RU version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
75% Positive
Analyzed from 3973 words in the discussion.
Trending Topics
#code#ide#jetbrains#still#using#don#more#air#codex#less

Discussion (76 Comments)Read Original on HackerNews
I want them to succeed, but can't see how they can win in this agentic world, where people are barely opening their IDEs, and living in agents terminal whole day and from time to time opening a PR to get a review
The volume of code is only increasing. Problems that used to be solved with a few lines (or even removing lines) are now solved with changes across 10 different files.
My IDE is invaluable for me when trying to navigate this stuff. I am completely convinced that people reviewing LLM code only via PR diffs are consistently missing massive systemic issues. You *need* to review changes in context of the surrounding code.
And doing this without an IDE is just making your life harder for no reason.
We have put a lot of thought into how we can add value for the workflow you just described. Here's the way I think about it: FSD for a car. Can you imagine trying to sell a car without a steering wheel? I still want to code, I still want the deterministic side, even in cases where I'm letting the machine do the work.
That's a small subset of the functionality you would need if you're actually authoring code. So the IDE maybe be more valuable, but the feature set you need is actually much smaller and can probably be redesigned given your narrow workflow.
Is this accurate?
Just some important things off the top of my head that I use daily:
* Instantly jumping between definitions and usages
* Folding and unfolding code blocks
* Quick overview of structures in files
* Database access, so I can browse the data and the code at the same time
Also, sometimes I just want to quickly refactor/rename some variable across all its usages or whatever. It's just quicker to do it in the IDE with a simple keyboard shortcut, rather than prompting an agent "rename oldName to newName".
Unless you are blindly vibe coding everything without an IDE to help navigate of what is being generated to reviewing the output, working would be hellish.
And if you are blindly vibe coding everything, I am just glad I don't have to work with you. While LLMs mostly speed me up, they make serious mistakes often enough that a review is necessary.
I have opened an IDE for very very few things in the last 9 months or so. Im still renewing a license at this point mostly because I like JetBrains the company and it's not a financial burden but they are in a bad place.
After using Air in PyCharm, it's some good stuff. It's re-imagined for this hybrid world. But my question for you, honest question: do you think you still want to look at code? How about write code? If so, what are some things you'd do, if you were in charge of our IDEs?
But there's still a group that needs to own the result, who still read code and write code. Folks who still believe in developers and development. This group might not be loud in SV, but they are big out in the world.
I'm a Python advocate at JetBrains and our team runs into folks like this all the time.
I've been enjoying using Air inside the IDE as a way to get the acceleration without giving up coding. I get the speed side from the agent and the trust side from the deterministic IDE.
Yes, we're writing less code, but the job of "a programmer" has always been about so much more than _writing_ code. It's about code reviews, QA, debugging, discovery, and maintenance; much more than the "writing" part. Anyone with production code will agree, I think: the writing part is the easy part. That's where I still very much prefer a proper IDE over a text editor or terminal. I want easy code navigation, I want proper static analysis without relying or waiting on third party tools, I want a visual overview of changes that happened. I want to stay in charge of whatever is writing my code. On top of that, I want my agents to have access to the tools that have made me the most productive developer for years.
Curious about your thoughts?
Of course, but agents are also opening up new possibilities to do these jobs.
For example, you can do quick first code review with agent, or you can ask agent to add couple of print statements and debug the code until it figures out the issue, also for discovery, you can do discovery with agents and generate nice output with the details you want (although not accurate sometimes)
As a JetBrains user myself, whose organization cancelled the IntelliJ license recently, I can attest things I am doing inside IntelliJ is getting less and less. I am primarily using IntelliJ for code navigation at the moment, which is still the best one
I’ll try out Air but I don’t have high hopes, my current workflows work great and I’m still not sold on what Air offers even after reading this post and the page about Air.
But I have been using their jetbrains remote system, and you can clearly see how incredibly high the RAM usage is on both server and client.
Personally I am also looking at the door, but not because of the resource usage… but because they keep putting resources into things which aren’t their core offering and it makes me wonder if they have run out of innovation in that area.
