Comment by Andrew CC (andrew-cc) on Why Aligning an LLM is Hard, and How to Make it Easier · 2025-01-23T09:38:04.636Z · LW · GW

Thanks for sharing this idea. I learn a lot from it. One feeling after reading this is that making AI aligned with all good values and ethics of humans sounds like creating a perfect and ideal being. What's more, it is like to create a god with our own human hand. This makes me feel that building ASI is a crazy and impossible goal.