GitHub Just Made a Big AI Coding Move
Summary
During Microsoft Build, GitHub unveiled a new GitHub Copilot app, which introduces a significant departure from OpenAI's Codex by allowing users to select any model from various providers. This key feature enables developers to choose the "current state of the art fastest, cheapest model" available, offering enhanced flexibility and control over their AI coding assistance. The author expressed considerable enthusiasm for this new capability, eager to explore its potential. However, new plan sign-ups for GitHub Copilot are presently paused, as GitHub focuses on ensuring a high-quality user experience. The exact timeline for when sign-ups will resume remains unclear, though availability could change.
Key takeaway
For AI Engineers evaluating coding assistants, the new GitHub Copilot app's promise of model provider choice is a critical differentiator from existing tools like Codex. You should monitor GitHub's announcements for when new plan sign-ups resume, as this flexibility could significantly impact your ability to optimize for performance or cost with "state of the art" models. Consider how this multi-model approach aligns with your team's specific needs and existing infrastructure.
Key insights
The new GitHub Copilot app offers model provider choice, unlike Codex, but sign-ups are currently paused.
Principles
- User choice in AI models is a key differentiator.
- Flexibility in model selection drives adoption.
- Prioritizing quality can delay new feature access.
In practice
- Evaluate AI coding tools for model flexibility.
- Monitor GitHub Copilot for sign-up resumption.
- Compare model performance and cost options.
Topics
- GitHub Copilot
- AI Coding Assistants
- Microsoft Build
- Model Selection
- OpenAI Codex
- Developer Tools
Best for: Machine Learning Engineer, NLP Engineer, Software Engineer, AI Engineer, Tech Journalist
Related on AIssential
Editorial summary, takeaway, and curation by AIssential. Original article published by Matt Wolfe.