Urgent.News

What's breaking now, across thousands of outlets.

AI

Gemini overlay crowding your phone screen? This nifty gesture could soon come to your rescue

Gemini could soon duck out of your way while it works in the background.

Gemini overlay crowding your phone screen? This nifty gesture could soon come to your rescue

Google is testing a new gesture that could soon allow users to minimize Gemini chat overlays on their phone screens. The gesture involves swiping left or right on the overlay, which keeps the chat running in the background without interrupting the user's ability to use the phone. This development comes as Google continues to work on making Gemini more useful even when it's not the primary focus of the device.

Earlier this year, reports emerged that Google was exploring ways to make Gemini work without taking up space at the top of the screen. Additionally, the option to offload tasks to Spark without fully opening the app was recently spotted. Now, the focus appears to be on enhancing Gemini's functionality in the background.

This Authority Insights story provides exclusive details about Google's efforts to integrate Gemini more seamlessly into the user experience. Authority Insights delivers the latest exclusive reports, app teardowns, leaks, and in-depth tech coverage from the Android Authority team, offering readers insights that are not available elsewhere.

Written by urgent.news from Android Authority's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at androidauthority.com →

More in AI

I Connected Claude to 20 Years of Azure SQL Data with a Custom MCP Server. Here's How.

A client came to me with a request that sounded simple: "We have 20 years of data in our database. We want our managers to ask Claude questions and get reports.

  • Client needed Claude to access 20 years of Azure SQL Database data.
  • Custom MCP server created on client's VPS to whitelist tables for Claude.
  • MCP server uses Node.js, SDK, and Zod to define secure data access.

LLM Wiki's Two-Step Chain-of-Thought Ingest: How Incremental Cache and Source Traceability Replace Traditional RAG

Traditional RAG systems retrieve chunks and answer from scratch every time. LLM Wiki takes a different path: it analyzes documents once, generates persistent wiki pages with full source traceability…

  • LLM Wiki uses a two-step chain-of-thought with incremental cache
  • Persistent wiki pages created after analyzing documents once
  • Caching intermediate results reduces cost of incremental updates

More from Tuesday 15 September →