Bringing developer choice to Copilot with Anthropic’s Claude 3.5 Sonnet, Google’s Gemini 1.5 Pro, and OpenAI’s o1-preview
[ad_1]
GitHub Copilot has long leveraged various large language models (LLMs) for various use cases. The first public release of Copilot was launched specifically with Codex, an early version of OpenAI GPT-3 Fine-tuned for coding tasks. Copilot Chat was launched in 2023 with GPT-3.5 and later GPT-4. Since then, we have updated the base model versions several times, using a range from GPT 3.5 Turbo to GPT 4o and 4o Mini models for different latency and quality requirements.
Last year we experienced a boom in high-quality small and large language models that excel individually at different programming tasks. It is clear that the next phase of AI code generation will be defined not only by multi-model functionality, but also by multi-model selection. GitHub is committed to its ethos as an open developer platform, ensuring that every developer has the opportunity to build with the models that work best for them. Today at GitHub Universe we delivered exactly that.
With Claude 3.5 Sonnet from Anthropic, Gemini 1.5 Pro from Google, and o1-preview and o1-mini from OpenAI, we offer developers choices for GitHub Copilot. These new models are rolling out – first in Copilot Chat, with OpenAI o1-preview and o1-mini available now, Claude 3.5 Sonnet rolling out gradually over the next week, and Google’s Gemini 1.5 Pro in the coming weeks. From Copilot Workspace to multi-file editing to code review, security autofix, and the CLI, we will soon provide a selection of multiple models across many of GitHub Copilot’s interface areas and features.
Whether in VS Code or on GitHub.com, individual developers can now decide which models work best for them, while organizations and companies have full control over which models they enable for their team. Try Copilot with multiple models today.
Anthropics Claude 3.5 Sonnet
Anthropic is new Claude 3.5 sonnet excels at coding tasks across the entire software development lifecycle – from initial draft through bug fixes and maintenance to optimizations. Claude 3.5 Sonnet demonstrates high proficiency in complex and multi-step coding tasks, handling everything from legacy app updates to code refactoring and feature development.
Google’s Gemini 1.5 Pro
The latest Twin models from Google show high skills in coding scenarios. Gemini 1.5 Pro features a context window with two million tokens and is natively multimodal – with the ability to process code, images, audio, video and text simultaneously. Gemini 1.5 Pro also offers impressive response times for regular code suggestions, documentation and explanatory code.
OpenAI’s o1-preview and o1-mini
OpenAI o1 preview and o1-mini are part of a new series of AI models equipped with more advanced reasoning features than GPT 4o. While our exploration When using o1-preview with GitHub Copilot, we found that the model’s reasoning capabilities enable a deeper understanding of code limitations and edge cases, producing efficient and high-quality results.
With GitHub Copilot, the developer is in control. Now you can also control which core LLM you use, all with a single login and subscription. Try Copilot with multiple models today.
First look: Multi-model selection for GitHub Spark
To pursue GitHub’s vision of reaching 1 billion developers, today at Universe we introduced GitHub Spark: the AI-native tool for building applications entirely in natural language. Sparks are fully functional micro-apps that can integrate AI capabilities and external data sources without the need to manage cloud resources. Using a creativity feedback loop, users start with an initial prompt, see live previews of their app as it is built, easily see options for each of their requests, and automatically save versions of each iteration so they can compare versions as they build.
Here is a first look or spark GitHub Spark.
Written by
[ad_2]
Source link