Google has announced an updated version of Gemini, saying that Gemini 2.0 Flash Experimental will "enable even more immersive and interactive applications", along with new coding agents that can take actions on behalf of the developer.

Google has used the name Gemini both for its conversational chatbot previously known as Bard, and its multimodal large language model (LLM) developed by Google DeepMind. Gemini Pro refers to the LLM.

The updated version of Gemini is twice as fast as the previous release, according to Google, and also includes new multimodal outputs, and comes with native tool use. Google also announced the introduction of a Multimodal Live API for building dynamic applications with real-time audio and video streaming.

Gemini 2.0 Flash is available via the Gemini API in Google AI Studio and Vertex AI during its experimental phase, with general availability coming early next year.

Alongside the improved performance, Gemini 2.0 Flash features improved multimodal, text, code, video, spatial understanding and reasoning performance. The improved spatial understanding enables more accurate bounding boxes generation on small objects in cluttered images, and better object identification and captioning.

Output options have also been extended, and developers will be able to use Gemini 2.0 Flash to generate integrated responses that can include text, audio, and images using a single API call.

This version also comes with multilingual native audio output, with a choice of eight voices and a range of languages and accents.

Native tool use is another improvement, with the option of natively calling tools like Google Search and code execution in addition to custom third-party functions via function calling.

A new multimodal live API means developers can now build real-time, multimodal applications with audio and video-streaming inputs from cameras or screens. Natural conversational patterns like interruptions and voice activity detection are supported.

Alongside the improvements to Gemini, Google has also announced a new developers tool. Jules is described as an AI-powered code agent that can handle Python and JavaScript coding tasks. Jules uses Gemini 2.0 and will handle bug fixes and other time-consuming tasks. Jules creates comprehensive, multi-step plans to address issues, efficiently modifies multiple files, and even prepares pull requests.

Developers can review the plans Jules creates and provide feedback or request adjustments before deciding whether to merge the code Jules writes into their projects.

Google says it is making Jules available for "a select group of trusted testers", and will make it available for other interested developers in early 2025.

Gemini 2 is available now in Google AI Studio.

More Information

Google AI Studio

Sign Up Page For Jules

Related Articles

Google Releases Gemini Code Assist Enterprise

Gemini Offers Huge Context Window

Gemini 1.5 Pro Now Available

Google Rebrands Bard As Gemini With Subscription

Google Releases Gemma Open Models

Google Adds Gemini To Bard

Google Adds Code Generation To Bard

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info