Understanding MCP (Model Context Protocol)
Understanding how LLMs talk to the external tools.
AI Authority
AI Authority is a developer community and blog that covers latest technology trends and development news for Artificial Intelligence enthusiasts.
Latest articles
What are Autoraters ?
Large language models (LLMs) produce certain output based on the input. How do we determine if the the output is correct or of good quality ? One way to do this is by employing humans who actually read the output and rate it. This of course is not sc...
Meta's Llama herd
Meta has released they new models. There are termed as Llama 4 herd. Llama 4 Models: The Scout model seems very interesting due to its relatively small size and less activated parameters. Llama 4 Scout: - 17B active parameters, 16 experts, 109B total...
Is AI going to take over programming jobs ?
Google’s chief scientist said that 25% of Google’s code is generated by AI. It this a death bell for the profession of software engineering ? As usual the truth is often not clear and predictions about future are often wrong. But again, the trends do...
Rise of Agentic AI
What is agentic ai and why it matters ?
Building for children: Android WearOS for Kids
The world of wearable technology is expanding rapidly, and Android WearOS has emerged as a versatile platform for developers to create innovative apps. While many WearOS apps cater to adults, there’s a growing opportunity to design apps specifically ...
Should India build its own Foundational Models ?
To train or not to train is a dillemma before poorer nations
StarGate : $500B US AI Initiative
Donal Trump is the new President of United States and he has wasted no time showing the world that he means business. One of the things he did was to declare project Stargate. This is supposedly AI project that involves OpenAI, Nvidia and Microsoft w...
DeepSeek - China taking us by storm
https://www.youtube.com/watch?v=Vt3DJNurS9U DeepSeek is a series of open-source large language models (LLMs) developed by a Chinese AI firm of the same name. It uses a Mixture-of-Experts (MoE) system, activating only the necessary parts of its neur...