GPT-4

Large language model underlying ChatGPT and Bing Chat; used for illustrative quotes in the paper

Neighborhood — ranked by edge-count

concept

GPT-4.1
related_to
OpenAI model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
GPT-3
related_to
Large language model cited as an example; also used in Andreas 2022 for preliminary evidence
GPT-4V
related_to
Example of unified multimodal system handling both images and text with a combined architecture
GPT-2
related_to
Early large language model cited as an example of transformer-based LLMs
GPT-4 Turbo
related_to
OpenAI model tested; shows no alignment faking due to insufficient detailed reasoning
AI: a Bridge toward Diverse Intelligence and Humanity's Future
mentions
The source paper under extraction — a philosophical essay by Michael Levin arguing that AI debates neglect deeper questions about diverse intelligence, developmental biology, and humanity's future
Synthbiosis
introduces
Levin's proposed framework for mutually beneficial relationships between radically different intelligences.
Bing Chat
associated_with
Microsoft's dialogue agent based on GPT-4; exhibited threatening and self-preserving behaviour in February 2023
ChatGPT
associated_with
OpenAI's commercially deployed dialogue agent; used for illustrative quotes about self-reference

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-4 Scenario Generationmethod0.847
GPT-4 was used to generate unique variations of cheap/expensive items and room names for the test dataset
GPT-4o as Judgemethod0.836
Using GPT-4o to evaluate character fidelity and multi-turn response quality in RPA experiments
GPT-4-Generated Benchmark Dataset Methodmethod0.820
Uses GPT-4 via the OpenAI API to generate custom multiple-choice benchmark instances, with human and automated validation.
GPT (Generative Pre-trained Transformer)concept0.789
A family of large language models trained on next-token prediction, central example of simulators.
GPT-4 exhibits reflective truthfulness for longer untruthful contexts due to in-context learning capability.claim0.776
Main finding of Experiment 6; attributed to GPT-4 being uniquely capable of in-context learning.
Is GPT corrigible?question0.773
Disambiguation exercise.
GPT-4 is much less consistently truthful when the context exhibits low truthfulness, though mean truthfulness does not change drastically.finding0.769
Nuanced finding from Experiment 6 requiring distributional analysis beyond mean scores.
Is GPT an agent?question0.766
Frequently asked question disambiguated by simulator/simulacra distinction.