GitHub Copilot Moves Beyond OpenAI Models To Support Claude 3.5, Gemini 9
GitHub Copilot will switch from using exclusively OpenAI's GPT models to a multi-model approach, adding Anthropic's Claude 3.5 Sonnet and Google's Gemini 1.5 Pro. Ars Technica reports: First, Anthropic's Claude 3.5 Sonnet will roll out to Copilot Chat's web and VS Code interfaces over the next few weeks. Google's Gemini 1.5 Pro will come a bit later. Additionally, GitHub will soon add support for a wider range of OpenAI models, including GPT o1-preview and o1-mini, which are intended to be stronger at advanced reasoning than GPT-4, which Copilot has used until now. Developers will be able to switch between the models (even mid-conversation) to tailor the model to fit their needs -- and organizations will be able to choose which models will be usable by team members.
The new approach makes sense for users, as certain models are better at certain languages or types of tasks. "There is no one model to rule every scenario," wrote [GitHub CEO Thomas Dohmke]. "It is clear the next phase of AI code generation will not only be defined by multi-model functionality, but by multi-model choice." It starts with the web-based and VS Code Copilot Chat interfaces, but it won't stop there. "From Copilot Workspace to multi-file editing to code review, security autofix, and the CLI, we will bring multi-model choice across many of GitHub Copilot's surface areas and functions soon," Dohmke wrote. There are a handful of additional changes coming to GitHub Copilot, too, including extensions, the ability to manipulate multiple files at once from a chat with VS Code, and a preview of Xcode support. GitHub also introduced "Spark," a natural language-based app development tool that enables both non-coders and coders to create and refine applications using conversational prompts. It's currently in an early preview phase, with a waitlist available for those who are interested.
The new approach makes sense for users, as certain models are better at certain languages or types of tasks. "There is no one model to rule every scenario," wrote [GitHub CEO Thomas Dohmke]. "It is clear the next phase of AI code generation will not only be defined by multi-model functionality, but by multi-model choice." It starts with the web-based and VS Code Copilot Chat interfaces, but it won't stop there. "From Copilot Workspace to multi-file editing to code review, security autofix, and the CLI, we will bring multi-model choice across many of GitHub Copilot's surface areas and functions soon," Dohmke wrote. There are a handful of additional changes coming to GitHub Copilot, too, including extensions, the ability to manipulate multiple files at once from a chat with VS Code, and a preview of Xcode support. GitHub also introduced "Spark," a natural language-based app development tool that enables both non-coders and coders to create and refine applications using conversational prompts. It's currently in an early preview phase, with a waitlist available for those who are interested.
Re: (Score:3)
1) Claude 3,5 sonnet is by far the best model for coding. So no, not "more".
2) It does not just randomly modify your code. You get a diff, which you then review (block by block - so you can accept some parts and reject others if you want).
3) You don't have to use it for core "coding" tasks if you don't want to. You can use it to do things like, "There's a X bug when I do Y. Add a ton of debugging statements all over the code." Or "Write a bunch of unit tests for this function I just wrote". Or you can d
Generating Code isn't Something to Brag About... (Score:2)
Re: (Score:2)
When I first started coding in the 90s, almost everyone still smoked cigarettes. Turns out those little 10 minute cigarette breaks where hugely valuable because we'd all be standing behind the building , boss, me, receptionist, the jr all smoking and talking casually about the problems we where facing. And on "Smokeo" everyone was equal. The fresh-out-of-highschool junior could chime in on what the boss talking about an issue with an investor, and he'd be listened to (even if he rarely had much useful to ad
This is what I call a waste of bits. (Score:1)
Who the hell fucking dreams this shit up, it gets paid for it too?
Mind-boggling.
More mind-boggling at this website posts this garbage.
Re: (Score:1)
Re: (Score:2)
"Stuff that makes nerds mad"
We're here to argue, No?
Hello World code is getting better every day (Score:2)
I can't keep track of all this progress anymore!