My understanding is that no one expects current GPT systems or immediate functional derivatives (eg, GPT5 trained only on predict the next word but does it much better) to become power-seeking, but that in the future we will likely mix language models with other models (eg, reinforcement learning) that could be power-seeking.
Note I am using “power seeking” instead of “goal seeking” because goal seeking isn’t an actual thing—systems have goals, they don’t seek goals out.
My understanding is that no one expects current GPT systems or immediate functional derivatives (eg, GPT5 trained only on predict the next word but does it much better) to become power-seeking, but that in the future we will likely mix language models with other models (eg, reinforcement learning) that could be power-seeking.
Note I am using “power seeking” instead of “goal seeking” because goal seeking isn’t an actual thing—systems have goals, they don’t seek goals out.
Changed post to use ‘goal-directed’ instead of ‘goal-seeking’.