Energy
Energy Engine is a framework for human recreation that attempts to allow computers to be virtually identical to a real-world human in a 3D contextual space. Rather than attempting to pass a singular Turing test involving a one time chat and a judge, Energy aims to solve indistinguisability in a 4D, world-wide context.
Research Areas
Energy aims to address 6 limited areas of modern day ML models by developing & integrating solutions.
Performance Testing
We establish hard coded metrics to ensure our model is improving. These are tests/benchmarks custom designed, used on previous models and models from other vendors. Youtube is one of Energy-Chan's metrics, providing ATHR with access to feedback/reviews.
Memory
Our model must be able to store and retrieve data in a human-like manner. To do this, we developed a complex system HLGraphRAG, inspired by Microsoft's GraphRAG, using weighted retrival graphs, allowing for high performance recall.
Movement
Our model is capable of moving, conducting actions such as waving a hand when they want to or conducting executions on a computer.
Real-time model & World
Our model is capable of keeping track of a world, having real-time updates to its information to make the best and personalized choices with low response times.
AGI
With every event/stream, our model gains new knowledge from the world and learns something new. Improving its score on tests is expected, intuition is not.
Reinforcement
The model has low rates of erroneous data. It's output matches the personality of the character, and it makes sense in a real world context.
Streaming Schedule
The first stream (YT) is planned to be sometime in 2025. This may be pushed back depending on development of the model. I intend to stream every 2ish so weeks, subject to my availability. If there is a busy week or month, there may not be a stream.
Content of Streams
The stream is estimated to follow this breakdown:
- 30 minutes of implementation/work
- 20 minutes of testing
- 10 minutes of just driving the model around with life (random content like a clash of clans attack, a CS lecture, a MLBB match, etc)
As the model progresses, it is likely that the implementation time decreases and the model driving time increases.
FAQ
Where to find the streams?
I will update this repo with a link sometime later.
What is the different between this model and other current-day AI Youtube content such as Vedal & Neuro?
The difference is that Energy-Chan is primarily a research prototype that has entertainment as a metric. In addition, there are a few components of Energy-Chan not found in Neuro, such as 3D-spatial movement and the memory engine (HLGraphRAG) used for high performance recall.
Code for AXNE?
Unfortunately, I have opted not to disclose the code for Auxilary Neural Engine. Energy-Chan is essentially proprietary, albeit this may change in the next few years or so.