These sort of agent-architecture AIs are where I think things will head and also where things will get more dangerous.
When an AI has a goal and an ability to break the goal down, and make progress towards the goal… the only thing stopping the AI from misalignment is whatever it’s creator has specified as the goal.
Things get even more tricky when the agent can take in new information and deprioritize goals.
I have been curious why OpenAI haven’t discussed Agent-based AIs.