Tabnine Enterprise supports single sign-on (SSO)

Posted on July 16th, 2023

Tabnine Enterprise supports SSO

We’re excited to announce that Tabnine Enterprise self-hosted now supports single sign-on (SSO) functionality, marking a significant enhancement to our platform. SSO integration streamlines the authentication process for your users by connecting Tabnine to your existing identity provider. This means your team members can access Tabnine with the same credentials they use for other applications, enhancing security and convenience. The setup process for SAML SSO can be found in our official Docs section on Tabnine’s website.

Tabnine is the ultimate option for software development teams seeking to integrate artificial intelligence into their processes.

With Tabnine AI coding assistant, you can automate repetitive coding tasks and produce high-quality, industry-standard code, detect errors more quickly, fix bugs faster, and onboard new codebases faster with Enterprise navigation. Using Tabnine Enterprise, you can run the model on-premises or in a virtual private cloud (VPC), ensuring full control over your data and infrastructure. Experience seamless and secure authentication with Tabnine Enterprise, empowering your development workflow like never before. For more information on how Tabnine Enterprise can benefit your organization, feel free to contact our enterprise expert and book a demo.

What are large language models, and are they going to get even larger?

Posted on July 10th, 2023

In an insightful webinar hosted by Tabnine’s CTO and co-founder, Eran Yahav, and VP of Ecosystems, Brandon Jung, they engaged in a comprehensive discussion about the advancements, challenges, and practical applications of leveraging language models. The webinar provided valuable insights into the current landscape of language models, and the advancements, challenges, and practical applications of leveraging language models for AI code assistance.

In this webinar, you’ll discover the latest developments in generative AI for code and beyond. Gain insights into how large language models (LLMs) work, their potential to solve complex problems, and their transformative impact on software development. The discussion also touches upon the trend of increasing model sizes and explores the implications of LLMs, including concerns related to bias, privacy, and security.

From diving into the underlying technologies to exploring the possibilities and limitations, this webinar provides an in-depth exploration of the trends driving AI machine learning with large language models.

Watch the full session below:

 

Tabnine is the AI coding assistant that helps development teams of every size use AI to accelerate and simplify the software development process without sacrificing privacy, security, or compliance. Tabnine boosts engineering velocity, code quality, and developer happiness by automating the coding workflow through AI tools customized to your team. Tabnine supports more than one million developers across companies in every industry. 

Unlike generic coding assistants, Tabnine is the AI that you control:

It’s private. You choose where and how to deploy Tabnine (SaaS, VPC, or on-premises) to maximize control over your intellectual property. Rest easy knowing that Tabnine never stores or shares your company’s code.

It’s personalized. Tabnine delivers an optimized experience for each development team. It’s context-aware and can be tuned to recommend based on your standards. You can also create a bespoke model trained on your codebases.

It’s protected. Tabnine is built with enterprise-grade security and compliance at its core. It’s trained exclusively on open source code with permissive licenses, ensuring that our customers are never exposed to legal liability.

Tabnine Chat can help with every stage of development, right in your IDE:

  • Answering questions regarding your code
  • Generating new code from scratch
  • Explaining a piece of code
  • Searching your code repos for specific functions or pieces of code
  • Refactoring code
  • Generating documentation (docstrings)
  • Finding and fixing code issues
  • Generating unit tests and more

 

CodeWhisperer: Features, pricing, and enterprise considerations

Posted on July 10th, 2023

What Is Amazon CodeWhisperer? 

Amazon CodeWhisperer is an AWS service that offers real-time, AI-driven code suggestions. Utilizing large language models (LLMs) and an extensive library of open-source code, it comprehends the context of your project and provides relevant recommendations as you type.

This is part of a series of articles about ChatGPT alternatives.

Amazon CodeWhisperer features 

Amazon CodeWhisperer provides the following main features:

  • Tailored code suggestions: CodeWhisperer offers code suggestions personalized based on the user’s existing code and comments.
  • Compatibility with popular programming languages and IDEs: The tool supports programming languages such as Python, Java, and JavaScript. It integrates with leading IDEs like Visual Studio Code and IntelliJ IDEA.
  • Integrates with AWS Services: As an Amazon product, CodeWhisperer is integrated with other AWS services, such as Lambda functions or S3 storage solutions.
  • Built-in security scans: To ensure the security of your applications, CodeWhisperer includes integrated security scans that detect potential vulnerabilities in generated code.
  • Reference tracker for open-source code: This feature helps you monitor open-source libraries used in your projects by providing relevant documentation links within the coding environment itself.
  • Bias avoidance: The AI-powered suggestion engine is designed to prevent biases based on race, gender, or nationality when generating recommendations.

The pricing details below are subject to change. For up-to-date pricing information, see the official pricing page.

Individual Tier

The individual tier is free and simple to set up, but it does not include the benefits of organizational license management.

