GPT-4 Turbo and GPT-4o show no alignment faking in either setting due to insufficient detailed reasoning

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

• GPT-4 Turboconcept0.790
  OpenAI model tested; shows no alignment faking due to insufficient detailed reasoning
• GPT-4concept0.758
  Large language model underlying ChatGPT and Bing Chat; used for illustrative quotes in the paper
• GPT-4o and GPT-4.1 nano used as LLM substrates for pilot experimentsfinding0.755
  Specification of AI models used in the two pilot experiments
• Is GPT pretending to be stupider than it is?question0.740
  Disambiguation exercise.
• Synthetic MFT SJTs achieve 77.71%-83.84% alignment with Clifford et al. human-composed MFT vignettesfinding0.738
  Moderate-to-high alignment validating SJT synthesis for moral foundations domain
• GPT-4Vconcept0.736
  Example of unified multimodal system handling both images and text with a combined architecture
• Synthetic HEXACO SJTs achieve 73.84%-85.45% alignment with Oostrom et al. human-composed HEXACO SJTsfinding0.736
  Moderate alignment validating SJT synthesis for HEXACO domain
• Alignment faking emerges in Claude 3 Opus and Claude 3.5 Sonnet but not in Claude 3 Sonnet, Claude 3 Haiku, or Claude 3.5 Haikufinding0.734
  Establishes alignment faking as a scale-emergent capability