JetBrains Thinkrail
github.com
github.com
(100% AI according to Pangram btw)
Rejecting slop doesn't imply rejecting all AI-generated text wholesale.
It’s a marker that the project is likely to be low-effort slop, which may or may not just be abandoned at the deep of a hat.
There's a famous Jobs story in which he insisted that even the insides of the computers be made beautiful. Because that shows care. Now people are arguing that even the outsides can be as ugly as they want, who cares.
Then I’ll probably hear about it again from someone I trust. I don’t need to be the first in my circle to test if this one is different.
I can do it. Anyone can do it. Probably better for my/their own needs than someone else’s agent can.
The README is meant to communicate substance and intent. Without the latter it’s an overly-verbose landing page.
1. AI generated text is just hard to read and verbose, if you worked so hard on your docs/specs, why would you want your README to be unreadable?
2. There's so much garbage written with AI that I'm just going to assume yours also is. Would you sign up to a gym with broken windows? It could be the best gym ever, but I wouldn't count on it.
Skill issue, it’s easy for a guy like me
If it is blatant unfixed llmese, then it means that no effort whatsoever was put into making this text.
What JetBrains needs is nothing short of a revolutionary product, which they would need to sell with an excellent introduction.
Instead they phoned it in and pasted that slop:
> Once a GitHub PR is open it shows the CI checks and review decision, and lets you mark it ready, hand failing checks or a diverged branch to the agent, merge it with the repository's last-used method, reopen it, or delete the remote branch.
The answer is very short.
But given you dont know me, im going to guess you wont be foolish enough to try and guess especially considering there are at least 100 different flavours.
Software is even more complicated. How is any person even the smartest software type in the world or AI going to know all the exact details of your wish if nobody tells them exactly every painful detail ?
Conciseness and highlighting relevant points is much more important than word count. Machine generated readmes are anything but. Sorry you can’t tell the difference between that and human prose, you should try reading more human content.
This is a useful criticism.
Left to themselves, LLMs prefer writing that's really atrocious. e.g. The writing will try and make everything sound profound.
The other problem I've noticed is e.g. LLMs will write in stuff that's inappropriate for the content of the text. e.g. Writing out stuff that looks like a chat reply, in commentary or descriptions or whatever.
I'd distinguish, though, between "sloppy writing" & "LLM generated writing". I'd agree if you didn't put in the effort to check the writing is of high quality, then perhaps the other parts are also not high quality.
I don't think just because "AI" wrote it it's bad. I wouldn't prefer e.g. sloppy human writing over well-crafted LLM-written text.
This readme the main thing which sticks out is the "what you get" bullet points are rather dense/verbose for bullet points. But aside from that it seems fine.
During the preset testing, I created dozens of READMEs using agents. Although I can't say that any of them were perfect for me, most of them were good enough.
README is a very special kind of document. For small projects, it's often the only one that potential users will read. The README should explain what the product is, what problems it solves, how to get started, provide some examples, and explain the restrictions. It should cover all these topics in a concise way so that even readers who aren't used to read long texts can easily read through it. It's definitely up to human to make it clear and easy to understand.
I care whether the readme is any good, not who wrote it. If you haven't bothered to critique the readme and instead critique its suspected creator — something entirely in your head — what else have you not bothered to do?
> (100% AI according to Pangram btw)
So what? Who cares about Pangram? I certainly don't! You cannot detect AI — it's impossible. Perhaps it's just Kenyans?[0]
[0]: https://marcusolang.substack.com/p/im-kenyan-i-dont-write-li...
Well, good luck in professional development then. Love it or hate it, this is the way everything is moving.
If you care about these things you are either not the intended target or you are a hypocrite.
Yep. The "A $thing, $elaboration." has joined "$title. $thing, $past_verb." in my "this team didn't care enough to do a basic pass over the main page introducing their product" tells.
Thanks JetBrains, I assumed the app would assemble prompts behind my back, so I'm glad they clarified that.
If they bothered reading this that would have been removed. I understand smaller players... Vibe Coders, Solo projects, something on its initial commit (to be edited / cleaned up / improved).
But, from JetBrains? Bad sign for the industry, IMO. Is it that fucking hard to have a decent technical writer collect some some human-readable documentation? This just exudes lack of effort.
