awacke1's picture
Update README.md
f25c363
|
raw
history blame
526 Bytes
metadata
title: AI Generating AI From Transcript
emoji: πŸƒπŸŒŸπŸ”
colorFrom: yellow
colorTo: green
sdk: streamlit
sdk_version: 1.17.0
app_file: app.py
pinned: false
license: mit
  1. ML:

  2. Theoretically optimal hypothesis regarding short programs

  3. The shortest program that fits training data is the best possible generalization.

  4. RL:

  5. We figure out what the reward is by observation

  6. We reward ourselves - it is our interpretation of our senses

  7. There is only one true reward in life: existence vs. non-existence