Everyone talks badly about Cursor and it is kinda a piece of junk, but no, there's nothing that has the features of: being able to see agent diffs in an editor, seeing diffs inline in chat, be able to click them to jump to the code, and being able to click old chat messages to edit/fork them.
Those are basically my only requirements, and it feels like I've tried everything and they're all everything only has 1 of those features. Zed is the closest, it technically has those features, they're just buggy and have provider specific quirks.
So I'm stuck on Cursor until Anthropic invents IDE technology, or at least VS Code wrapper technology.
Jetbrains IDEs have AI support with all the things you've described, and in a more polished experience that requires significantly less maintenance and tuning. It does that while affording an actual IDE experience that works well for supported languages/projects out of the box, without the need to constantly tune plugins and experience jank misaligned UX that seems to be the norm for VSCode and derivatives.
No association with Jetbrains, and despite having a license, don't even use their AI support much myself (mostly using CC, with IDE integration for diff viewing). But if you haven't tried it recently, probably worth a revisit if you're open to Jetbrains products.
I hope their models improve. I used Junie when it first came out and it was okay but unreliable. I use Cursor with composer right now and I never have any issues. I sure do miss using PyCharm though.
Sounds really minor, but was actually a big contributor to me canceling and switching. The VS Code extension has a morphing spinner thing that rapidly switches between these little catch phrases. It drives me crazy, and I end up covering it up with my right click menu so I can read the actual thinking tokens without that attention vampire distracting me.
And of course they recently turned off all third party harness support for the subscription, so you're just forced to watch it and any other stuff they randomly decide to add, or pay thousands of dollars.
I used Gemini CLI for a while because it was free to me. The primary reason I stopped was because it wasn't very good, but their "thinking summaries" didn't help matters. They were model generated and just said things to the effect of "I'm thinking very hard about how to solve this problem" and "I'm laser-focused on the user objective". So I feel you: small things like this make a big difference to usability.
(They were against ToS before (might still be?), and people were having their Anthropic accounts banned. Actually charging people money for the tokens they're using seems like a much more sensible move.)
Yes, but I got a subscription because I was tired of alt+tabbing to the Cursor spending dashboard between prompts to make sure I wasn't over spending.
I'm ok if they slow me down for a few hours during peak usage. But getting cut off for 20+ days because I'm not thinking about the prompt cache for a bit makes a subscription feel pretty useless.
I was using it with Zed before, because I guess I'm one of the only programmers who doesn't just full vibe, which seem to mean I'm not the target customer for a lot of these companies who seem to be going all in on the terminal interfaces.
I've gone back to Cursor auto the last few weeks, it hasn't been too bad actually, I haven't managed to run out of the $20/mo plan yet.
> The way it is now, I can modify web sites using extensions
This isn't related too directly to WASM, what you want is DOM rendering only, you would theoretically reject canvas and WebGL rendering I imagine. But you could create DOM nodes with WASM. The only difference is that WASM is not as easy to decompile, but I can't imagine you're really unminifiying and patching Javascript are you?
Yes, I disabled WebGL many years ago (and Flash many years before that) when I was running Google Chrome. These months, I run Trivalent, which has it and WebGPU disabled by default.
I'm not a web dev, so maybe directing my hatred and resentment at wasm like I did in my first comment is a mistake. I don't like the idea of a site that draws its whole UI to a canvas (for reasons you can probably understand) and I have been assuming that that is impractical in just Javascript and that in practice, wasm is needed for that.
According to one of those services that gives fast answers to questions, Vanadium (the browser of the GrapheneOS project, which I also trust to give security recommendations) has wasm enabled, but that is a new development. Before late 2025, wasm worked only when JavaScript JIT was enabled, and the default was to have it disabled, which is how most users left it. It was possible for the user to enable it only on a few sites chosen by the user (per-site configurability).
I did not mean to broadcast misinformation, and will be more careful in the future. I do know that when the web gets new capabilites to make it a better application-delivery platform, my experience of the web strongly tends to get worse. The introduction of HTML5 and other technologies circa 2006 for example was a very salient example of that.
It might be that this is common with new tech, I'm too young to have grown up in the early concert scene. But with video games the curve was similar. People would show up just to see the tech and how much stuff people could put on the screen, It's only pretty recently that part has started getting boring.
I'd imagine similarly there were points in time where people who go to concerts just to see the electric guitars and lighting setups.
> No, nothing deserves this constant whining and crying day in and day out.
Why even try an start a conversation with that attitude? Wayland doesn't get nearly as much hate as Windows, Chrome, or iOS. But I guess literally nothing is worth writing an article that has the word "fuck" in it 7 times, because that crosses some kind of ultimate line?
Does it though? Unless all countries unify their laws regarding this matter it will fail in the same way that blacklist filtering does.
Also I'm not convinced that borrowing a device presents a new or different failure mode. Children could always obtain physical contraband from their friends so nothing has changed here.
it solves the problem of it being too trivial for a 12 year old to access content which at best is quite problematic and at worst outright traumatizing
as in, the same reason we have laws that a clerk glances at the age on you id if you look young and buy alcohol but your parent are still allowed to let you drink with them if they think its right (or what a 16+ movie with them etc. etc.)
this is also why it really shouldn't be anything much more fancy then parent controls checking min age of content locally / indication of age for feed fetching. Everything else is disproportional (unrelated from all the other issue it might have).
What kind of experience you have is about what kinda of developer you are. If you're the kinda programmer who wants to use all the newest versions of stuff because you think it'll be better, then you'll be in an endless quagmire of hitting limitations.
Most web programmers fall into that bucket for example. If you're the type to recoil at XMLHttpRequest, reaching to fetch or other even newer stuff. Then you'll balk at Win32 and be in a never ending pit of new Windows technology. I'd argue this is true of basically all new software. It's worth starting with whatever the oldest most compatible version of your target and ignoring the advertising and hype.
Those are basically my only requirements, and it feels like I've tried everything and they're all everything only has 1 of those features. Zed is the closest, it technically has those features, they're just buggy and have provider specific quirks.
So I'm stuck on Cursor until Anthropic invents IDE technology, or at least VS Code wrapper technology.
reply