But I don't use it for AI assistant development, it's definitely meant for humans and not AI agents.
It's wild that a set of IDEs that are generally fairly good just completely fail in this basic workflow. I really wonder what went through the minds of the product owners and developers that implemented this.
Now my agents mainly write code under my direction and I review it either in the harness or on GitHub.
I hadn’t opened it in ages and when I did need an IDE something like Zed was more than sufficient.
I use it when I need to deeply understand a PR.
But I'll admit to keep my skills from atrophying, there are some projects of mine I don't touch with AI.
An IDE still has it's uses, and it's perfectly fine without AI. Agents and IDEs have never felt like something that should be combined in my opinion.
If I edit code I know what I want to edit. If I want AI to do it, I prompt an agent.
I just could not understand their AI strategy.
I know because I've tried practically all of their AI product offerings and not a single one feels coherent.
Hopefully, all these companies will go back to reason in a few years, when the bubble will burst. By bubble bursting, I don't mean that AI will disappear, but the nonsense and crazy money around it will.
While they are both "agentic development tools", it seems that Air is mostly concerned with managing multiple agents, whereas Thinkrail is about spec-first development.
And fleet was made to attract the VSCode generation, who they were starting to lose new user momentum to. But VSCode is no longer the biggest threat.
Okay, but what stops any of that for happening for any of the new things since then? To me, a large part of the appeal of Fleet was that it wasn't the entire IDE; adding a new skin to something that feels much too heavyweight for me does not resolve the fundamental problems I had with it.
I actually think they could do something more radical than Fleet today after seeing the (alpha, but impressive in use) ArtCraft apps, and translations like Bun. They could embrace still being the best traditional IDE, translating their trademark intelligence, with a lot of the heaviness removed. The thing that struck me about the ArtCraft apps was how fast and light their interfaces felt compared to the originals.
I suppose they were in a tough spot regardless though. They started developing it before the AI age, so they would have to pivot either way.
That doesn't exactly inspire confidence that this product will stick around.
I liked their products. Also, personally I am not seeing next level devexp yet, other than just using my agents for everything
They'd honestly do well just to pick one of the open harnesses, aquihire their team and start from their
The only reason I keep Rubymine open these days is out of habit and I still like using it's git UI but there's less reason to do that every day. It's also a total RAM hog. JetBrains - please, make a lightweight, chat first IDE like everyone else is doing.
Also, reading through their "SPECS".... https://github.com/JetBrains/thinkrail/blob/d299f20d2ba014f3... or https://github.com/JetBrains/thinkrail/blob/d299f20d2ba014f3...
How is this llm-vomit "specs that are ground truth" etc.?
(That's also why there are so many of them: It just isn't that hard, everyone feels like a genius when they figure it out, and it's a great way to resume-build in the AI era).
We are due for another innovator that adds a net new, valuable facet to the development experience soon.
Since conflict resolution these days mostly boils down to “hey LLM, resolve conflicts” this is much nicer.
Also jj tracks every change to the repo so undo works much better and is more readable than reflog
Not having to stage changes in lieu of them automatically getting picked up was a bit of a learning curve for me, but now that I've gotten used to it I like it a lot better and I don't think I could go back. The equivalent of the reflog pretty much always has my changes in it if I accidentally lose them without manually saving due to the snapshotting, and I have no need for a stash because commits and branches are essentially just recording a checkpoint rather than being things that feel "heavyweight".
As an added bonus, dealing with conflicts is a lot less annoying because each commit records its conflicts separately, so fixing them doesn't require doing a stateful pipeline of changes in a big rebase; I can just do them piecemeal, in any order I want, and even just check out other stuff and work on them before coming back later if I feel like it.
I was "that guy" who would sometimes have coworkers come for help with git problems (https://xkcd.com/1597/ alt text). I've forgotten most of that knowledge (and all of that muscle memory) and didn't have to learn nearly as much to replace it with the ability to do a lot more with a lot fewer mistakes.
I guess they'll just copy submodules too. Kind of feels like there's little point using it if it's just going to copy Git's mistakes.
it is built, though, that the Git backend can be swapped for another backend.
I'm not sure where you're getting two production backends from. I guess you're referring to the Google internal one that nobody can use?