… then again, they did recently figure out how to make development on a Windows remote work… so I can keep using my linux machine while developing Windows software, so I think that earned a lot of goodwill from me.
I do feel however they have been neglecting anything non-AI for a while now. I in particular loved their auto complete, and with the new guesswork AI auto complete it's just not the same. I want deterministic behaviour from my IDE.
On the LLM side, I couldn't use the Anthropic subscription with their offerings, so I just use it from a harness outside the IDE, and switch to the IDE for review. This may not be JB's fault, but it still makes their offering useless to me.
I may be one of the few remaining but I also still program myself sometimes (I weigh it based on the task). The IDE has been pushing so much AI it has been getting in my way sometimes, and it is definitely using more resources for stuff I don't use.
I too am on the fence on whether I'll resume my subscription. Luckily for JB I dearly dislike VSCode's code navigation and interface, and would severely miss their debugging tools integration.
I'm happy about our Air launch because we're being AI "realists"...neither too much sunshine pumping nor too much skeptic. We're doubling down on developers and development, both when you type and when you don't.
On to the point..I can promise the PyCharm is doing some pretty massive non-AI stuff on the deterministic side. I think determinism is the best path to trusting the code generated by the box.
We tried to make this work, but unfortunately hit a hard stop with Anthropic: their current policies do not allow us to support this integration :c
We still hope to resolve this in the future
About the terminal, honest question...is that because you are looking at code less and less? Writing code less and less?
I know harnesses (and harness harnesses) have a long way to go and lots of improvements even without models getting “smarter”, I’m rooting for JetBrains but so far IDEA has been more of hindrance in the LLM-era. The CLI TUI’s have become the most important tool I have and the GUI versions haven’t kept pace.
I’d love to live in IDEA instead of the CLI but so far I’ve found that to be too limiting and not as adaptable to our rapidly changing field. Maybe Air will help with that, we will see.
I want something like herdr in IDEA, a way to monitor agents, smart worktree integration, easily visualize changes and use the power of the InteliJ brains to assist in coding (lint/checks/etc).
Right now my IDE gets more in my way than assists me in shipping code.
I don't think that there's a better alternative at the moment, and I get the need to pump out features to keep the revenue stream going, but I miss the slimmer versions
Their IDEs have been nosediving for years now in a way usually reserved to "has been acquired by private equity". But they have not been acquired by private equity as far as I can tell.
I'm writing this from my laptop, where each keypress in a .md file in WebStorm makes the fan spin up (not hyperbole).
What happened, JetBrains?
Most development was done in Russia (disregard tales sold to the West about them supposedly being a Czech company, they were Czech mostly in the name, real work happened elsewhere). Exited Russia in the beginning of 2022, leaving many talented people behind: not everyone wanted or could leave because of families, obligations, personal beliefs.
Remembering where most of JB's money was coming from, can't really say they had a choice.
The answer is more like the obvious one...our category is getting redefined, at hyper-speed, and all of the players are all over the map trying to sort this out.
I like what we're doing with JetBrains Air. We know what we bring to the table, who it's for, and we're doubling down on developers and development.
That said, CPU fan on Markdown is not cool. Want me to look through it with you?
Honestly not really.
I mean I am happy that there is some kind of response, but this is just damage control.
And, frankly, you do not need me to fix that. Of that I am certain.
I'm not running any weird setups or something out of the ordinary. If you actually test your software on a normal computer (think: random thinkpad with 8th gen intel cpu), running some random boring linux distribution (think: debian) you will run into these problems.
The bad experiences all so far have been smoke-test-level issues.
Or.. well. Product strategy. Not even bugs or performance issues at all.
__
But, yeah, you had to say something. I understand that, given your role as "developer advocate" (as per the HN account about section). This is your job after all.
But, honestly, sticking ones head in the sand and hoping that this passes might've been the strategically more wise move.
The problems your employer has cannot be fixed by one person taking their time and looking at an individual issue some other vocal guy on the web has. I think we both know that.
I'm sorry, genuinely.
