I found this hard to read. Can you give a concrete example of what you mean? Preferably with a specific prompt + what you think the model should be doing
This is powerful evidence that even though models are trained to output one word at a time, they may think on much longer horizons to do so.
from anthropics most recent release, mainly was the thought.
I was trying to fit that into how that behaviour shows up.
I found this hard to read. Can you give a concrete example of what you mean? Preferably with a specific prompt + what you think the model should be doing
This is powerful evidence that even though models are trained to output one word at a time, they may think on much longer horizons to do so.
from anthropics most recent release, mainly was the thought.
I was trying to fit that into how that behaviour shows up.