nedoPC.org

Also, Shaos what do you mean a higher form of logic? Do you have something in mind?

> Can you explain ternary computers?

Ternary computers are computers that use ternary logic instead of the more common binary logic. Ternary logic uses three values: 0, 1, and -1. This allows ternary computers to perform some operations more efficiently than binary computers.

Ternary computers have been around for many years, but they have never been widely adopted. There are a number of reasons for this. One reason is that ternary computers are more complex to design and build than binary computers. Another reason is that ternary computers are not as compatible with existing software and hardware as binary computers.

However, there are a number of potential advantages to using ternary computers. One advantage is that ternary computers can perform some operations more efficiently than binary computers. Another advantage is that ternary computers can be more energy-efficient than binary computers.

As the cost of designing and building ternary computers decreases, it is possible that we will see more widespread adoption of this technology. Ternary computers could be used in a variety of applications, including artificial intelligence, machine learning, and cryptography.

The researchers' approach involves two main innovations: first, they created a custom LLM and constrained it to use only ternary values (-1, 0, 1) instead of traditional floating-point numbers, which allows for simpler computations. Second, the researchers redesigned the computationally expensive self-attention mechanism in traditional language models with a simpler, more efficient unit (that they called a MatMul-free Linear Gated Recurrent Unit—or MLGRU) that processes words sequentially using basic arithmetic operations instead of matrix multiplications.

Third, they adapted a Gated Linear Unit (GLU)—a gating mechanism to control information flow in neural networks—to use ternary weights for channel mixing. Channel mixing refers to the process of combining and transforming different aspects or features of the data the AI is working with, similar to how a DJ might mix different audio channels to create a cohesive song.