Tabnine, the originators of the AI coding assistant category, is unveiling a new capability for its software development chat tool, Tabnine Chat, that allows engineers to choose the large language model (LLM) from a catalog of models that powers the chat assistant. This grants development and engineering teams the flexibility to select the models that best suit their needs, as well as the ability to switch between models as desired.
The space of AI and LLMs changes at a rapid pace. Keeping up with this pace of innovation is a challenging task, as many solutions force the user to lock-in to a specific model, ultimately isolating teams from the best of the best in AI tech, according to the company.
Tabnine Chat—the enterprise-grade, code-centric chat assistant that enables users to interact with Tabnine AI models via natural language—now allows developers to switch between models at will, allowing them to take full advantage of newer LLMs.
“Engineering teams should have the freedom to choose the most suitable model for their use case without the need for multiple AI assistants or vendor switches. They should be able to choose based on each model’s specific performance, privacy policies, and the code it was trained on,” said Eran Yahav, co-founder and CTO of Tabnine. “To date, this has not been possible with the best-of-breed AI coding assistants—but we are changing that. Tabnine eliminates any worry about missing out on AI innovations and makes it simple to use new models as they become available.”
This agility, paired with Tabnine’s transparency into behaviors and characteristics relating to model performance, privacy, and protection, enables users to choose from any of the following models:
- Tabnine Protected, Tabnine’s original model that offers high performance without the danger of intellectual property violations or code leakage
- Tabnine + Mistral, a new Tabnine model that offers the highest class of performance while maintaining complete privacy
- GPT-3.5 Turbo and GPT-4.0 Turbo, the industry’s most popular LLMs
Regardless of the model that developers select, users benefit from the full capacity of Tabnine, including code generation, code explanations, generation of documentation, AI-created tests, and codebase awareness, according to the company.
To learn more about Tabnine Chat, please visit https://www.tabnine.com/.