Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

blog.jetbrains.com

Post reply on HN
Print view View original

121–130 of 130 posts

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#121

Post by snuxoll »

kgilpin wrote: post #20
mfro wrote: post #6

Earlier quoted context omitted.

This quote claims it is 'powered by Claude' “JetBrains and Anthropic share a commitment to transforming how developers work. Developers rely on Claude’s state-of-the-art performance in solving complex, real-world coding tasks. We’re excited to see how Junie, powered by Claude, will help the global developer community create innovative things within the trusted JetBrains IDEs that customers love.” Mike Krieger, Chief…

In my experience working on JB extensions, Rider is the most different of the IDEs. Most people think of just IntelliJ and that’s the same code base as eg PyCharm. But Rider seems substantially different.

The biggest difference between the language-specific IDEs in my experience is how they expose the project structure, with GoLand, PyCharm, etc. providing a much more directory centric workflow while Rider by nature has to work around .sln and .*proj files.

But Rider is uniquely weird in its use of ReSharper for code analysis.

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#122

Post by thenickdude »

The free tier now supports connecting to local AI models running on LM Studio or Ollama, but it still doesn't actually function without an internet connection.

If you block access to the internet or to their AI API servers [1], it refuses to start a new chat invocation. If you block access halfway through a conversation, the conversation continues just fine, so there's no technical barrier to them actually running offline, they just don't allow it.

Their settings page also says that they can't even guarantee that they implemented the offline toggle properly, a flag that should be the easiest thing in the world to enforce:

>Prevents most remote calls, prioritizing local models. Despite these safeguards, rare instances of cloud usage may still occur.

So you can't even block access to the very servers that they say their faulty offline toggle would leak data to.

[1] https://www.jetbrains.com/help/ai-assistant/disable-ai-assis...

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#123

Post by int_19h »

lolinder wrote: post #97
jwortmann719 wrote: post #95

Earlier quoted context omitted.

it is token based AFAIK, but we will provide some more information around credits/quota/tokens for the different price tiers in the coming days/weeks

Token based is a pretty strong downside for me that would be enough to get me to use other tools like Cursor (even though I love JetBrains IDEs). I get actively stressed watching an automated system burn through my money on its own recognizance. If I'm going to have quotas or usage-based pricing I want the metrics used to be things that I have direct control over, not things that the service provider controls.

TANSTAAFL. With flat pricing, companies have incentives to downgrade you to cheaper models - which currently strongly correlates with worse quality of output - or, more likely, to trim context significantly and hope you won't notice.

But yes, there should absolutely be ways to track usage, ideally before the prompt is even submitted for processing (maybe for >N tokens per query, where N can be specified in settings but has a reasonable default).

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#124

Post by eclectric »

thenickdude wrote: post #122

The free tier now supports connecting to local AI models running on LM Studio or Ollama, but it still doesn't actually function without an internet connection. If you block access to the internet or to their AI API servers [1], it refuses to start a new chat invocation. If you block access halfway through a conversation, the conversation continues just fine, so there's no technical barrier to them actually running of…

I disconnect from the internet sometimes and noticed this morning that my previous night's chat was invisible. I could only see it once I connected again.

This puts me off a bit to finally try local models. Anyone know what kind data is collected in those rare instances of cloud usage?

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#125

Post by t-redactyl »

basejumping wrote: post #110
lantry wrote: post #101

Earlier quoted context omitted.

the Jetbrains AI assistant plugin lets you choose which model to use.

Yes, but you need to pay the license to them. I guess I'll switch, it's just silly that there isn't an official integration

Hi, from JetBrains here :)

We made the choice to integrate directly with third party providers for a few reasons, but the major one is to do with how the providers can use our user's data. We have very restrictive agreements which don't allow the providers to use the data for training or any purpose other than validating the requests.

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#126

Post by t-redactyl »

eclectric wrote: post #124
thenickdude wrote: post #122

The free tier now supports connecting to local AI models running on LM Studio or Ollama, but it still doesn't actually function without an internet connection. If you block access to the internet or to their AI API servers [1], it refuses to start a new chat invocation. If you block access halfway through a conversation, the conversation continues just fine, so there's no technical barrier to them actually running of…

I disconnect from the internet sometimes and noticed this morning that my previous night's chat was invisible. I could only see it once I connected again. This puts me off a bit to finally try local models. Anyone know what kind data is collected in those rare instances of cloud usage?

Hi, here are our data collection policies for the cloud-based LLMs. We've worked out agreements that heavily restrict how third party companies can use your data, including not storing it or using it for model training: https://www.jetbrains.com/help/ai/data-collection-and-use-po...

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#127

Post by t-redactyl »

mhb wrote: post #109
t-redactyl wrote: post #64

Earlier quoted context omitted.

Where are you updating from? Toolbox, or from the website? I'm seeing 2025.1 in both, so you might have some caching if you're checking the website.

The Help..Check for Updates in PyCharm. I got Toolbox, so, problem worked around. Thanks.

You're very welcome! Enjoy the new release, there's quite a few fun new features.

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#128

Post by KronisLV »

pauleveritt wrote: post #111
KronisLV wrote: post #98

Oh hey, they've worked some more on the features: https://www.jetbrains.com/ai-assistant/ And it's available with the all products pack: https://www.jetbrains.com/ai-ides/buy/?section=personal&bill... I think I'll be more than happy to try it out then cause I have that pack and compare it against the Github Copilot plugin, or the likes of Continue.dev (which was pretty good in VS Code, but kind of buggy in JetBrains…

We've come a long way with AI Assistant in the last few months. Lots more planned.

That's awesome to hear, best of luck!

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#129

Post by mdaniel »

mhb wrote: post #50

Dumb question? How come in PyCharm when I go to update, it only offers me v2024.3.5 and not v2025.1?

Aside from the Toolbox answer, even within the Toolbox it was previously two separate actual installations of PyCharm (community and professional) but starting in 2025 they're now just one install, and it switches behavior based on your authentication https://www.jetbrains.com/pycharm/download/#:~:text=PyCharm%...

Re: JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier

#130

Post by sieabahlpark »

t-redactyl wrote: post #125
basejumping wrote: post #110

Earlier quoted context omitted.

Yes, but you need to pay the license to them. I guess I'll switch, it's just silly that there isn't an official integration

Hi, from JetBrains here :) We made the choice to integrate directly with third party providers for a few reasons, but the major one is to do with how the providers can use our user's data. We have very restrictive agreements which don't allow the providers to use the data for training or any purpose other than validating the requests.

[dead]
Post reply on HN