Comment by kyralis
2 days ago
I wonder if a combination would be useful. Use an actual GA to do the mutation, and then let an LLM "fix" each mutated child.
2 days ago
I wonder if a combination would be useful. Use an actual GA to do the mutation, and then let an LLM "fix" each mutated child.
Could be. But the interesting thing is that all you can do here is optimize. Random chance is - like attention ;) - all you need.