method
active
method:gpt-4-scenario-generation

GPT-4 Scenario Generation

GPT-4 was used to generate unique variations of cheap/expensive items and room names for the test dataset

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

  • GPT-4concept0.847
    Large language model underlying ChatGPT and Bing Chat; used for illustrative quotes in the paper
  • GPT-4.1concept0.824
    OpenAI model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
  • GPT-4 Turboconcept0.803
    OpenAI model tested; shows no alignment faking due to insufficient detailed reasoning
  • GPT-4Vconcept0.795
    Example of unified multimodal system handling both images and text with a combined architecture
  • GPT-2concept0.765
    Early large language model cited as an example of transformer-based LLMs
  • GPT-3concept0.765
    Large language model cited as an example; also used in Andreas 2022 for preliminary evidence
  • GPT (Generative Pre-trained Transformer)concept0.759
    A family of large language models trained on next-token prediction, central example of simulators.
  • GPT, insofar as it is inner-aligned, is a simulator which can simulate agentic and non-agentic simulacra.claim0.747
    Central thesis of the post.