So basically copilot is a great excel corner-drag-fill-thing
Working with these LLMs is like managing a team of brilliant high school interns. They're brilliant, but they're also teenagers. Manage them wisely and they'll multiply your abilities (at least within some narrow domain). Let them walk all over you and they'll write garbage faster than you can pick it up.
Co pilot has only been good for me as a small intellisense snippet engine. Its been dead wrong when I let it write more than 50 characters honestly.
Love this so much, been using Co-Pilot and had a few moments where I'm like "No wait, that's a bug!" The biggest difference between me and you though is that when I used Co-Pilot, it had actually wrote code for an edge-case and I created a bug by trying to correct it 😂
Copilot has really improved my scope in terms of backend programming. All helper functions I need are auto generated, even the ones I didn't know I needed. Also in terms of translation of a requirement I copied somewhere or a json I need to manually write
I extremely rarely let copilot write multiple lines of code, but as single-line automcomplete iv found it incredible
I find that it's good for rewriting existing code. E.g. a couple days ago during a Scala code review, I saw someone had a long chain of matching on Optional values, and I wrote `// instead we use a for-comprehension`, and Copilot perfectly rewrote the code as a for-comprehension.
Copilot is such a complete tool, not only writes code for you, also writes bugs for you! Freaking awesome!
The summary is my exact experience of copilot. For languages I consider myself competent in, I love copilot. It helps smooth out the boilerplate and I generally can provide it with enough context to guess what I'm up to. For languages I'm learning, I generally turn it off and debug interactively with gpt
My experience exactly after 4 months. My take is that you code faster in the beginning but the gain becomes less and less. Coding is much more tiring because you don't have to write the stuff that require less thought. You're always working in the hard bits. It won't replace good programmers. It will reduce the number of good programmers because beginners will rely on it.
One other thing that Copilot is really good is generating code for an API that you're unfamiliar with. I had to do some stripe scripts to check that all invoices were generated correctly. It would take like 30 minutes of me looking at the documentation, working through all that text, instead Copilot generated the code for me in 3 minutes. But it was still important that I knew some details on how the API worked beforehand, so I had the opportunity to fix some of the bugs before they happened. If I hadn't knew the Stripe API details beforehand, maybe it would take like 10 minutes. Still better than 30.
Honestly the best thing copilot has done for me is speeding up writing unit tests Not only will it take out any of the boiler plate around, for example, mounting components, but also, if you give a good enough name to your test case and it is a simple case, it easily create it for you
Exactly my experience as well. I love copilot for taking over the boring work for me, so I can spend my time actually tackling the difficult stuff. Writing boilerplate, filling translation files, mapping data from one structure into another and interestingly documenting my code are now all things I spend less time on, since copilot usually gets these things done for me.
Copilot has been an *insane* boost to my productivity in all ways. Just a matter of learning what it's good at and where it falls short. Easily the best dev tool I've ever used.
7:19 lmao 😂 felt that moment
Thank you for your honest and earnest contributions to the work. Keep it up, stay genuine and always grateful. Mahalo
Great summary. It kind of reflects my thoughts about Copilot as well! 🎉
Ahhhhhh WOW the quicksort example is so perfect and perfectly points out the problem with these a.i. tools.
1:14 the "Jesus take the wheel" was spot on 😂😂😂😂
@ThePrimeagen