I believe prompting an AI is more like delegation than abstraction especially considering the non-deterministic nature of the results.
It does further than non-determinism. LLM output is chaotic. 2 nearly identical prompts with a single minor difference can result in 2 radically different outputs.
It does further than non-determinism. LLM output is chaotic. 2 nearly identical prompts with a single minor difference can result in 2 radically different outputs.