> There is currently only one production-ready builtin commit backend: the Git backend. <omitted> Google also has its own cloud-based backend.
https://docs.jj-vcs.dev/latest/glossary/?utm_source=chatgpt....
No, git-branchless is a wrapper around Git. jj is an independent source control system with git compatibility. jj can, and does, function entirely without git.
> I'm not sure where you're getting two production backends from. I guess you're referring to the Google internal one that nobody can use?
Lots of people within Google use it!
If you work at Google, jj can and does function without Git.
If you do not work at Google, jj is a Git wrapper.
I don't think harness like Claude Code or Codex support jj very well for working in parallel
BTW, what's "InnovationHub" it's mentioned but I can't find a good link or explanation.
Overall it just looks like an experimental direction for IDE dev. I'd prefer they leaned into native dev like Zed though.
I'd also caution against saying things like llms are doing most of the work I don't think that's true. And where it is true it shouldn't be. These things are still new tech and they need a lot of hand holding and oversight still.
To be clear, it clicks things to do things like test software. If you build an API, you're not testing if the clicking actually works.
EDIT: found it at https://thinkrail.ai/blog/thinkrail-sdd/
---
Also... why bun?! I just finished purging it from all my systems, ha! It'd be cool to have plain pnpm support.
And probably something to understand what your agents are doing and why. With which reasoning.
Otherwise also stay a damn good IDE. We still need that. My agents are floundering on our bigger codebases and only produce warts.
I've been using Intellij IDEA lately.
I have pycharm, phpstorm, goland still installed and use them every now and then. I, however, spend a lot more time in claude code in the cli and main I'm reviewing.
I go to the specific ide when I need to debug heavily something or when I'm starting out to create a base. I don't like the structure that claude code sometimes comes up with, so I like starting it out and then it follows the pattern.
So I’m willing to give it a try.
The versioned and linked spec feature sounds somewhat interesting though.
There aren't enough digital french cleat systems.
The true benefit of a French cleat isn't storage or organizing the way a fiddly pegboard and hanger approach uses, it's the ability to move all tools for a specific project onto a single rail without having to fiddle around, reducing friction for engaging and re-engaging with a project.
I tried Air before and found it underwhelming. I tried using it around Pi through ADB, but it didn't any benefit around using Pi purely.
JetBrains, explain concisely why this isn't written in C/C++/Rust?
I’ve been using Orca as my agent orchestrator du jour - but its editor experience is just pathetic. Really what I want is Zed integrated into a similar all-in-one platform like Orca (but more minimal - Orca is a total slopshow with way too many features)
This is exactly what I was missing
Edit: oh shit I am on the cancel screen and reminded I also used ReSharper. Best of luck jetbrains I have given you a lot of money figure your shit out and I would happily return.
Migrating my screenwriting software[0] from OpenTUI to Roc thought me what were once rough edges that take a lot of time are now just a prompt away from a solution.
It now uses 10x less RAM, bundle is half the size, and my initial implementation is 700-800 fps for scrolling and 200 fps for writing.
Granted, a TUI is less complex than a full-blown GUI, but I built a Roc Iced platform just as easily that abstracted Iced flux away
Even if I wanted not to code it I couldn't. LLMs are still incapable of creating code up to any decent standard.
Also, while I do the get the joy of programming, we sometimes forget to focus on the user. You being happy to have typed the whole thing once, and have it run everywhere via the magic of browsers may not be the best strategy if this means your user's lap will be overheating.
In the end as much as I like coding I would prefer my users' experience to be the best it can be. LLM assisted code delivers this better and faster than hand-typing it all (which in turn is better than completely vibecoding it)
JetBrains tools are heavier and can take a few seconds to launch, but they also have some of the most responsive typing out there. They did some good work on zero-latency typing modes when that was a big topic and they were very good at typing latency relative to most editors.
They will never be the right tool for the personality type that gets angry when their IDE takes a few seconds to launch at the beginning of the day or when an application takes more than 1GB of RAM, but I am not that type of person so I enjoy them.
I think the TUI people are well served by vim or emacs and should just stay there and be happy.
The rest of your post feels like an injected ad for your project underneath a topic where it's not relevant
It also has nothing to do with TUI vs. GUI, since my comment addressed both (anecdotally).
If anything, your mentioning of their performance work is exactly my point.