GPT is behavior cloning, but it is the behavior of a universe that is cloned, not of a single demonstrator.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• What we call GPT's 'downstream behavior' is the behavior of simulacra; it is primarily through simulacra that GPT has potential to perform meaningful work.claim0.822
  Clarifies where agency resides.
• GPT, insofar as it is inner-aligned, is a simulator which can simulate agentic and non-agentic simulacra.claim0.817
  Central thesis of the post.
• GPT's ability to simulate text automata is the source of its most surprising and pivotal implications for paths to superintelligence.claim0.800
  Importance of recursive generation.
• Treating GPT as an unsupervised implementation of a supervised learner leads to systematic underestimation of capabilities.claim0.787
  Critique of the oracle/supervised frame.
• There is a categorical distinction between a thing which evolves according to GPT's law and the law itself.claim0.776
  Simulator vs simulacra ontological divide.
• GPT is corrigible in a negative sense because the agent specification (prompt) is not fixed by the policy and the policy lacks direct training incentives to control its prompt.claim0.772
  GPT's corrigibility explained.
• GPT doesn't seem to care which agent it simulates, nor if the scene ends and the agent is effectively destroyed.claim0.770
  Illustrates the simulator-simulacra distinction.
• I do not think any simple modification of the concept of an agent captures GPT's natural category; GPT is not a roleplayer, only that it roleplays.claim0.767
  Rejection of the agent interpretation.