manish.sh
Digital Media · Content Creation
Overview
Manish Shahi is a software engineer and AI developer who writes the Inside LLMs series — reverse-engineering assistants by interviewing them, then auditing claims against papers — along with MCP server guides, agent tooling walkthroughs, and practical notes on models and developer workflows.
News
Inside Character.ai: The Technical Story of What Keeps Users Hooked manish.sh
From c.ai to Character.ai - what it is, the problem it solves, then Kaiju, memory, Lorebook, and the infra behind long chats.
Read more
Report
Inside Qwen 3.8-Max-Preview: Reverse Engineering an AI Assistant by Interviewing Itself manish.sh
I interviewed Qwen 3.8-Max-Preview on memory, tools, context, and hallucinations, then checked published research. Plain English, diagrams, transcript.
Read more
Report
Inside DeepSeek: Reverse Engineering an AI Assistant by Interviewing Itself
Interviewed DeepSeek on how it works, then checked against papers. Same method as Kimi - plainer English and concept diagrams.
Read more
Report
Inside Kimi K2.6: Reverse Engineering an AI Assistant by Interviewing Itself
I interviewed Kimi on memory, tools, and safety, then checked published research on K2.6. Plain English, diagrams, sources.
Read more
Report
How I Built an MCP Server in PHP for Fayyaz Travels
Fayyaz Travels is an Inncelerator client. I shipped PHP MCP for site analytics first. Flights, hotels, holidays, and ticket email come next.
Read more
Report
Give Your Agents Power to Purchase: Agentcard.sh Go-To Guide
Agents fill carts then stall at checkout. Agentcard.sh issues capped one-time Visas so they can finish buying - MCP, Companies wizard, and when not to use it.
Read more
Report