Would be curious to see if anyone find it really useful. I've tried both Copilot and Codewhisper (Amazon Q now) before, wasn't impressed and uninstalled both. Just tried Q in VSCode again, I can't figure out how to ask questions relevant to the specific workspace that's useful to me. It seems like a bolt-on chat interface to your IDE with a bad UX. Feels like even "clippy" was more useful back in the day...
I tried out Copilot Workspaces before they fixed the waitlist access check yesterday and it seems to work a lot better by running a multistep process and allowing the user to incrementally modify the plan and rerun code generation.
The UI is similar to the code review interface except the file list on the left is generated from a plan and there's a bullet point list for each file of changes the plan generates. It enables a REPL loop where the AI code gens, the user tests the changes, then updates the file plans and reruns code generation again, creating and adding files as necessary. The end result is a PR with generated description or a commit direct to main.
I'm excited for this next wave of AI coding agents but Amazon seems to have rushed this into production
You can almost feel bad for VCs who think that their little startups will compete in the productivity space.
Amazon, Microsoft and Apple remove all enterprise barriers to entry, no startup can even remotely compete with this. They can take your ideas and implement them far faster than previously possible, why use some ambiguous startup when you can just wait a year for the Google integrated solution.
Combine that with Google and Apple's hardware dominance, companies like Rabbit and Humane are toast. They will make an app or hardware that out competes in a year. "Teenage Engineering" is cool and all, but a vibrant orange body isn't going to compete with a vertically integrated organization with true AI resources.
It's just momentum at this point. They don't even have to play any of the traditional anti-trust / monopoly games that companies of yore did. Look at AWS and the Elasticsearch situation. Amazon didn't really do anything other than take an open source product, freely distributed, and run it as a service and profit from it. We can debate the morals of it, but it's a far cry from being proactively anti-competitive.
Always makes me chuckle when someone complains about an app updating automatically. If you've taken some kind of special steps to keep an app from updating and it still does it, that's one thing. But it's the year 2024, automatic software updates are so common at this point, it just makes me think "what rock have you been living under?"
And here we're talking about an AI project... These products are so new, of course they're updating frequently and automatically. I just don't understand this complaint.
