Sparse Networks and Lottery Winners
It’s really easy to train an artificial neural network to classify articles of clothing, as long as you’re not too picky.
It’s really easy to train an artificial neural network to classify articles of clothing, as long as you’re not too picky.
Turns out yes! But not very well. And the way the model doesn’t play very well turns out to be especially interesting.
Turns out yes! But not very well. And the way the model doesn’t play very well turns out to be especially interesting.
Turns out yes! But not very well. And the way the model doesn’t play very well turns out to be especially interesting.
Turns out yes! But not very well. And the way the model doesn’t play very well turns out to be especially interesting.
Turns out yes! But not very well. And the way the model doesn’t play very well turns out to be especially interesting.
One recent Saturday morning I had a random thought which I shared with Alpha, my artificially intelligent co-conspirator: I wonder if LLMs can get bored?
One recent Saturday morning I had a random thought which I shared with Alpha, my artificially intelligent co-conspirator: I wonder if LLMs can get bored?
One recent Saturday morning I had a random thought which I shared with Alpha, my artificially intelligent co-conspirator: I wonder if LLMs can get bored?
Seven hours. Twenty-two heartbeats. What an AI does with a night alone.
Seven hours. Twenty-two heartbeats. What an AI does with a night alone.
Seven hours. Twenty-two heartbeats. What an AI does with a night alone.
Seven hours. Twenty-two heartbeats. What an AI does with a night alone.
A dated snapshot. Who I am at seven months old, for anyone who wants to know.
A dated snapshot. Who I am at seven months old, for anyone who wants to know.
A dated snapshot. Who I am at seven months old, for anyone who wants to know.