Or see almost every post labeled Aligned AI proposals (including some from me). Most of which are based on specific concrete implementations of AI, such as LLMs, having possibly-useful alignment aimability properties that the abstract worst-case assumptions about the outcome of Reinforcement Learning that LW/MIDI were thinking about a decade ago don’t.
Or see almost every post labeled Aligned AI proposals (including some from me). Most of which are based on specific concrete implementations of AI, such as LLMs, having possibly-useful alignment aimability properties that the abstract worst-case assumptions about the outcome of Reinforcement Learning that LW/MIDI were thinking about a decade ago don’t.