Introducing SafeCoder

Today we are excited to announce SafeCoder - a code assistant solution built for the enterprise.

The goal of SafeCoder is to unlock software development productivity for the enterprise, with a fully compliant and self-hosted pair programmer. In marketing speak: “your own on-prem GitHub copilot”.

Before we dive deeper, here’s what you need to know:

• SafeCoder is not a model, but a complete end-to-end commercial solution
• SafeCoder is built with security and privacy as core principles - code never leaves the VPC during training or inference
• SafeCoder is designed for self-hosting by the customer on their own infrastructure
• SafeCoder is designed for customers to own their own Code Large Language Model

Why SafeCoder?

Code assistant solutions built upon LLMs, such as GitHub Copilot, are delivering strong productivity boosts. For the enterprise, the ability to tune Code LLMs on the company code base to create proprietary Code LLMs improves reliability and relevance of completions to create another level of productivity boost. For instance, Google internal LLM code assistant reports a completion acceptance rate of 25-34% by being trained on an internal code base.

However, relying on closed-source Code LLMs to create internal code assistants exposes companies to compliance and security issues. First during training, as fine-tuning a closed-source Code LLM on an internal codebase requires exposing this codebase to a third party. And then during inference, as fine-tuned Code LLMs are likely to “leak” code from their training dataset during inference. To meet compliance requirements, enterprises need to deploy fine-tuned Code LLMs within their own infrastructure - which is not possible with closed source LLMs.

From StarCoder to SafeCoder

At the core of the SafeCoder solution is the StarCoder family of Code LLMs, created by the BigCode project, a collaboration between Hugging Face, ServiceNow and the open source community.