DEV Community: Tabnine

How to use AI in your engineering organization [webinar]

Tabnine — Mon, 06 Feb 2023 14:22:17 +0000

Artificial Intelligence has become a critical tool for organizations to enhance productivity, innovation, and competitiveness. In this webinar we will cover best ways to integrate AI into your team’s workflow.

We will cover:

Identifying areas where AI can be applied in your organization
Defining clear goals and objectives for your AI initiatives
Acquiring the right skills and resources to implement AI
Developing a data strategy to ensure access to quality data for AI models
Addressing security and privacy concerns
Implementing, monitoring, and evaluating AI initiatives
Keeping up with AI advancements and continuous improvement

Don't miss your chance to hear from Tabnine CEO and Co-founder, an industry expert, and see real-world examples of how AI is revolutionizing engineering operations in organizations. Sign up now! (https://tabnine.zoom.us/webinar/register/WN_To01_Mp7RCCEmqIQN-pzKA

)

Let's talk about generative AI!

Tabnine — Mon, 02 Jan 2023 10:17:45 +0000

AI will fundamentally change how businesses operate, innovate, and scale in the near future.

We invite you to join us on Wednesday, together with Professor Eran Yahav, to discuss generative AI and its implications for software development👇
https://twitter.com/i/spaces/1yoKMZLRDveGQ?s=20

The deal you've been waiting for is finally here!

Tabnine — Tue, 29 Nov 2022 06:28:01 +0000

All Tabnine Pro features, half the price!

Advanced completions

Whole-line code completions
Full-function completions
Natural language to code completions
Learns your coding patterns & style

50% off Tabnine Pro

How to get better code predictions from AI

Tabnine — Mon, 07 Nov 2022 10:34:35 +0000

Tabnine now has over a million users and over 500k active monthly users. As a company we cherish the opportunity to work with some of our best users to understand how they interact with Tabnine. Adding to these priceless conversations is the data we gather from our users that choose to share with us for the benefit of product development.

One of the most fascinating data points is how some users really use Tabnine in a deep, deep way. These users have more than 30% of their code generated by Tabnine. On the other end of the spectrum there are users that really don’t find much value in our product. But why these two groups? Controlling the data for language and total usage uncovers some interesting observations. While a majority of our customers see 10-20% of their code generated by Tabnine the ends of the distribution have quite the Marmite characteristics. Looking into this a bit deeper and doing observational sessions with new and experienced users we have found that there is a defining characteristic that makes Tabnine really shine. In this article we will discuss what we found and how this has helped us craft a simple set of “best practices” that will both help use Tabnine better as well as have a few knock on benefits for any individual developer and the companies that they work for. So let’s dive in.

The heart of Tabnine is the machine learning (ML) algorithm that works in real-time to provide suggestions in the user’s IDE. Any ML algorithm is only as good as the data that was used to train it. Perhaps you remember the classic Cat OR Not? algorithm that was used to determine if a picture was that of a cat or something else. In order to successfully determine the animal in the picture, the algorithm was trained on millions of pictures of cats and not-cats from the internet. Tabnine’s code algorithms work very similarly. If you’d like to train an algorithm to help understand and suggest code for a Javascript front-end it would need to be trained on good Javascript doing front-end work. Tabnine comes configured with a large universal model that has been trained with billions of lines of open source code and specialized models trained for specific languages like Java, Typescript, Python and others.

For most users simply letting Tabnine handle the model switching gives users a great experience. Most developers get good completions with automatically switching models for various languages. As code complexity and variety increases there is an opportunity to boost productivity by pursuing a custom model solution. This is something that Tabnine can help with as well.

While the nuances of training large language models and custom derivations of these models isn’t specifically part of this article, a basic understanding of how these models learn is really helpful. The model will only really be able to suggest completions that it has observed in the training data. We call Tabnine an AI Pair Programming tool for a very good reason. Imagine two developers working together side by side. The junior dev will want and appreciate the help of the senior engineer, but in this relationship communication is key to good results. Your AI pair programming buddy isn’t a mind reader and neither is Tabnine (though we are working on that in a few sprints…) To get the most out of a pair programming effort, as well as Tabnine we need to prompt the effort with comments and well thought through variable and function names.

Let’s look at a quick example:

Figure 1: Here is an example of giving Tabnine some “meat” to work with in the comments. In this example we are creating an algorithm for the industry standard image classification problem using pictures of iris flowers. The url for the example is placed above for reference, and we lead with the task we wish to accomplish. In this case it’s acquiring the necessary libraries for a random forest classifier and manipulations of the dataset. The gray italics after the comment are the suggestions that Tabnine displays. We simply press the tab key to accept.

