Source URL: https://simonwillison.net/2025/Jun/26/geminiception/
Source: Simon Willison’s Weblog
Title: Geminiception
Feedly Summary: Yesterday Anthropic got a bunch of buzz out of their new window.claude.complete() API which allows Claude Artifacts to run their own API calls.
It turns out Gemini had beaten them to that feature by over a month, but the announcement was tucked away in a bullet point of their release notes for the 20th of May:
Vibe coding apps in Canvas just got better too! With just a few prompts, you can now build fully functional personalised apps in Canvas that can use Gemini-powered features, save data between sessions and share data between multiple users.
Ethan Mollick has been building some neat demos on top of Gemini Canvas, including this text adventure starship bridge simulator.
Similar to Claude Artifacts, Gemini Canvas detects if the application uses APIs that require authentication (to run prompts, for example) and requests the user sign in with their Google account:
Tags: vibe-coding, gemini, generative-ai, ai, llms, google
AI Summary and Description: Yes
Summary: The text discusses the introduction of the window.claude.complete() API by Anthropic, allowing Claude Artifacts to run API calls, and notes that Gemini had previously implemented a similar feature, which enhances the usability of its Canvas platform for building applications. This development emphasizes the competitive landscape in generative AI and highlights the implications of user authentication within the API usage.
Detailed Description:
– **Anthropic’s New API**: Anthropic recently announced their window.claude.complete() API, enabling Claude Artifacts to conduct their own API calls. This development signals a significant step in the evolution of AI tools, particularly for generative models.
– **Gemini’s Precedence**: The text notes that Gemini had previously delivered a comparable feature over a month prior, though this was not prominently featured in their promotional materials. This suggests a need for companies to better highlight important updates to capture user attention.
– **Functionality of Gemini Canvas**:
– Users can now create personalized coding applications in Gemini Canvas with enhanced capabilities.
– Ability to use Gemini-powered features, which allows for dynamic data handling—saving and sharing data across sessions and among multiple users—improving collaborative efforts in app development.
– **User Authentication Feature**:
– Gemini Canvas incorporates an authentication mechanism which prompts users to sign in with their Google account if the application requires authenticated API usage. This highlights the importance of secure access in deploying generative AI applications, ensuring that only authorized users can interact with specific features.
– **Community Engagement**:
– Noteworthy individual contributions, such as demos from Ethan Mollick, showcase innovative applications using Gemini Canvas, indicating a vibrant community of developers exploring creative uses of generative AI.
**Implications for Security and Compliance Professionals**:
– The race between AI companies like Anthropic and Gemini emphasizes the necessity for continuous innovation and secure API management within generative AI.
– Developers should be aware of the importance of user authentication to safeguard sensitive data in AI applications.
– As these tools evolve, the landscape of security will need to adapt to incorporate best practices for privacy and compliance in accordance with emerging technologies.
Overall, this announcement is pivotal for professionals in AI security, indicating shifts in capabilities that may affect how applications are developed and secured moving forward.