Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Chyral: Embed LLMs Natively
Learn to embed and run language models natively in apps and websites for enhanced security and reduced latency, with a live demo of a browser with its own LLM.
I am going to show how to embed large/small language models natively to any apps or even websites without the support of internet, not only this is quite interesting for businesses which require security policies but it also gives extra flexibility to platforms with fine grained control.
I am going to showcase my browser called Chyral as an example which has it’s very own small language model as a web browsing companion, also some tricks, softwares and tools to help embed such capabilities to your app or software!
Chyral is a privacy-first browser utilizing local, offline AI for agentic automation.
- C++C++ is the compiled, multi-paradigm powerhouse (procedural, OOP, generic) designed by Bjarne Stroustrup for high-performance systems, from operating systems to AAA game engines.C++ is the multi-paradigm (procedural, object-oriented, generic) programming language created by Bjarne Stroustrup in 1985, originally as an extension of C. It delivers a critical combination: low-level memory control and high-level abstraction, making it the premier choice for performance-critical applications. This includes major operating systems (like Windows and Linux), embedded systems, and demanding software like the Unreal Engine or Adobe products. The ISO/IEC JTC 1/SC 22/WG 21 committee continuously evolves the standard, with the latest being C++23 (ISO/IEC 14882:2024), ensuring modern features (e.g., modules, coroutines) integrate without compromising the language's core zero-overhead principle. It remains the essential engine for systems where speed and resource management are non-negotiable.
Related projects
Building an AI on-call engineer
Dhaka
Explore Aster, an AI on-call engineer. Learn its current functionality, architectural choices, and practical LLM engineering patterns from…
Building the Filter for AI Generation: Solving "Insight Blindness" with Matryoshka Embeddings
Dhaka
Learn how to overcome "Insight Blindness" in AI generation with Matryoshka embeddings. This demo shows a production pipeline…
How to build good skills for LLMs
Dhaka
Learn to build effective LLM skills that enhance capabilities without overwhelming context, preventing hallucinations. This talk shares practical…
Building a Persistent Memory & Stateful Second Brain AI Agent
Dhaka
Learn how to build a stateful AI agent with persistent memory using Obsidian and context engineering. This talk…
Vibe Coding to Production: A PM’s LLM Pipeline for OE Data Cleaning
Dhaka
Learn how to build a real OE data cleaning system using Claude, GPT-4 mini, and Apps Script, moving…
Local LLM Orchestration with LangChain & LM Studio
Manchester Nh
Compare building a multi-perspective LLM tool using pure Python, LangChain, and Prompt Flow to understand framework trade-offs on…