Home

Problems with current AI

(copied over from the Discord)\

I had a quick go at mapping out an overview of what's relevant/missing in the quest to unlock machine intelligence.

Basically I'm thinking: What properties do bio-brains have that AI is lacking?

Here's the second draft:

# Considerations
What qualities does a neural engine need to have?

🔸 Homogeneity
    Neocortical tissue is homogenous.
    We want a basic computation mechanism that's abstracted away from input modality
    So image / audio / text / sensory / etc. data goes thru some initial layers
      INTO a generic neural engine

🔸 Local
    (bio-networks act locally, backprop requires global forward-then-backward)

🔸 Scale-Free
    letter <-> word, word <-> phrase, phrase <-> sentence, etc.
    Need a mechanism that handles arbitrary abstraction
    It's ugly to separate into fixed "N layers" (won't scale)

🔸 Energy efficiency / sparsity
    Transformers are fugly huge / inefficient
    bio-brains run at low watts. Only a small fraction of the brain NN is used for a computation,
    evolutionary forces have pushed us towards efficient computation. fastest reaction wins. (Genetic Algos + multimodal AI gym setups???)

🔸 Agency
    At what level is agency? Does it just sit on top of the LLM? Or can we see it as an emergent property from neuronal behaviour (competition/inhibition)
    - Recursion / looping
        Our brains loop. We learn to loop. e.g. socratic dialogue, problem-solving
        Dynamical systems / SSM / mamba / ...

🔸 Learning
    🔹 One-shot learning
        We don't need to get run over at 1000 red lights to learn to wait for the green when we cross the road
        - Our bio-system releases chemicals to strongly reinforce certain patterns

    🔹 Solidify early-learning
        Observe how our auditory cortex learns. Low-level is baked in before puberty.
        e.g. Dynamically add neurons. A neuron's learning rate decreases over time.

    🔹 Intelligent teacher-student training (curriculum learning)
        It's ludicrous to train an LLM on a million kids' stories
        Keep feeding the student challenges where it can solve say 70% of them

    🔹 Continual learning
        What if LLM can repeatedly contemplate, think/distill thoughts and fine-tune on these new conclusions?
        What if the engine can extract targeted information from its environment (e.g. read a new arxiv paper/blogpost)

    🔹 [TODO] Wake/Sleep / Dreaming

🔸 [TODO] Maslow's hierarchy of drives

🔸 [TODO] Evolutionary learning (neuroevolution?)