Table of Contents
JetBrains s.r.o, a company that provides professional software development tools, has launched a new product called JetBrains AI, an AI-powered coding companion that helps developers write better code. It is now generally available to users of JetBrains’ integrated development environments (IDEs), which are software applications that combine various tasks of software development, such as coding, building, debugging, and testing, into a single platform.
What JetBrains AI can do
JetBrains AI is powered by multiple generative AI models, also known as large language models (LLMs), that can generate natural language and code based on the given context and input. Because JetBrains AI is deeply integrated with JetBrains’ IDEs, it can understand both the code and the overall project that the developer is working on without requiring the developer to leave their editing environment to interact with it.
It provides a conversational interface with an LLM, where the developer can ask questions, request code review, ask for the generation of code snippets, and then easily copy and paste the code directly into the project. It can also assist with documentation, test generation, code refactoring, and language translation.
How it connects to different LLM providers
Jodie Burchell, developer advocate for data science at JetBrains, told SiliconANGLE in an interview that what makes JetBrains AI unique is that it is powered by an AI Service that transparently connects it to the right LLM provider based on the developer’s needs.
“This is basically a service that is contacted by a network within the IDE. Right now, we determine heuristically which model to use based on which one is going to be the best for the job,” Burchell said. “In the future, we may introduce the capability to choose the models that you want to work with. And this is potentially not that far off as we are considering allowing organizations to bring their own models.”
JetBrains employs a combination of OpenAI’s most recent models, including GPT-3.5 and GPT-4, as well as its own LLMs, via the AI Service. Burchell also stated that the company has recently signed on with Google and will be integrating some of the company’s models in the near future.
“Generally, the idea will be, if it’s really important in terms of privacy or fine-tuning, you may have the opportunity to bring your model,” Burchell added. However, this will naturally come with a bit of a compromise as some models will not be as powerful as others. “So, this is something we’re working on, but it will not be part of the initial release.”
How it ensures data privacy
Burchell also stressed that JetBrains has been cautious about agreements with AI providers that no data will be stored or used for training. This means that any company that uses JetBrains AI can be certain that their data will remain private.
How JetBrains AI handles errors and hallucinations
As with any AI tool, JetBrains AI can still produce errors or hallucinations, which are cases where the LLM generates incorrect or irrelevant information. Burchell said that this can be greatly reduced by providing the LLM with as much context as possible and making sure that its information is as up-to-date as possible. JetBrains is investigating a process known as retrieval-augmented generation, or RAG, which uses real-time data to maintain an LLM’s knowledge base in order to reduce the number of errors it generates.
“This is also the reason we chose JetBrains AI,” said Burchell. “We really do want to emphasize that we’re dealing with models that are fluid and they can hallucinate. You should not be just accepting things at face value; you should use other functionality in your IDE to help refine code and own it. We don’t want people to think this is going to replace them. It’s just another productivity tool.”
How to get JetBrains AI
JetBrains AI integrates directly into JetBrains’ commercial IDEs and will eventually be available across the entire JetBrains product line. Individuals pay $10 per user per month or $100 per year. Organizations pay $20 per user per month or $200 per year.
