minssam.
474 POSTS

Archive.

AI, education, tools, and the ideas that connect them.

NOTE / 086

Search Text, Images, and Audio Simultaneously on Your Device — EmbeddingGemma 2 Deep Dive

Google DeepMind's EmbeddingGemma 2, released on October 6, 2026, is an open-source multimodal embedding model that maps text, code, images, video, and audio into a single 768-dimensional space. With 740M parameters running entirely on-device, it enables AI-powered search over student notes, lecture videos, and audio recordings — all without an internet connection.

EmbeddingGemma2READ MORE ↗
NOTE / 087

Gemini 3.8 Live Extended Thinking: The AI That Reasons While It Speaks

Google DeepMind's Gemini 3.8 Live Extended Thinking, released to general availability on September 15, 2026, is an audio-to-audio model that performs deep reasoning during live voice streaming. It ranked #1 on Artificial Analysis' Speech-to-Speech leaderboard, and its asynchronous function calls keep audio flowing even while complex tools run in the background.

Gemini38LiveREAD MORE ↗
NOTE / 090

NotebookLM Is Now Gemini Notebook — and It Can Run Code Inside Your Notes

Google officially renamed NotebookLM to Gemini Notebook on July 16, 2026. Beyond the name change, each notebook now has its own secure cloud computer that can write and run code, generate charts, and export spreadsheets and slide decks. The product has shifted from a reading-and-summarizing tool to an analysis-and-output platform.

GeminiNotebookREAD MORE ↗
MINSSAM.COM