Bug0 uses Gemini 2.5 Pro’s multimodal reasoning capabilities to automate testing and cut manual debugging by 60%. Integrating the model for two primary functions, AI assertion and agentic failure summarization, vastly improved the platform’s debugging workflows and reliability. Explore how they did it: https://goo.gle/42PrUVO
Google AI for Developers
Technology, Information and Internet
AI for every developer. So what will you build?
About us
Our goal is to equip developers with the most advanced models to build new applications, helpful tools to write better and faster code, and make it easy to integrate across platforms and devices.
- Website
-
https://goo.gle/ai-devs
External link for Google AI for Developers
- Industry
- Technology, Information and Internet
- Company size
- 10,001+ employees
Updates
-
Grounding with Google Maps is now available in the Gemini API📍https://goo.gle/46YjY7b The new feature connects the multimodal capabilities of Gemini models with the real-world data of Google Maps (from 250 million places) allowing devs to build a new class of geospatial-aware AI apps. Learn to enable the Grounding with Google Maps tool in your Gemini API request, and get: - Hyper-local recommendations - Place-based answers - Route and distance calculations - Check out the docs: https://goo.gle/4qgrgKZ - Remix the demo app: https://goo.gle/3KS846a
-
-
AI Studio starter apps give you the code and inspiration to build your next big idea. Remix any app, like the Home Canvas example shown here, and customize it to your vision with a single prompt. Go from idea to deployment → https://goo.gle/4gHeDEs
-
Google AI for Developers reposted this
CEO of Latitude | Built AI Dungeon (8M+ downloads) | Building Voyage: A platform where you can be anyone, do anything, in any world you imagine.
We’ve been working with Google exploring the the future of storytelling with AI video and super excited for the new version of Veo 3.1 to be public. Check it out! https://lnkd.in/g9qYY3ad
-
With Gemini CLI's new pseudo-terminal (PTY) support, you can run complex, interactive commands like vim, top, or git rebase -i directly within the CLI without having to exit, keeping everything in context. How it works: We serialize the terminal state, streaming it to you in real-time. This enables full two-way interaction for commands that require rich terminal capabilities. Learn more and get started: https://goo.gle/42IxQzN
-
🎙️ Get a technical deep dive into Veo, Google's state-of-the-art text-to-video model with native audio. Google DeepMind's Dumitru Erhan and Logan Kilpatrick discuss the evolution from early video prediction models and key engineering challenges such as model evaluation, scaling video models, and integrating physics-based realities. Watch the full Release Notes episode → https://goo.gle/3JaQCt0
-
Introducing C2S-Scale 27B, our new Gemma open model that can translate complex single-cell gene expression data into “cell sentences” that LLMs can understand. ⚕️ https://goo.gle/47e7tTS The 27B model, built for single-cell analysis using the Gemma family of open models, has identified a novel cancer therapy pathway that’s been validated experimentally in living cells. A major challenge in cancer treatment is that some tumors are invisible to the body’s immune system. C2S was able to predict a drug that would positively boost immune signals, and showed a potential pathway to make tumors more responsive to immunotherapy. Check out resources on Hugging Face: https://goo.gle/493e99I Access the code on GitHub: https://goo.gle/4optZQE
-
-
🎥Veo 3.1 & Veo 3.1 Fast are now available in paid preview in the Gemini API → https://goo.gle/48xMRrU These upgraded Veo models give devs higher-quality outputs, audio support, and new creative controls for more precise video generation. Veo 3.1 improvements: + Richer native audio and dialogue + Better narrative control + Improved image-to-video capabilities New controls in Veo 3.1: > Scene extension → video_to_extend > First and last frame → first_frame, last_frame > Ingredients to video → reference_images Start building: - API Docs: https://goo.gle/47dYpyk - Cookbook: https://goo.gle/4hgyFpA
-
Spend less time on issue triage and more time coding → https://goo.gle/4oabQWS Gemini CLI GitHub Actions is your AI coding teammate that acts as both an autonomous agent and an on-demand collaborator for your repository. 🔹 Intelligent issue triage 🔹 Accelerated pull request reviews 🔹 On-demand collaboration
-
AI-first Google Colab improves productivity as your coding partner to unlock data science, machine learning, and AI workflows. Go from an empty notebook to full analysis and interactive visualizations without writing code yourself. Try out it out → https://goo.gle/4obKMpY