TBH sooner or later explaining the opaque recurrence with extrinsic logic will be more sustainable, and already there is a need for that with existing models. Human language readable chains of thought are just a false sense of security, and open models already emit pretty unreadable ones at times while doing the right thing based on it (since policy optimization loops with synthetic data through reinforcement learning).
I mean, its literally just more efficient loop of model generating reasoning text, for it to be fed back as context. There is nothing groundbreaking here. At the end of the day, its all just search.
TBH sooner or later explaining the opaque recurrence with extrinsic logic will be more sustainable, and already there is a need for that with existing models. Human language readable chains of thought are just a false sense of security, and open models already emit pretty unreadable ones at times while doing the right thing based on it (since policy optimization loops with synthetic data through reinforcement learning).
I mean, its literally just more efficient loop of model generating reasoning text, for it to be fed back as context. There is nothing groundbreaking here. At the end of the day, its all just search.