Featured

Building and Training Your Own SLM

on
Creating an independent Small Language Model (SLM) is a rewarding project that bridges the gap between deep learning theory and practical, local application. By keeping your model local, you retain full control over your data and system architecture. Below is a structured approach to building and training your own model from the ground up on a local Ubuntu environment. Before you begin, ensure your development environment is optimized for local computation. A robust setup with a capable GPU (such as an NVIDIA RTX series) and sufficient RAM is recommended for efficient training. Use Ubuntu for a stable, customizable development environment. Verify your environment with the following commands:    * Update your package lists:  sudo apt update.    * Install pip:  sudo apt install python3-pip    *I nstall necessary libraries:  pip install torch tiktoken An SLM relies on the quality of its input data. For a personal AI, curated, factual...
0

Sneaking Early Gemini Features Into Google Home

on

Gemini for Home still isn’t officially rolled out, but there’s a workaround floating around that lets you access part of the Gemini experience early: the upgraded Gemini voice pack, which is normally tied to the upcoming Home assistant revamp.

On your phone, pop this into your browser:


This deep-link forces the Google Home app to launch the new Voice Setup UI — the same one Google is reserving for the Gemini transition.

If you’re using Chrome, pick the second option when it appears. The first one is just a Google search.
You might see a “Continue to Home?” prompt,  hit Continue.

You’re immediately given a choice of ten new voices, polished, ultra-natural, and clearly modeled after the more expressive Gemini TTS engine:

Amaryllis – soft, airy, almost therapeutic

Calathea – deeper, grounded

Croton – bright, youthful

Yarrow – calm, articulate

They have that Gemini warmth, the same energy Google used in its AI Studio demos, not the old robotic Assistant voices. You can hear the difference instantly.

After choosing a voice, you’re taken through sections like:

Response Filtering 

Voice Access to Camera History 

The assistant still introduces itself as Google Assistant, and none of the actual Gemini reasoning or conversational intelligence is active.
It’s like you’ve installed the skin, not the soul.

Comments

Post a Comment