Overview
At the Google Cloud Next 2024 conference in Las Vegas, a series of groundbreaking AI products have been unveiled, showcasing the latest advancements in generative AI technology. Among these innovations are notable upgrades such as Gemini 1.5 Pro、 Google Vids and Imagen 2, designed to transform various creative and development processes.
Gemini 1.5 Pro
Google announced the public preview of its latest generative AI model, Gemini Pro 1.5, on the Vertex AI platform. This model can handle contexts of up to 1 million tokens (equivalent to about 700,000 English words or approximately 30,000 lines of code), which is four times the capacity of Anthropic's Claude 3 model and eight times the maximum context of OpenAI's GPT-4 Turbo. Models with large context windows can better understand the overall content of the input data and generate richer contextual responses.
Additionally, Gemini Pro 1.5 supports multiple languages and is multimodal, capable of understanding text, images, videos, and audio streams. The capacity of 1 million tokens can process about one hour of video or approximately 11 hours of audio.
Gemini Code Assist
Gemini Code Assist is an enterprise-oriented AI coding completion and assistance tool. This tool is an evolved version of Duet AI for Developers, utilizing the latest Gemini 1.5 Pro model to provide developers with comprehensive codebase analysis, code generation, and support for private code repositories across multiple storage solutions. Gemini Code Assist competes more with GitHub's Copilot Enterprise rather than the basic version of Copilot. It offers Google-specific features, such as support for a context window of up to 1 million tokens, and allows enterprises to fine-tune Code Assist based on internal code repositories. It supports code repositories located on services like local servers, GitLab, GitHub, and Atlassian's BitBucket. Currently, the feature is in the preview stage and supports plugins for popular editors like VS Code and JetBrains.
Google has also released CodeGemma, a new open-source model specifically tailored for code generation and assistance, part of the Gemma series.
Google Vids
Google Vids is set to be a part of the Google Workspace suite, enabling users to create impressive videos by converting marketing copy and images into video storyboards that support real-time collaboration and customization.
Imagen 2
Imagen 2 is an enhanced image generation tool integrated into Google's Vertex AI development platform. Despite Google having faced significant controversy in the realm of image generation, Imagen 2, as part of a model series, introduces a host of new features. These include creating and editing images based on textual prompts, rendering multilingual text, logos, and symbols, and overlaying these elements onto existing images.
Additionally, Imagen 2 has introduced two new functionalities: inpainting and outpainting. Similar to Adobe's Firefly, these features can be used to remove unwanted parts of an image, add new components, and expand the image boundaries to create a broader view. The tool now also has the capability to generate brief four-second video clips based on textual prompts, akin to video clip generation tools from companies like Runway, Pika, and Irreverent Labs.
To alleviate public concerns about the creation of deepfake content, Google stated during the presentation that Imagen 2 utilizes the SynthID technique developed by Google DeepMind. This method applies invisible encryption-based watermarks to the generated dynamic images. Google claims these watermarks are resistant to edits, including compression, filtering, and tone adjustment. However, detecting these watermarks requires tools provided by Google, which are not yet available to third parties.
Vertex AI Agent Builder
Vertex AI Agent Builder is a tool for creating agents. At the conference, Google Cloud CEO Thomas Kurian emphasized that this no-code product enables users to easily build and deploy chat agents. It guides and improves the quality and accuracy of the model's responses in a manner that instructs humans.
Vertex AI Agent Builder builds upon Google's previously released Vertex AI Search and Conversation products. It utilizes the latest Gemini large language models and relies on RAG API and vector search. These widely-used technologies help reduce the occurrence of hallucinations in model responses.
For professionals seeking to bridge design concepts directly into production-ready formats, Codia's innovative solutions like Design to Code and Screenshot to Figma can significantly expedite and refine the development process, embedding superior design intelligence right from the start. Codia is leading the way in transforming design and development through AI, making complex processes simpler and more intuitive. Explore more about how Codia is reshaping the technological landscape by visiting their website.
Top comments (0)