Kite is saying farewell and open-sourcing its code
151–160 of 547 posts
Re: Kite is saying farewell and open-sourcing its code
#152"Our diagnosis is that individual developers do not pay for tools. Their manager might, but engineering managers only want to pay for discrete new capabilities, i.e. making their developers 18% faster when writing code did not resonate strongly enough." I never used Kite, but I've tried Github Copilot twice, and found it marginal at best (and distracting at worst - which is why I turned it off both times). If Kite wa…
My experience with copilot has been very different. It easily pays for itself, and getting my employer (seed stage startup) to spring for it for the entire team was an easy sell. Yeah it's pretty dumb most of the time. But I know that, and I don't use code from it without carefully checking it out and modifying it. But it's still a huge help. Just the time saved writing tests alone pays for it. And I've had a few spo…
This, so much. My code since using Copilot is easily ten times better tested than it was before, and I wasn't especially lazy when it comes to testing.
Given 1-2 hand-written unit tests, Copilot can start filling in test bodies that correctly test what's described in the function name. When I can't think of any more edge cases, I'll go prompt it with one more @Test annotation (or equivalent in another language) and it will frequently come up with edge cases that I didn't even think of and write a test that tests that edge case.
(One great part about this use case for those who are a little antsy about the copyright question is that you can be pretty darn confident that you're not running a risk of accidental copyright violation. I write the actual business logic by hand, which means copilot is generating tests that only interact with an API that I wrote.)
Re: Kite is saying farewell and open-sourcing its code
#153Earlier quoted context omitted.
My experience with copilot has been very different. It easily pays for itself, and getting my employer (seed stage startup) to spring for it for the entire team was an easy sell. Yeah it's pretty dumb most of the time. But I know that, and I don't use code from it without carefully checking it out and modifying it. But it's still a huge help. Just the time saved writing tests alone pays for it. And I've had a few spo…
Kite has been around for a lot longer, if anything Copilot was Github copying them
Re: Kite is saying farewell and open-sourcing its code
#154"Our diagnosis is that individual developers do not pay for tools. Their manager might, but engineering managers only want to pay for discrete new capabilities, i.e. making their developers 18% faster when writing code did not resonate strongly enough." I never used Kite, but I've tried Github Copilot twice, and found it marginal at best (and distracting at worst - which is why I turned it off both times). If Kite wa…
A few tools that I put on the company card when I worked at a Big Tech Co as an IC:
* DataGrip (Jet brains)
* Colab Pro (Google)
* Postman Pro
These were all small $ enough where I didn't need to justify the expense. It was just assumed that if I thought the tool was worth the $, it was.
For more expensive purchasing decisions, there was a longer purchasing/approval process. But the expense would have to be 5-6 figures per year before hitting this barrier.
Re: Kite is saying farewell and open-sourcing its code
#155Re: Kite is saying farewell and open-sourcing its code
#156This is a very self-serving recap: "we were too early and we're still too early and Copilot proves it because its not 10x": it is 10x, sorry.
Now whether or not that's due to the fact that copilot had the financial resources to train a significantly superior ML model is another question, but throwing shade at copilot is a fairly transparent move.
Re: Kite is saying farewell and open-sourcing its code
#157"Our diagnosis is that individual developers do not pay for tools. Their manager might, but engineering managers only want to pay for discrete new capabilities, i.e. making their developers 18% faster when writing code did not resonate strongly enough." I never used Kite, but I've tried Github Copilot twice, and found it marginal at best (and distracting at worst - which is why I turned it off both times). If Kite wa…
I paid for intellij - damned near the entire architecture team where I worked had a copy, and the company sure as shit wasn't the one paying for it. (I eventually stopped subscribing, in part because they were too slow distancing themselves from Russia, in part because of their movement away from open source with their newer tooling.) Developers will pay for software, if the value proposition is there.
I'd cut them some slack here. They had to get their team out of there first—with the way Putin is running things, they sure as hell couldn't announce they were leaving Russia until everyone who was going to follow them was out of there.
On the day of the invasion they tweeted a statement condemning the attack, and within two weeks announced they were leaving Russia.
https://twitter.com/jetbrains/status/1496786254494670851?lan...
https://blog.jetbrains.com/blog/2022/03/11/jetbrains-stateme...
Re: Kite is saying farewell and open-sourcing its code
#158I am very impressed and happy to see the open-sourcing of their code like this. I often find myself thinking about how much human knowledge and effort disappears when a company shutters and all of their documents, code, etc go with them.
Re: Kite is saying farewell and open-sourcing its code
#159> it fell short of the 10× improvement required to break through because today’s state of the art for ML on code is not good enough. You can see this in Github Copilot, which is built by Github in collaboration with Open AI. As of late 2022, Copilot has a number of issues preventing it from being widely adopted. True, AI assisted coding does not deliver 10x. But as a user of another AI assistant, I feel that it gives…
Which one do you use?
Tabnine for JetBrains CLion. It works with Rust and several other languages.