This model ain't ChatGPT or Claude or whatever. it also is not Sora or Chatgpt image or- you get the point. It's a POC of how models improve and the same thing could be applied to an LLM. it starts out printing random numbers, but a built in "un-AI trainer" trains it to only output odd numbers. (numbers 1-20) (You will see this text again if you go to the site!)
https://github.com/Dan-1118/ML-model-mini-POC-of-model-improvement-SEE-DESC/tree/main
