Urgent.News

What's breaking now, across thousands of outlets.

AI

Gemini is getting rid of Gems, and its replacement aims to make repetitive work a lot easier

It introduces some key new features that make them better than Gems.

Gemini is getting rid of Gems, and its replacement aims to make repetitive work a lot easier

Gemini's skills are a new feature that lets you save frequently used instructions and run them without repeating prompts. These skills are now available globally in Gemini chat and will be introduced to Google Workspace clients soon. Once a skill is created, you can easily access it by typing "/skill name" in the prompt bar. This feature can streamline tasks such as generating custom skills from past chats and automatically running them with matching prompts.

You can also combine multiple skills to work on larger projects, like using a writing style skill with brand guidelines to produce on-brand content. Additionally, skills can now include reference files such as text documents, PDFs, or images. In the upcoming weeks, skills will gain features similar to Gems, like the ability to share with others and incorporate files from Google Drive and Gemini Notebook.

Starting November, support for Gems will be discontinued, followed by the removal of Opal in November and Gems for Workspace education in June. If Gems are phased out, they will automatically convert into skills. Gemini skills are accessible across all Google AI subscription tiers, with U18 access coming soon.

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

This story

This is one outlet's version. Read the fullest account.

Read the original at xda-developers.com →

More in AI

What agent frameworks cost on the wire: measurements from agentic-arena

Most framework comparisons argue from feature lists. I wanted numbers, so agentic-arena holds the model, tools, datasets and iteration budget fixed and measures what each framework does differently.

  • Vanilla baseline uses 753.5 prompt tokens per item in a 15-item tool-use task
  • smolagents framework uses 3,295.5 tokens, a 3.90x increase over vanilla baseline
  • smolagents is the only framework that can handle three consecutive 429 errors

More from Wednesday 30 September →