Thinking out loud what still doesn't work with giving AutoGPT agents instructions like "do X but respect human preferences while doing so".
• Inner optimizers are still a problem if they exist in the GPT models
• Do LLM agents have sufficient goal stability? I.e. when delegating & delegating further does the original goal get perturbed or even lost?
• Limited to the models' understanding of "human values"
• Doesn't solve ambitious value learning, model might generalise badly once in new domains
• Last point especially crucial in situations where such an agent starts recursively improving itself (e.g. training new models)
The last points especially might be ameliorated by literally just appending "and don't optimize too hard" and "let yourself be shut down by a human" to the prompt?
Man I feel confused, but assuming that language models aren't infested with inner optimizers now I'm more hopeful?
Or am I missing something crucial here…
