Google has introduced LangExtract, an open-source Python library designed to help developers extract structured information from unstructured text using large language models such as the Gemini models. The library simplifies the process of converting free-form text into structured data, offering features like controlled generation, text chunking, parallel processing, and integration with various LLMs.
Opal is a new experimental tool from Google Labs that lets you build and share powerful AI mini apps that chain together prompts, models, and tools — all using simple natural language and visual editing. It's currently in public beta in the US.
This post explores how developers can leverage Gemini 2.5 to build sophisticated robotics applications, focusing on semantic scene understanding, spatial reasoning with code generation, and interactive robotics applications using the Live API. It also highlights safety measures and current applications by trusted testers.
A review of a Google paper outlining their framework for secure AI agents, focusing on risks like rogue actions and sensitive data disclosure, and their three core principles: well-defined human controllers, limited agent powers, and observable actions/planning.
A Google engineer's testimony shows how page quality is scored and confirms the existence of a popularity signal that uses Chrome data.
Google's AI function brings Gemini-powered language models right into your spreadsheet cells without any add-ons. With it, you can generate fresh text, summarize blocks of data, categorize entries, or even guess sentiments—all by typing a simple formula.
The article provides examples such as:
- *sentiment analysis* ```=AI("Is this customer feedback positive, negative, or neutral?", A2)```
- *data categorization* `=AI("Classify this expense as Travel, Office, or Other", D3)`
- *simple calculations* `=AI("Add the numbers in these cells", A1:A5)`
The article provides examples such as:
- *sentiment analysis* ```=AI("Is this customer feedback positive, negative, or neutral?", A2)```
- *data categorization* `=AI("Classify this expense as Travel, Office, or Other", D3)`
- *simple calculations* `=AI("Add the numbers in these cells", A1:A5)`
This article details the release of Gemma 3, the latest iteration of Google’s open-weights language model. Key improvements include **vision-language capabilities** (using a tailored SigLIP encoder), **increased context length** (up to 128k tokens for larger models), and **architectural changes for improved memory efficiency** (5-to-1 interleaved attention and removal of softcapping). Gemma 3 demonstrates superior performance compared to Gemma 2 across benchmarks and offers models optimized for various use cases, including on-device applications with the 1B model.
This document details how to run Gemma models, covering framework selection, variant choice, and running generation/inference requests. It emphasizes considering available hardware resources and provides recommendations for beginners.
Google's Gemini 2.5 Flash model is a new, faster, and more cost-effective model with adjustable 'thinking' capabilities. The article details how to use it with llm-gemini, explores pricing differences compared to Gemini 2.0 Flash, and shares example SVG outputs.
Google’s John Mueller downplayed the usefulness of LLMs.txt, comparing it to the keywords meta tag, as AI bots aren’t currently checking for the file and it opens potential for cloaking.