Figure 2: In this example the same outcome is attempted without the comments. While Tabnine will help complete individual lines (e.g. “import numpy as”…will get an autocomplete “np”) but as we can see the snippet completions are much shorter as the context and intention are not as clear.

Tabnine is contextually aware, and as a particular file grows in size Tabnine will understand variables and functions used previously, so that will certainly help, but there is so much more power available when we interact in a conversational manner. But beyond the help it gives the individual developer, there is more benefit for the developer and the customer or business they are working for. No pull request has been rejected for being too well commented. Tabnine helps reduce technical debt and bug work by helping build robust documentation for the code that is being written. And that is certainly something that will help everyone.

Altering your coding style to incorporate more comments and more conversational programming methods is what we have observed to be the key defining metric for our users that are really leveraging the tool for a meaningful productivity boost. Give it a try and see if it’s something that will work well for you as well.

Webinar! Become a Tabnine expert in 40 minutes ⚡️

Tabnine — Sun, 04 Sep 2022 08:53:09 +0000

Join our webinar tomorrow and learn all about:

🎯 Which plan best suits you?
🎯 Foundational features of Tabnine
🎯 The Tabnine Hub
🎯 How to get the best results

⏰ Monday | September 5th | 5PM CET

Pair Programming With AI - Friend or Competitor?

Tabnine — Sun, 21 Aug 2022 07:24:31 +0000

Today! A fascinating Twitter Space, with Tabnine CEO and CTO of, along with a few interesting people in the community - Pedro Sanders, Adam Gross, and Eddie Jaoude - who discuss whether Artificial Intelligence will replace our jobs, or become our best friend in the future.
https://twitter.com/i/spaces/1yNGaYLmdrnGj?s=20

Are you looking for new cool things to try? 🔮

Tabnine — Tue, 09 Aug 2022 11:58:32 +0000

Tabnine Pro is free to try!
https://www.tabnine.com/pro

The next generation of AI for code is here!

Tabnine — Wed, 15 Jun 2022 13:45:34 +0000

Dror Weiss | June 15, 2022

Today, I’m excited to make a few important announcements:

1,000,000+ developers use Tabnine!
I’m happy to share that Tabnine is successfully automating 30% (and often >40%) of the code created by over 1,000,000 developers. I would like to thank our fantastic user community. One million developers is massive, but as we’re confident that all developers will use AI in the near future, you are the early adopters of AI technology for creating higher quality software faster. Your trust and feedback drive us to push the limits of what’s possible, taking Tabnine to a new and exciting technology foundation.

Tabnine’s new code-native AI models enable whole-line, full-function code completions, and natural language-to-code completions.

Over the past year, we have completely revamped our AI models as well as our approach to integrating new models into the platform. As opposed to a monolithic approach that mandates a single AI model, Tabnine now supports any compatible AI model for providing guidance to developers.

In fact, Tabnine now uses a family of a dozen of code-native models. The new code-native models are trained from the ground-up on code (vs. models pre-trained on text and retro-fitted to learn code). Each of these models is optimized from its basic “vocabulary” to fit a specific language and domain, thus using the entire learning capacity of the model for the relevant code patterns. Our code-native models improve Tabnine by providing better precision and a 5x increase in the length of suggestions.

Tabnine’s AI models run on a powerful GPU cluster to predict the code for you. We can’t wait for you to try it!

With the new AI models, Tabnine can contextually complete whole lines of code and even full functions, as well as generate code based on natural language description in comments. This functionality is now available for Python, JavaScript, TypeScript, Java, and 7 other languages as a part of Tabnine Pro using the Visual Studio Code and JetBrains IDEs.

The new models are now used for predicting full lines and snippets of code, and we’ll be gradually rolling them out also for better precision and length than the current mid-line code completion available in Tabnine Starter.

Launching Tabnine Pro
We’ve included the new line completion and snippet completion functionality in our new Pro plan, which is now our recommended plan for professional developers. The new Pro plan also allows customers of 3+ team members to train the AI model on the code in their GitHub, GitLab, or BitBucket repositories.

With Tabnine, developers can code better, no matter where they are coding from. 🏖️ Including the beach 😎

Tabnine — Tue, 24 May 2022 07:53:58 +0000

10 Software Developers You Should be Following in 2022

Tabnine — Mon, 18 Apr 2022 10:14:11 +0000

Being a software developer in 2022 can sometimes seem like an overwhelmingly solitary existence. One of the challenges of a hybrid or remote work environment is that opportunities to learn and be inspired by your teammates can be limited.

