Kenneth Ryan Turner

I'm building FORGE because I want AI to do more than just answer questions and spit out code.

FORGE is a dual-AI system I've been developing since 2025, built around two specialized brains that work together.

🧠 JB handles reasoning, planning, engineering, and verification.

⚡ MARI handles coding, conversation, memory, and creative problem-solving.

A Supervisor oversees the system, with approval controls and memory designed to keep track of where information comes from.

The goal? I want to eventually tell FORGE to build an entire software system and have it plan the work, write the code, check for mistakes, and explain what it's doing.

Right now, I've got a working prototype and an evaluation system with 301 automated tests passing. I'm testing whether two specialized AI brains actually perform better together instead of just assuming they do.

I'm not claiming I've built the smartest AI in the world. I'm building something I intend to prove works.

Still early. Still testing. Still building.

I'm looking to connect with AI developers, researchers, founders, and people who want to challenge the technology and help make it better.

Everybody wants to build the next big AI. But here's my question. Who's making sure the damn thing is actually right?

I've been building FORGE since 2025, and one thing I've learned is that getting AI to give you an answer is easy. Getting it to give you the RIGHT answer, explain why, and catch its own mistakes? That's a whole different story.

That's why I'm building FORGE differently.

I've got two AI brains working inside one system.

🧠 JB handles reasoning, planning, engineering, and checking the work.

⚡ MARI handles coding, conversation, memory, and creative problem-solving.

Then I've got a Supervisor watching over both.

Now here's the part I think matters most.

I'm not going to sit here and tell everybody I've built some revolutionary AI just because I got two models talking to each other.

I want to PROVE they're better together.

We've got 301 automated tests passing on the evaluation system. But those tests don't prove FORGE is smarter. They prove we're building a way to find out.

And believe me, I've broken this thing more times than I can count. 😂

But that's building. You find what's wrong, fix it, test it, and keep going.…

Been a hell of a journey building FORGE, but things are starting to get interesting.

When I first started this project, I had one goal. I wanted to build an AI system that could actually remember, reason, develop software, and work alongside me instead of just answering questions.

That idea turned into FORGE.

Right now I've got two specialized AI brains working within the system.

JB handles the heavy thinking. Reasoning, engineering, planning, and checking work.

MARI handles conversation, development, and memory.

The goal is to get them working together, challenging each other's answers, catching mistakes, and eventually taking on entire development projects with proper oversight.

But here's the big update.

I'm officially taking FORGE into AI research.

We've started putting together our first formal study, testing whether two specialized AI agents working together can actually outperform a single model.

And I'm not talking about running a couple of prompts and calling it groundbreaking.…

I'm Kenneth Ryan Turner, but I go by John.

I'm the independent developer and creator behind FORGE, an ambitious AI project I'm building to explore what happens when specialized AI systems work together as one.

FORGE is being developed around two distinct AI brains:

🧠 MARI — Conversational Intelligence
Focused on natural communication, persistent memory, personality, contextual understanding, and human-AI interaction.

⚡ JB — Reasoning & Development Intelligence
Focused on complex reasoning, software engineering, autonomous coding, planning, and problem-solving.

The bigger vision?

An AI ecosystem that doesn't just answer questions, but can collaborate, build software, tackle complex development challenges, and become increasingly capable through real engineering improvements.

FORGE is currently in private development and testing. I'm focused on measurable intelligence, reliability, security, and genuine functionality — not flashy demonstrations.

Why I'm here:

I'm looking to connect with experienced AI engineers, founders, researchers, technical mentors, and potential investors who believe independent developers can build meaningful technology.…