TechNow: OpenDevin, GPT/Claude Prompt Engineer, Sakana Model

In this post, we cover open-source projects like OpenDevin, empowering developers to build on top of Devin, the AI for software engineering, to GPT/Claude Prompt Engineer, a tool that helps craft optimal prompts for AI models, there’s something for everyone. And Sakana AI is pushing the boundaries with their “Evolutionary Model Merge” technique, automatically generating new foundation models by combining existing ones

OpenDevin

OpenDevin lets you replicate, enhance, and innovate Devin, an AI for software engineering, using open source. It gained popularity after Cognition Labs’s Devin video went viral. The project uses large language models (LLMs) for development tasks, ensuring safe code execution with Docker and Kubernetes, and facilitating user interaction through React or VSCode interfaces.

GPT/Claude Prompt Engineer

The claude-prompt-engineer helps you create optimal prompts for Claude 3 by describing your task. The process involves generating multiple prompts, testing them in an ELO tournament style, and selecting the best one. The tool is open-source, improves prompt creation through automation, supports multi-variable prompts, and utilizes Claude 3’s advanced capabilities, leading to higher quality outputs than previous versions. 

Sakana model

Sakana AI has crafted a method called “Evolutionary Model Merge.” This technique leverages evolutionary algorithms to automatically forge new foundation models. It does this by mixing and matching from a pool of over 500,000 open-source models on HuggingFace.

The key is finding the best ways to combine these models, both in how they’re built (their architecture) and how they think (their parameters).

Details on Specific Models:

• EvoLLM-JP: This is a Japanese Large Language Model with 7 billion parameters, focused on math. It’s remarkable because it outdoes models that are ten times its size on Japanese language tasks, hitting a 94.2% accuracy rate on the MGSM benchmark compared to the previous best of 75.6%.
  
• EvoVLM-JP: They also created a Japanese Vision-Language Model, EvoVLM-JP, that beats current models on visual question answering tests, scoring 74.3% on JA-VG-VQA-500 and 69.8% on JA-VLM-Bench-In-the-Wild.
  
• EvoSDXL-JP: Finally, they’ve developed a highly efficient Japanese image generation model that works in just four diffusion steps, making for rapid image creation.

Neuroevolution: Sakana AI’s approach isn’t just about making individual models better. It’s about how you can stitch together a variety of models to build AI systems that are more general-purpose and efficient, all while cutting down on the hefty costs usually involved in training them. 

Artificial General Intelligence: The ability to combine different aspects of intelligence—like language understanding, reasoning, and visual processing—into a cohesive whole suggests a path forward for the development of Artificial General Intelligence (AGI).