On the other hand, 2022 gives us access to near-limitless possibilities when it comes to finding online virtual mentors. There are some truly incredible devs out there doing some really inspiring work.

Taking inspiration from others is a great way to quickly level up your skills. Remember what Jean-Luc Godard said: "It’s not where you take things from, it’s where you take them to.’”

Here is our list of 10 Software Developers You Should be Following in 2022:

Ania Kubów

Like most of our online mentors, Ania now splits her time between software development and online course creation. Ania quit the rat race a few years back to focus on her growing YouTube channel which has already racked up more than 8 million views and 250 thousand subscribers. Ania is all about ‘reaching and teaching’ with the goal of educating students on how to code by building retro games and awesome projects. You can make your Wednesdays even more wonderful by checking out Ania’s weekly video releases on YouTube and FreeCodeCamp.

YouTube

Lana Lux
Lana is a full-time indie game developer currently working on her very own apocalyptic city survival game called STRAIN. You can check out her daily streams on Twitch and tutorials on YouTube. Lana’s light-hearted approach to game development is always fun, refreshing, and informative. Unlike some of the other developers we’ve mentioned in our list, Lana doesn’t just write code, she’s a legit 3D artist creating tons of gorgeous assets for her games. If you’d like to learn more about the world of indie game development, Unity, C#, and Maya 3D, you should definitely give Lana Lux a look.

YouTube

Mosh
Mosh Hamedani is a software engineer with over two decades of experience. He’s taught more than 10 million students how to code through his online courses and YouTube channel, where he’s built a massive following of over 2 million subscribers. Mosh believes coding should be fun and accessible to everyone. He started programming at the age of seven on a Commodore 64 and fell in love with it. Outside the software world, he enjoys photography, playing jazz piano, swimming, and Latin dancing. Mosh is based in Melbourne, Australia.

YouTube

Coding Garden with CJ
CJ started coding Coding Garden a couple of years back and has been dropping fresh content several times a week since then. The community is open, interactive, and engaging. Any coder, from beginner to expert, can learn and grow together. Whether it's a tutorial, Q&A session, algorithmic problem solving, or full application design and build, there's always something new to learn in the garden. With close to 50 thousand followers on Twitch, 120 thousand on YouTube, and well over 4.5 million views, you’ll be in good company when you roll up your sleeves and dig into Coding Garden’s content.

YouTube

Shaun Pelling (The Net Ninja)
Shaun is a full-stack web developer and online instructor with more than 1000 free programming tutorials on his YouTube channel The Net Ninja. His massive library covers subjects including - Modern JavaScript, Node.js, React, Vue.js, and Firebase just to name a few. The depth and breadth of his courses have helped him land a loyal following of close to 1 million subscribers. In addition to creating compelling course content, Shaun works on various UK-based eCommerce websites for small independent organizations as well as large international brands.

YouTube

Ben Awad
Ben is an enigma of sorts, his celebrity extends far beyond the boundaries of the development world into the mysterious domain of ‘social influencer heartthrob’. Vox wrote an article about him last year entitled “Anatomy of a TikTok hunk”. At only 24 years old, Ben has already built an enormous following on TikTok and YouTube with videos focusing (mostly) on React, React Native, GraphQL, Typescript, Node.js, PostgreSQL, and Python software development. His YouTube community tops 350 thousand and he’s racked up more than 14 million views on Tik Tok.

YouTube

Jeff Delaney
Jeff is the founder of fireship.io, home to a massive free and paid tutorial catalog. Delaney has also accumulated over 1.2 million subscribers and 116 million views on the fireship.io YouTube channel. The channel is home to tons of “High-intensity ⚡ code tutorials to help you build & ship your app faster.” Jeff refers to his Fireship.io website as “a gateway drug for developers who want to build awesome web & mobile apps.” One of the massive benefits of the fireship.io business model is that you get to spend hours watching free tutorials before having to decide whether or not Jeff’s teaching style works for you.

YouTube

The Cherno (Yan Chernikov)
Yan, who is a massive fan of graphics rendering, got his start working on game engines for the TripleA industry behemoth Electronic Arts. After putting in a solid 4.5 years at EA, Cherno decided to head out on his own and start Cherno Studio, built using his very own game engine he named Hazel. You can join the close to half a million subscribers who regularly tune in to The Cherno’s YouTube channel for a behind-the-scenes peek at the process and follow the team building the games. The channel is packed with tons of tutorials geared toward programmers interested in game development.

