GPT (Generative Pre-trained Transformer)

A family of large language models trained on next-token prediction, central example of simulators.

Neighborhood — ranked by edge-count

thinker

framework

Simulator ontology
associated_with
The framework proposed: self-supervised models are simulators that generate simulacra; distinguishes simulator from simulated agents.

hypothesis

artifact

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-like Transformer Autoregressive Model (Self-Prior)method0.791
The self-prior is implemented as a GPT-like transformer that autoregressively models the joint distribution of the unified latent state
GPT-4concept0.789
Large language model underlying ChatGPT and Bing Chat; used for illustrative quotes in the paper
Treating GPT as an unsupervised implementation of a supervised learner leads to systematic underestimation of capabilities.claim0.787
Critique of the oracle/supervised frame.
GPT-2concept0.776
Early large language model cited as an example of transformer-based LLMs
GPT-4Vconcept0.775
Example of unified multimodal system handling both images and text with a combined architecture
GPT-4.1concept0.772
OpenAI model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
GPT is behavior cloning, but it is the behavior of a universe that is cloned, not of a single demonstrator.claim0.761
Broadening behavior cloning to universal simulation.
GPT-3concept0.760
Large language model cited as an example; also used in Andreas 2022 for preliminary evidence