Aider remains to me one of the places where innovation happens and it seems to end up in other places. Their new feature to architect with o1 and then code with sonnet is pretty trippy.
Only can run so many IDEs at a time though.
It's great!
aider --sonnet --no-auto-commits --cache-prompts --no-stream --cache-keepalive-pings 5 --no-suggest-shell-commands`
For me it's still the cleanest editor.
VS Code is way too cluttered to be my daily driver for basic editing.
If not, it has some ai support.
So far I've had all the vscode extensions just work in cursor (including devcontainers, docker, etc.) I hope it continues like this, as breaking extensions is something that would take away from the usefulness of cursor.
My hunch says that IDEA should be worried a lot. If I am on the edge evaluating other tools because of AI assisted programming, lot of others would be doing that too
IDEA has "AI Assistant"[^0]. Is it not usable for you (I might have missed your comment mentioning it)?
None of these points seem to apply..
They're still selling their yearly subscription even if they can't upsell me on an AI subscription
I find a lot of teams are so focused on their vision that they fail to integrate their tool into my workflow. So I don’t use them at all.
That’s fine for art, but I don’t need opinionated tools.
What I want in a product comes from customer interviews. It’s not “my opinion” other than perhaps our team’s interpretation of customer requests. A customer can want certain pain points addressed and have friction to move to a particular solution at the same time.
Or does wanting a product that meets customer needs too opinionated?
There is also https://codeium.com/jetbrains_tutorial I have been using the free tier of it for half a year, and quite like it.
Supermaven has https://plugins.jetbrains.com/plugin/23893-supermaven also good free tier. (Although they recently got investment to make their own editor.)
They are executed locally, and you can find the local model files if you look hard enough (2).
(AI Assistant is different, costs extra and runs over the network; but you dont have to use it)
[1] - https://www.jetbrains.com/help/idea/full-line-code-completio... [2] - https://gist.github.com/WarningImHack3r/2a38bb66d69fb5e7acd8...
It helps find relevant content to copy to your clipboard (or just copies all files in the repo, with exclusions like gitignore attended to) so you can paste everything into Claude. With the large context sizes, I’ve found that I get way better answers / code edits by dumping as much context as possible (and just starting a new chat with each question).
It’s funny, Anthropic is surely losing money on me from this, and I use gpt-mini via api to compute the relevancy ratings, so OpenAI is making money off me, despite having (in my opinion) an inferior coding LLM / UI.
- Mine prepends the result with the output of running `tree -I node_modules --noreport` before any other content. This informs the LLM of the structure of the project, which leads to other insights like it will know which frameworks and paradigms your project uses without you needing to explain that stuff. - Mine prepends the contents of each included file with “Contents of relative/path/to/file/from/root/of/project/filename.ts:” to reinforce the context and the file’s position in the tree.
It started out as just predictive text, but now it has a chatbot window that you can access GPT, Claude, etc. from, as well as their own model which has better assurances about code privacy.
Forgot to mention killer feature - droping links to docs automatically fetches them in aider which helps with grounding for specific tasks
My project has well over half a million lines of code. I'm using an IDE (in my case Qt Creator) for a reason. I'd love to get help from an LLM but CLI or external browser windows just aren't the way. The overhead of copy/paste and lack of context is a deal breaker unfortunately.
In case I'm missing something, please let me know. I'm always happy to learn.
- want to use your particular ide which does not have the llm plugin.
- don't want to use any of several ide's that support several llm's using a picker.
- don't want to use copy/paste to a web browser or other tool
- don't want to use 2 ide's at the same time if 1 of them is not your favorite
I would settle for the 3rd or 4th option, both work very well for me.
Anyway, I don't use them either. I prefer to use ChatGPT and Claude directly.
Good at integrating AI into a text editor != Good at building an IDE.
I worry about the ability for some of these VSCode forks to actually maintain a fork and again, I greatly prefer the power of IDEA. I’ll switch if it becomes necessary, but right now the lack of deep AI integration is not compelling enough to switch since I still have ways of using AI directly (and I have Copilot).