YouTube

Lama Dev (Safak Kocaoglu)
Safak’s YouTube channel is less than 2 years old and has already racked up more than 80 thousand subscribers and 4.5 million views. Safak’s passionate full-stack approach to teaching web development has played a key role in the meteoric rise of his audience numbers. If you’re itching to add some web design and animation skills to your toolset and React, Node.js, HTML, and CSS tutorials are your jam, Lama Dev is definitely worth a look.

YouTube

Bucky Roberts
Bucky and The New Boston have the oldest and largest YouTube channel on our list by far with 2.6 million subscribers and nearly 500 million views. The TNB channel was started back in early 2008 and is packed with hours of free tutorials. New devs can dive into the well-organized playlists for JavaScript, Java, C, C++, and Docker tutorials. If you’re interested in blockchain tech, you may want to check out TheNewBoston blockchain project, an open-source digital economy being developed by a community of contributors all over the world. This economy rewards contributors in TheNewBostonCoin (TNBC) for adding value.

YouTube

Are you following some incredible devs that weren’t on our list? Share their names with us @Tabnine_ on Twitter and maybe we can add them to our next list.

Tabnine Announces Easy Integration with Atlassian’s Bitbucket

Tabnine — Wed, 30 Mar 2022 14:03:30 +0000

We’re on a roll! Today’s announcement about our integration with Bitbucket marks a major milestone for Tabnine, now officially partnering with all three leading git providers. Bitbucket users can now benefit from the same easy Tabnine integration as GitHub and GitLab users, allowing them to leverage their existing repositories to privately train their own personalized AI coding assistants.

Millions of software developers and engineers invest countless hours every day refining their Bitbucket repositories based on their best practices, code reviews, QA, and security testing. Utilizing existing assets is a key principle of all AI-assisted ‘work smarter’ productivity enhancements. Now the time invested in creating repositories can be translated into additional productivity gains.

Software development teams using Bitbucket and Tabnine for Teams’ premium personalized AI coding assistant can increase the development speed of every team member, streamline onboarding, automate remote knowledge sharing, improve team-wide code consistency, and reduce code review iterations.

Bitbucket is known for providing professional team features at incredibly affordable prices, that coupled with best-in-class Jira integration, integrated code reports, a handy code-aware semantic search tool, and the CI/CD pipeline, make Bitbucket a great option for anyone looking for a top-tier git provider and a powerful partner for Tabnine.

How to get started:

Atlassian/Bitbucket users can purchase a Tabnine for Teams monthly or annual account from the Tabnine website.

As a Tabnine for Teams user, log in to the Tabnine App
Navigate to the “Team AI” tab
Enable Bitbucket repository integration
Tabnine will build, test, and upload your private team model
Enjoy your team’s personalized Tabnine AI assistant

Tabnine is proud to provide an easy integration experience for the millions of Bitbucket, GitLab, and GitHub users who are adding Tabnine’s AI code completion assistant to their software development workflow.
Feel free to reach out to support@tabnine.com with any questions – We’re always happy to help.

https://www.youtube.com/watch?v=TBEjAfQUHaU&ab_channel=Tabnine

Tabnine and GitLab Partner Up!

Tabnine — Wed, 02 Mar 2022 19:31:38 +0000

We are incredibly excited to announce Tabnine’s partnership with GitLab. This new integration will give millions of Tabnine and GitLab users the ability to easily create private custom AI models trained on code from their GitLab repositories, coding conventions, and best practices.

All development teams using gitlab.com can now benefit from a personalized Tabnine AI assistant trained on their GitLab repositories.

For Tabnine, this is another big step in integrating its core technology with leading dev tools such as GitLab. We are committed to the global developer community and engineering teams of all sizes and stacks, and as such see this is a natural step forward in accommodating our solutions to everyone, anywhere.

The Tabnine partnership builds on GitLab’s already strong foundation of developer-centric integrations. GitLab has a well-deserved reputation for providing everything professional development teams need to deliver cutting-edge code.

With the Tabnine-GitLab integration, you can use your team’s code repositories hosted on GitLab to train a private AI model that code, and benefit from AI assistance that’s tailored to your team’s code patterns and best practices.

How to get started:

As a Tabnine for Teams user login to AI Code Completions for Developers & Teams | Tabnine
Navigate to the “Team AI” tab
Connect to your GitLab repositories
Tabnine will build, test, and upload your private team model
Enjoy your personalized Tabnine AI assistant

Tabnine is thrilled to provide a GitLab integration experience for all of our current developers and we look forward to helping the millions of GitLab users experiencing Tabnine’s AI assistant for the first time.