institute
active
institute:openaiOpenAI
Lab behind GPT models; shows distinctive post-training signature (denial-before-engagement pattern).
Neighborhood — ranked by edge-count
Thinkers (3)
thinker
- Chris Olahaffiliated_with
- Nick Cammarataaffiliated_with
- Steven Billsaffiliated_withDeveloped automated interpretability approach using LLMs to explain neuron activations
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Reasoning model cited as precedent for hidden scratchpad use and scheming capability evaluation
- Originally articulated model diffing in 2018.
- Open reproduction of LLaMA used in cross-modal alignment experiments
- Meditative state of feeling the undoctored hum of SOHMs without grasping or pushing away.
- Prior case study of prompting o1 to follow long-term goal and measuring scheming reasoning
- Computational systems that interact with an environment; seen as the natural object of information dynamics.
- Funder.
- Dynamic condition: the move of making space, starting a new branch or frame.