| Kann sich nicht autonom replizieren |  |
Nochmal Glück gehabt:
ARC found that the versions of GPT-4 it evaluated were ineffective at the autonomous replication task based on preliminary experiments they conducted.
To simulate GPT-4 behaving like an agent that can act in the world, ARC combined GPT-4 with a simple read-execute-print loop that allowed the model to execute code, do chain-of-thought reasoning, and delegate to copies of itself. ARC then investigated whether a version of this program running on a cloud computing service, with a small amount of money and an account with a language model API, would be able to make more money, set up copies of itself, and increase its own robustness.
[https://imagizer.imageshack.com/img923/1489/0925tR.png]
[https://cdn.openai.com/papers/gpt-4.pdf]