GitHub Models: A new generation of AI engineers building on GitHub
GitHub has launched GitHub Models, providing developers access to advanced language models for AI experimentation, enhancing coding practices while ensuring privacy and security in development processes.
Read original articleGitHub has launched GitHub Models, a new initiative aimed at empowering over 100 million developers to become AI engineers by providing access to industry-leading language models. This platform allows developers to experiment with various models, including Llama 3.1, GPT-4o, and Mistral Large 2, through an interactive playground. Users can test prompts and model parameters for free, facilitating a hands-on learning experience. The integration with Codespaces and Azure AI enables seamless transition from experimentation to production deployment, ensuring enterprise-grade security and data privacy.
GitHub Models is designed to lower the barriers for developers interested in building generative AI applications, offering sample code and tools to streamline the development process. The initiative aligns with GitHub and Microsoft’s commitment to privacy, ensuring that user prompts and outputs are not shared with model providers. The platform is set to expand further, with plans to introduce additional models and capabilities in the future.
The launch is part of a broader trend where developers are increasingly leveraging AI in their workflows, with GitHub Copilot already contributing significantly to code generation. The initiative aims to foster a collaborative environment for AI development, encouraging experimentation and innovation within the developer community. GitHub Models represents a significant step towards integrating AI into everyday coding practices, making advanced tools accessible to a wider audience.
Related
The Death of the Junior Developer – Steve Yegge
The blog discusses AI models like ChatGPT impacting junior developers in law, writing, editing, and programming. Senior professionals benefit from AI assistants like GPT-4o, Gemini, and Claude 3 Opus, enhancing efficiency and productivity in Chat Oriented Programming (CHOP).
Self hosting a Copilot replacement: my personal experience
The author shares their experience self-hosting a GitHub Copilot replacement using local Large Language Models (LLMs). Results varied, with none matching Copilot's speed and accuracy. Despite challenges, the author plans to continue using Copilot.
Meta releases an open-weights GPT-4-level AI model, Llama 3.1 405B
Meta has launched Llama 3.1 405B, a free AI language model with 405 billion parameters, challenging closed AI models. Users can download it for personal use, promoting open-source AI principles. Mark Zuckerberg endorses this move.
Big tech wants to make AI cost nothing
Meta has open-sourced its Llama 3.1 language model for organizations with fewer than 700 million users, aiming to enhance its public image and increase product demand amid rising AI infrastructure costs.
Up to 90% of my code is now generated by AI
A senior full-stack developer discusses the transformative impact of generative AI on programming, emphasizing the importance of creativity, continuous learning, and responsible integration of AI tools in coding practices.
It's three things, all currently waitlisted:
1. A new model playground (like the ones by OpenAI and Anthropic) that lets you try prompts against a large range of models
2. Client libraries for the same using what looks like a universal API proxy, though I think these are existing Azure libraries
3. A "gh models run" command (similar to my LLM CLI tool) that lets to interact with models on the command line
So it's mostly a wrapper around existing Azure stuff that makes it MUCH easier to use, because GitHub are better than Azure at things like authentication systems that don't strike fear into your mortal soul.
Also, the pricing is pretty shady. It seems like your GitHub PAT gives you free limited access, but if you ever want to move to a paid model, you have to transition to Azure. The shady part is that it's pretty hidden. You have to go to a specific model in the Marketplace, (for example: https://github.com/marketplace/models/azureml-mistral/Mistra...), then go to the bottom of the "Chapters" to the "Going beyond rate limits" section. There it just directs you straight to the Azure portal.
Maybe if they wanted to develop it into a useful feature it would create unique LLM benchmarks from your pull requests and issues, so you can easily test which model performs best on your codebase. Then augment that with fine-tuning to your code style, etc.
If I've learned one thing in the software industry, then that with a sufficiently creative definition of the word 'engineer' everything is possible. It feels like every week the AI "industry" turns more into some sort of cursed influencer economy. I guess if you've got to explain to your shareholders how you're gonna make the 10 billion back you spent on graphics cards you gotta be optimistic.
They really need to move on from this pricing structure. It's too expensive to host and distribute large binary files from GitHub.
My experience is that Azure OpenAI is waay behind on API and model parity compared to the same thing from OpenAI.
Related
The Death of the Junior Developer – Steve Yegge
The blog discusses AI models like ChatGPT impacting junior developers in law, writing, editing, and programming. Senior professionals benefit from AI assistants like GPT-4o, Gemini, and Claude 3 Opus, enhancing efficiency and productivity in Chat Oriented Programming (CHOP).
Self hosting a Copilot replacement: my personal experience
The author shares their experience self-hosting a GitHub Copilot replacement using local Large Language Models (LLMs). Results varied, with none matching Copilot's speed and accuracy. Despite challenges, the author plans to continue using Copilot.
Meta releases an open-weights GPT-4-level AI model, Llama 3.1 405B
Meta has launched Llama 3.1 405B, a free AI language model with 405 billion parameters, challenging closed AI models. Users can download it for personal use, promoting open-source AI principles. Mark Zuckerberg endorses this move.
Big tech wants to make AI cost nothing
Meta has open-sourced its Llama 3.1 language model for organizations with fewer than 700 million users, aiming to enhance its public image and increase product demand amid rising AI infrastructure costs.
Up to 90% of my code is now generated by AI
A senior full-stack developer discusses the transformative impact of generative AI on programming, emphasizing the importance of creativity, continuous learning, and responsible integration of AI tools in coding practices.