I'm a long term vim user. I find all the IDE stuff distracting and noisy. With AI makes it even more noisy. I'm guessing the new generation will just be better at using it. Similar to how we got good at "googling stuff".
It’s a mistake to assume that there will be 100% correlation between the past and future, but it’s probably as bad of a mistake to assume 0% correlation. (Obviously dependant on exactly what you are looking at).
So while the odds at the extremes are low, they cannot be ignored.
No one can predict the future. But those that assume tomorrow will be like today are - per history - going to be fatally wrong eventually.
Each circumstance is different. Sometimes the past is a good guide to the future – even for the notoriously unpredictable British weather apparently you can get a seventy percent success rate (by some measure) by predicting that tomorrows weather will be the same as todays. Sometimes it is not - the history of an ideal roulette wheel should offer no insights into future numbers.
The key is of course to act in accordance with the probability, risk and reward.
So you're just out here wasting my time
See you
Vim has been around since the Stone Age.
Jokes aside, I don’t really see why ai tools need new editors vs plugins EXCEPT that they don’t want to have to compete with Microsoft’s first party AI offerings in vscode.
It’s just a strategy for lock-in.
An exception may be like zed, which provides a lot of features besides AI integration which require a new editor.
Vi and vim were never products sold for a profit.
Who was saying what? And what were they saying?
EDIT: ah I think I understand now.
The thing is, I don’t see any advantage to having AI built into the editor vs having a plug-in. Aider.vim is pretty great, for example.
The only reason to have a dedicated editor is a retention/lock in tactic.
The editor handles the human to text file interface, handling key inputs, rendering, managing LSPs, providing hooks to plugins, etc. AI coding assistants kind of sits next to sits it just handles generating text.
It’s why many of these editors just fork vscode. All the hard work is already done, they just add lock in as far as I can tell.
Again, zed is an exception in this pack bc of its CRDT and cooperative features. Those are not things you can easily add on to an existing editor.
Really wouldn't recommend this in its current state.
I think it has to do with Cursor's much better custom small models for code search/replace, but can't be sure.
Instead of putting the AI in your IDEA, put it in your git repo:
Zed is lightening fast.
Wish it had more features.
Ironically, for creating that, these new age code editor startups would probably have more luck with neovim and it's extensive lua API rather than with vs code. (Of course, the idea with using a vs code fork is about capturing the market share it has).
For this, either GitHub Copilot or their own AI plugin seem to work nicely.
It's kind of unfortunate because creating new plugins for the JetBrains IDEs has a learning curve: https://plugins.jetbrains.com/docs/intellij/developing-plugi...
Because of this, and the fact that every additional IDE/tool you have to support also means similar development work, most companies out there will probably lean in the direction of either a web based UI, a CLI, or their own spin of VS Code or something similar.
I'll use Continue when a chat is all I want to generate some code/script to copy paste in. When I need to prepare a bigger input I'll use the CLI tool in Sophia (sophia.dev) to generate the response.
I use Aider sometimes, less so lately, although it has caught up with some features in Sophia (which builds on top of Aider), being able to compile, and lint, and separating design from the implementation LLM call. With Aider you have to manually add/drop files from the context, which is good for having precise control over which files are included.
I use the code agent in Sophia to build itself a fair bit. It has its own file selection agent, and also a review agent which helps a lot with fixing issues on the initial generated changes.
https://plugins.jetbrains.com/plugin/20540-codeium-ai-autoco...
Here's an example of something I recently added (an inline inspector), that my main competitor (VS Code) said wasn't possible with the VS Code APIs: https://cursive-ide.com/blog/cursive-1.14.0-eap1.html. I have another major feature that I don't have good online doc for, which is also not possible with the VS Code API (parinfer, a Clojure editing mode). This gives you an idea of what it looks like, but this is old and my implementation doesn't work much like this any more: https://shaunlebron.github.io/parinfer.
It’s not great:
Or is it yet another lame distraction effort around the abject and embarrassing failure to ship GPT-5?
These people are pretty shameless in ways that range from “exceedingly poor taste” to “interstate wire fraud” depending on your affiliation, but people who ship era-defining models after all the stars bounced they are not.