Now, our project had direction.
Using the AI again, I created a script that prompts and directs MLX to create a SPL-Token.
This script will be connected to Solana via hardhat as it stated earlier, and facilitate the deployment of our token in an automated process.
Many of you might not be aware, but Apple just released its "Chat GPT", named MLX Chat.
A LLM & AI Model that can do pretty muich everything... including crypto.
An example of Apple MLX power and "hackability": visualizing model confidence. NeuralBeagle14 here.
I'm "playing" with code to add --colorize param to mlx_lm to be able to show confidence of the model on the next token using standard top_p algorithm.
I started from
@antirez
…
Asking Apple's AI to write the Rust code for our token itself did the job.
It has a pretty long database on coding, including Rust and Solidity, and it promptly gave us a more satisfying result.
Just in time for the holidays, we are releasing some new software today from Apple machine learning research.
MLX is an efficient machine learning framework specifically designed for Apple silicon (i.e. your laptop!)
Code:
Docs: