I now code for fun with AI because it can handle the boring parts. 80% of anything is mostly drudge. And while we can’t subsist on frosting alone, having assistant that can keep you in the zone is very rewarding.
Three major iterations from now this whole conversation will be quaint and everyone will have always thought this.
I use free RustRover for my open source work. I have not purchased a (new) license for my commercial work, because I haven't been getting as much value as it since my flow has switched to primarily agentic.
Mainly, they're pushing Junie and it just isn't that good or compelling, when faced off against the competition.
The key thing for me is that I think they had an opportunity here to really rethink how LLMs could interact with an editor since they potentially controlled both the editor and the LLM interaction. But they just implemented another chat-based interaction model with some bells and whistles, and also were late getting it out really, and what they delivered seemed a bit meh.
I was hoping for something that worked more closely inside the editing process, inline in the code, not just completions and then an agentic log alongside.
I also don't like that I can't seem to get it to work with 3rd party LLM providers, really. It seems to allow specifying an OpenAI API compatible endpoint, but it's janky and doesn't seem to allow me to refresh and manage the list of models properly?
It just still seems half-baked.
I love Opus and I am a heavy CC user now, but I don't like that Claude Code is taking me out of my IDE, away from hands on with the code, and out of my editing process.And I don't like how it tries to take over and how weak its review flow is. I end up almost always with surprises during my review process, despite my finding the quality of its code and analysis quite good. To me there was a real chance here for a company like JetBrains to show its worth in applying AI in a more sensible way than Anthropic has.
VSCode and Zed have no appeal to me though. I've mostly gone back to emacs.
In the meantime, their IDEs themselves feel a bit stalled in terms of advancement. And they've always suffered from performance problems since I started using them over 20 ago.
> I have not purchased a (new) license for my commercial work, because I haven't been getting as much value as it since my flow has switched to primarily agentic.
I still buy a personal Ultimate license because I want to see them succeed even if like 80% of my time is spent either in a CLI or Visual Studio Code (for quicker startup and edits), a bit unfortunate that Fleet never got to be really good but oh well.
Over the last two decades I've given them quite a bit a money on personal subscriptions, and indirectly a lot more through employer purchases on my behalf.
I dislike VSCode very much, but I do think the foundational pieces of the JetBrain's IDEs are starting to show their age.
If context disambiguates, then you have to use attention which is even more resource intensive.
You want to be as state free as possible. Your tokenizer should match your vocab and be unambiguous. I think your goal is sound, but golfing for the wrong metric.
Most of C++ programs written before P0593R6 depended on implementation behaviour, and were graciously allowed to not be undefined behaviour just 5 years ago. C++ as a language standard is mostly irrelevant, what one should care about is what the compiler authors consider valid code.
You have to rely on implementation for anything to do with what happens to memory after it is freed, or really almost anything to do with actual bytes in RAM.
The default case should be the safe correct one, even if it “breaks” backward compatibility. Without it, we will forever be saddled with the design mistakes of the past.
Three major iterations from now this whole conversation will be quaint and everyone will have always thought this.