If you are using CodeWhisperer at the individual tier, you can:

  • Use CodeWhisperer with the AWS Toolkit in either VS Code or JetBrains.
  • Authenticate with Builder ID.
  • Control your own reference tracker settings.
  • Access code generation for all supported languages.
  • Share code fragment data with AWS by default (you can opt-out in the IDE settings).
  • Share telemetry data with AWS by default (you can opt-out in the IDE settings).
  • Run up to 50 security scans per month.

Professional Tier

The professional tier incurs charges for additional features, with your employer covering the costs through their company AWS account.

Pricing for the CodeWhisperer Professional Tier is calculated on a “per user, per month” basis. Organizations are billed monthly based on the maximum number of users who have access to CodeWhisperer during a calendar month’s billing period. At the time of this writing, the professional tier costs $19 per user.

If you are using CodeWhisperer at the professional tier, you can:

  • Appoint administrators, who can centrally manage which developers should have access to CodeWhisperer and set policies at the organizational level.
  • Use CodeWhisperer with the AWS Toolkit in either VS Code or JetBrains.
  • Authenticate with credentials set up by your employer’s AWS account’s IAM Identity Center administrator in IAM Identity Center.
  • Not use Builder ID.
  • Allow your administrator to control the reference tracker settings.
  • Access code generation for all supported languages.
  • Not share code fragment data with AWS.
  • Share telemetry data with AWS by default (you can opt-out in the IDE settings).
  • Run up to 500 security scans per month.

Amazon CodeWhisperer vs. GitHub Copilot 

GitHub Copilot, an AI-driven software development tool by Microsoft-owned GitHub, was introduced in 2021 and became generally available in 2022.

There are some notable differences between GitHub Copilot and Amazon CodeWhisperer:

Generality

  • Copilot is a general-purpose AI-assisted development tool, while CodeWhisperer primarily targets use cases related to Amazon platforms, such as Amazon Web Services. Copilot doesn’t cater specifically to Microsoft technologies or related programming use cases, despite being hosted on a Microsoft-owned platform.
  • CodeWhisperer is designed to support Amazon technology scenarios, and usually performs better with Amazon-related technologies. However, it can also be used in non-Amazon environments.

Language Support

  • Copilot can generate code for almost any language and is optimized for a broader range of languages, including Python, JavaScript, TypeScript, Ruby, Go, C#, and C++. Additionally, Copilot supports nearly all major IDEs.
  • CodeWhisperer supports fewer programming languages and IDEs. It currently supports C#, Java, JavaScript, Python, and TypeScript, with most compatible IDEs being Amazon-based (JetBrains and Visual Studio Code are the exceptions). 

Enterprise Features

  • CodeWhisperer provides enterprise features such as security scans, documentation references, and the ability to opt out of sharing code fragments and telemetry data with Amazon.
  • Copilot does not currently provide similar enterprise features, making it more limited for use in enterprise environments.

Challenges of Implementing CodeWhisperer 

Despite its numerous benefits, developers and organizations may face some challenges when implementing Amazon CodeWhisperer, including:

  • Code quality and security: Even though Codewhisperer does provide some features to verify the security and quality of the code, it could still generate code that does not meet an organization’s quality or security requirements. Any code it generates must be carefully reviewed, limiting its productivity gains.
  • Data leakage concerns: As an AI-powered service, CodeWhisperer requires access to your source code to generate suggestions. Organizations must ensure proper data protection measures and compliance with relevant regulations while using such services.
  • Integration with existing workflows: Developers may need to adjust their current development processes to effectively incorporate CodeWhisperer, potentially involving changes in coding practices or team collaboration methods.
  • Potential overreliance on AI-generated code: While helpful, it’s essential for developers not to become overly dependent on generated code and continue developing their skills.

Tabnine: An enterprise-grade Codewhisperer alternative

Tabnine is an AI code assistant used by over 1 million developers from thousands of companies worldwide. It provides contextual code suggestions that boost productivity, streamlining repetitive coding tasks and producing high-quality, industry-standard code. Tabnine’s code suggestions are based on Large Language Models that are exclusively trained on credible open-source licenses with permissive licensing. With Tabnine Enterprise, developers have the flexibility to run the model on-premises or in a Virtual Private Cloud (VPC), ensuring full control over their data and infrastructure while leveraging the power of Tabnine to comply with enterprise data security policies.

Advantages for enterprises:

  • Trained exclusively on permissive open-source repositories
  • Eliminates privacy, security, and compliance risks
  • Avoid copyleft exposure and respect developers’ intent
  • Can be locally adapted to your codebase and knowledge base without exposing your code


Tabnine Chat

Tabnine has recently released Tabnine Chat which is an AI assistant trained on your entire codebase, safe open source code, and every StackOverflow Q&A, while ensuring all of your intellectual property remains protected and private.

Tabnine Chat is always available for you, right in the IDE, to:

  • Answer any of your questions regarding your code
  • Generate new code from scratch
  • Explain a piece of code
  • Search your code repos for specific functions or pieces of code
  • Refactor code
  • Generate documentation (docstrings)
  • Find and fix code issues
  • Generate unit tests, and more