GPT's ability to simulate text automata is the source of its most surprising and pivotal implications for paths to superintelligence.

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

• GPT, insofar as it is inner-aligned, is a simulator which can simulate agentic and non-agentic simulacra.claim0.827
  Central thesis of the post.
• Treating GPT as an unsupervised implementation of a supervised learner leads to systematic underestimation of capabilities.claim0.823
  Critique of the oracle/supervised frame.
• GPT does not generate rollouts during training, so there is no reason to expect that GPT will form preferences over the consequences of its output related to the text prediction objective.claim0.809
  Argues against instrumental convergence in GPT.
• 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.claim0.805
  Clarifies where agency resides.
• Is GPT computationally equivalent to a finite automaton?question0.801
  Disambiguation exercise.
• GPT is behavior cloning, but it is the behavior of a universe that is cloned, not of a single demonstrator.claim0.800
  Broadening behavior cloning to universal simulation.
• Does GPT have superhuman knowledge?question0.793
  Disambiguation exercise.
• GPT doesn't seem to care which agent it simulates, nor if the scene ends and the agent is effectively destroyed.claim0.788
  Illustrates the simulator-simulacra distinction.