Geeky Gadgets

The Latest Technology News



Julian Horsey

Author Archives:

Julian Horsey

Executive Editor & Co-Founder of Geeky Gadgets

Julian Horsey is the co-founder of Geeky Gadgets and a veteran technology journalist with over 18 years of experience. A published author and multimedia designer, he specializes in emerging frontiers including Artificial Intelligence, autonomous agents, and next-gen hardware like mini PCs and wearables.

Driven by curiosity and a passion for design, Julian provides in-depth analysis on how AI workflows—from Claude to Google Gemini—are transforming productivity and creativity. His work has been cited by global tech leaders and major publications, reflecting nearly two decades of expertise in 3D printing, AR/VR, and DIY electronics. When not exploring the latest AI models, he is an avid maker and experimenter in the world of DIY tech.

Connect with Julian:
X / Twitter | Muck Rack

7 NotebookLM Tips : Manage Notebooks, Sources & Multimodal Inputs for Teams

By

Google's NotebookLM offers a structured way to manage information, streamline workflows, and enhance AI-driven tasks. As explored by AI LABS, this platform acts as a centralized knowledge hub, helping users organize data, synthesize insights, and reduce inefficiencies. With features like multimodal … [Read more...] about 7 NotebookLM Tips : Manage Notebooks, Sources & Multimodal Inputs for Teams

Claude Cowork Plugins Centralize Work Across SaaS Apps, Reducing Tool Switching

By

Claude Cowork, created by Anthropic, features a modular plugin system designed to enhance automation and simplify workflows. According to Ben AI, this system allows businesses to integrate software platforms, automate repetitive tasks, and customize processes without requiring advanced technical … [Read more...] about Claude Cowork Plugins Centralize Work Across SaaS Apps, Reducing Tool Switching

OneNote Integration Guide 2026 : Loop, Teams, Outlook, Word & PowerPoint for Faster Follow-Up Work

By

Microsoft OneNote offers a range of integrations with Outlook, Loop, and Teams, allowing users to streamline workflows and enhance collaboration. As outlined by Mike Tholfsen, these integrations allow you to manage tasks, share updates, and collaborate in real time without switching between … [Read more...] about OneNote Integration Guide 2026 : Loop, Teams, Outlook, Word & PowerPoint for Faster Follow-Up Work

OpenClaw Joins OpenAI : Raising Questions About Its Open Source Future

By

OpenAI has acquired OpenClaw, a platform specializing in AI agents capable of performing tasks autonomously. As explained by Sam Witteveen, OpenClaw offers features like sandboxed code execution for secure scripting and persistent memory that allows agents to retain knowledge across sessions. The … [Read more...] about OpenClaw Joins OpenAI : Raising Questions About Its Open Source Future


Building AI-First Automations with Trigger.dev, Modal, and Supabase

By

AI-first workflow automation allows you to design, execute, and monitor processes with greater efficiency by using artificial intelligence and natural language processing. As outlined by Jannis Moore, this approach simplifies traditionally complex tasks, such as defining workflows or managing data … [Read more...] about Building AI-First Automations with Trigger.dev, Modal, and Supabase

Thinking on Paper Method: Make It Wrong, Shorter, Then Rewrite for Better Recall

By

Thinking on paper is a structured approach to learning that emphasizes externalizing your thoughts to reduce mental overload and improve understanding. As explained by Justin Sung, this method involves three key principles: "Make it Wrong," "Make it Shorter," and "Make it Again." By starting with … [Read more...] about Thinking on Paper Method: Make It Wrong, Shorter, Then Rewrite for Better Recall

Minimax M2.5 Benchmarks : Targets $1 per Hour for 100 Tokens per Second

By

The Minimax M2.5 is a compact yet capable AI model that combines affordability with competitive performance, as detailed by Sam Witteveen. With a processing cost of just $1 per hour for 100 tokens per second, the M2.5 offers a cost-effective alternative to larger models like GPT-5.2 and Claude Opus. … [Read more...] about Minimax M2.5 Benchmarks : Targets $1 per Hour for 100 Tokens per Second

5 Powerful Gemini 3 AI Features Hidden in Plain Sight for Improved Productivity in 2026

By

Google Gemini includes a range of AI-driven features that support productivity and simplify workflows. While its primary functions are widely recognized, Paul J Lipsky highlights several lesser-known capabilities that can make a meaningful difference in daily tasks. For instance, the "Files in this … [Read more...] about 5 Powerful Gemini 3 AI Features Hidden in Plain Sight for Improved Productivity in 2026


YouTube App for Apple Vision Pro Supports Dolby Vision 8K HDR Playback

By

The release of the visionOS YouTube app on the Apple Vision Pro introduces a new way to experience video content in immersive virtual environments. By using the Vision Pro's spatial computing capabilities, the app supports features like 360° and 180° video formats and gesture-based navigation, … [Read more...] about YouTube App for Apple Vision Pro Supports Dolby Vision 8K HDR Playback

MiniMax M2.5 Uses 10B Active Parameters per Token, Aiming for Cheaper Always-On Agents

By

The MiniMax M2.5 is an advanced AI model designed to balance high performance with cost efficiency, as explained by Caleb Writes Code. Building on its predecessor, the M2.1, this model incorporates a sparse activation mechanism that activates only 10 billion parameters per token, or 4% of its total … [Read more...] about MiniMax M2.5 Uses 10B Active Parameters per Token, Aiming for Cheaper Always-On Agents


Geeky Gadgets