The OP post feels like completely marketing department, no skin in the game. I'm afraid they are becoming Borland.
What else can one use?
Excluding VSCode and all those AI-first IDEs I mean. JetBrains' git features have been excellent. I have not yet seen them be reproduced anywhere, but, eventually, they will kill that classic UI plugin. :(
I find this setup works great for actually participating in the development. To understand what is happening and keep the mental model of what the project is about. Review in progress work in IntelliJ, use the Git, Database and REST(.http files) in the IDE as the agents generate the code.
I don't see a problem with this setup is it really that uncommon? Have people stopped using TOOLS completely? That said I don't have much interest in these JetBrains AI products, at least not currently.
DataGrip is seriously under-rated, IMO.
For a while I used Junie for small refactorings, and it generally does a good job, quite quickly. A couple of times I tried asking it for more complex things, and it didn't do well. I do find the UI to be a bit tricky, so it's quite possible I did something wrong or didn't add something to the context I was supposed to. Hopefully they sort out the "AI Chat" panel soon.
But now I use Codex/ChatGPT... and what it can do is frankly incredible. And it might just be me, but I do like having my AI chat UI completely separate from my IDE.
edit: Sorry; misread. No, and I am very confused by their diaspora of AI offerings!
They had the best IDE. Now they went all into AI, trying to compete on another people's field, and the cost of that is diminishing their main product. Do they really want to compete with Anthropic? Instead of that they could improve the other sides of IDE. Even with AI I have to review the code. Especially with AI. I need tools to check the diffs, I need to refactor it, I need to run it in different ways, see how it works, and so on. That's where IntelliJ could shine, not as AI tool.
I couldn't find how to change the mode without it trying to use Junie, or claude etc. very frustrating.
It's clearly existential for JetBrains, and it's revealing that the opening goes for the fear with "but it hasn’t changed what it costs to be wrong" while ignoring that this hasn't exactly been a major concern for most software people for a scarily long time, including JetBrains themselves.
I still love RustRover and PyCharm! Switching to anything else would be a big downgrade.
Side note: I am confused by the various JB LLM integrations. Air, Junie, at least 1 (maybe 2 more?) the IDEas have suggested I try.
About compared with Codex, we have some tricks up our sleeve that are actually valuable for the target market we're going after: folks that want to understand and own what they've done. Watch for the videos we'll be doing (and look for my shining face in the PyCharm channel.)
On the last point...yes, the downside of choice is choice.
It's not bundled with the IDEs but it's available on github
Two things that fell short for me:
1. No support for my Claude subscription
2. The git interface lags behind other JetBrains IDEs
About point 1: We tried to make this work, but unfortunately hit a hard stop with Anthropic: their current policies do not allow us to support this integration, and we were not able to negotiate an exception :c
We still hope that we will find an agreement here
- It sees very little investment ever since they introduced Rider.
- They give out VS Code one for free, yet the VS users are neglected.
- Touching code manually is outdated by agents anyway.
[0]: https://github.com/spockz/semantic-editor
1) Import of historical data from agents. I often look up past agent sessions and require search into them as a primary feature of the harness. I know for a fact that historical conversations are not encrypted for both Codex and Cursor on a local filesystem, so Intellij tool could import them into ai assistance plugin even before user is authenticated with either Cursor or Codex. There are few annoying things in search for both Cursor and Codex extensions, so having great search over past conversations could be a great introductory feature
2) Auth .. I am not sure about this one technically because I haven't looked myself into how agent auth is done for Cursor and Codex, but at least for Codex, their IDE extension for vscodium/cursor/zed/etc. is able to use existing authentication from the CLI codex tool, so I do not need to login into every new IDE I try Codex extension in. With Intellij Codex auth did not work at all for me.
3) Cursor authentication worked, though I needed second one for Intellij while being logged in with CLI, but the model reasoning level is not selectable from within ai assistant, one more deal breaker for me unfortunately (I found it stays like this for a long time: https://forum.cursor.com/t/intellij-cursor-acp-reasoning-lev...)