Bringing developer choice to Copilot with Anthropic’s Claude 3.5 Sonnet, Google’s Gemini 1.5 Pro, and OpenAI’s o1-preview
Blog post from GitHub
GitHub Copilot, an AI-powered coding assistant, has evolved by leveraging various large language models (LLMs) like OpenAI's Codex, GPT-3.5, and GPT-4, with recent updates introducing models like Anthropic’s Claude 3.5 Sonnet, Google’s Gemini 1.5 Pro, and OpenAI’s o1-preview and o1-mini. These models enhance Copilot's capabilities by offering developers choice in selecting the best suited model for their specific tasks, thus reinforcing GitHub's commitment to providing an open platform for developers. GitHub Copilot now integrates multi-model functionality across multiple surface areas such as code review and security autofix. Additionally, GitHub introduced "GitHub Spark," an AI-native tool allowing developers to create applications using natural language, supporting the platform’s vision of reaching 1 billion developers by offering a seamless integration of AI features without cloud resource management.