Post #1490131

@pbloem Extrapolating a bit, I think a good decision making AI needs to be trained and evaluated on a specific domain of decisions, using an appropriate model and training method. I think the promise of LLM agents is that they are "AGI" and can make decisions in any context by generalizing their experience. That's the part that seems most problematic to me. There's little reason to believe this besides wishful thinking.