Get Locked in with the Power of Autonomous AI

Who it's for

G6 is a platform for professionals who want to build AI to perform specialist human jobs that cannot otherwise be automated using existing state of the art techniques. It is not limited to a certain domain and is designed to be fully extensible. Think of the system as being like a set of intelligent Lego blocks which can be put together in whatever way you want.

What it's not designed for

G6 is not designed to perform simple tasks that can be solved by existing chatbots (if you need something like this, please see ChatGPT from OpenAI or Anthropic's Claude). Similarly, although the system is not specifically designed for building simple websites or writing simple/boilerplate code it can be used for this. Instead, it is designed to build solutions to otherwise intractably difficult, complex, high stakes and/or potentially as yet unsolved real world problems.

Our offering

G6 is a platform for developing no code AI applications that can be used autonomously to solve real world problems. It is designed to allow domain specialists (e.g. engineers, programmers, scientists, clinicians, finance professionals, lawyers, business people etc.) to design AI solutions for the hardest problems which they encounter on a daily basis.

Our mission

Simply put, G6 allows people to build sophisticated software solutions to otherwise impossible problems (i.e. problems which cannot be solved using large language models, machine learning or human written software alone).

Perspectives

G6 is a general-purpose AI for solving and building automated solutions to difficult real-world problems. There are a number of perspectives on G6:

1. A self-programming system.
2. A mathematical calculus for thought.
3. A no-code platform for building software.
4. A way for non-AI specialists to build AI applications.
5. An AI copilot for real-world problem solving.
6. A method for machine learning algorithms.
7. A system for teaching computers how to learn and think.
8. The next generation of declarative programming systems.

What you can achieve

Internally, the system has automated self-optimization. It also has the ability to learn from mistakes. One of the only limitations on the system is around safety and ethics, so please don't try to use the system to do anything illegal, dangerous, or immoral.

But we think you'll love it, and we also think the best way to learn about G6 is to try it.

No, but we find that people who know how to code are typically able to learn how to use the system faster than non-coders and can produce better results in less time. This means that the total cost of building a solution on G6 is typically less for people who are able to directly edit and refine code.

This is a very difficult question to answer and it really depends on the size and complexity of the problem you are solving. On average, using the system speeds up workflow by about 80% meaning that a simple problem typically takes about 5 man hours to solve however an extremely complex/open problem can take upwards of 100 man hours.

Yes, you can absolutely port code written in G6 to any platform at any time by copying and pasting from the user interface.

Objectives and System Design

G6 is a software as a service platform for real-world problem solving using AI. Prompts in G6 are called objectives: a specification of what you want to achieve. G6 will interact with you to achieve the objective, as long as it's not obviously illegal or immoral. G6 is written in G6 and is potentially an order of magnitude more complex than most state-of-the-art AI systems.

Internal Workings

It’s not straightforward to explain G6’s internal workings. Curious readers should check out answers 2 and 3. Still curious? Contact us about joining our team.

Get Started

G6 is super easy to use. The system guides you through the problem as you solve it. Each user's experience varies based on background, problem, and preferences—so just dive in and learn as you go.

About Fluid Intelligence

G6 gets its name from Spearman's G coefficient. Spearman theorized intelligence has two components: g (general intelligence) and s (specific intelligence). This idea is still influential in modern psychology.

6 Subsystems

The "6" refers to six subsystems working in parallel: a database engine, a creative/lateral thinking module, an LLM for language, a logic engine, a custom algorithm designer, and an 'intuitive scientist' for autonomous experimentation. These are coordinated as a 3-layer adaptive system based on Danko Nikolic’s theory of practopoiesis. It is an example of a so called 'seed AI'.

A Bit About LLMs

LLMs are powerful tools that are changing how we work, but they also have serious limitations. They struggle with creativity, logic, problem solving, and tasks that humans find trivial. While LLMs will continue to improve, they likely won’t achieve true general intelligence alone.

Why G6 Is Different

G6 only uses LLMs when they’re appropriate. Otherwise, it decomposes tasks into sub-problems and routes them to the most suitable subsystem. This enables a more robust, flexible, and reliable intelligence.

The Full Intelligence Toolkit

If LLMs are like a screwdriver, G6 is a full toolbox—wrenches, hammers, chisels, etc. You can build something far more complex, powerful, and creative. That’s why we call G6 artificial general intelligence as a software service.

Imperative vs Declarative Prompting

When prompting ChatGPT, you issue commands (imperative). With G6, you describe the outcome you want (declarative). It figures out how to get there.

Declarative Prompting Example

"Create a compelling story about a child who saves their village from a storm that I can share with my son as a bedtime story"

This prompt defines the goal, not the steps. G6 then decides how to achieve it.

Imperative Prompting Example

"Write a story. Begin with a boy waking up. Make sure he fights a storm. End it with him saving the town."

This prompt gives step-by-step instructions—suitable for LLMs, but not for G6’s more abstract reasoning abilities.