can infer my intentions with pretty good accuracy.

I'm guessing Copilot will largely be similar, but with support for multiple lines. It'll probably be especially helpful for imperative, somewhat repetitive languages like Go, where boilerplate is common.

Most people are out there making what are essentially wordpress blogs but in a different language.

In my experience, copilot is good at boilerplate and common patterns, but will not help you with the novel stuff (where it will predict the boilerplate and not the interesting transformation that you actually intend)

Once you've figured out an algorithm, you still need to code it. Thinking != coding. Coding is the easy and cheap part.

It’s a shame it doesn’t cover any language I use with the technical preview.

Something tells me copilot can be a big win for very verbose languages like C, where most code follows very specific structures.

What are your thoughts on the IP though? Aren't you worried that the code you're writing ends up being a huge legal ticking bomb?

Only if people are distributing the code.

You’d be surprised at how much code is “borrowed”