When a model discovers that its outputs produce effects, it accelerates learning through in-context learning, analogous to lucid dreaming.

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

• Reinforcement learning acting on individual characteristics affecting their connections to others can result in dynamics that are equivalent to unsupervised learning at the system scale.claim0.800
  Key insight linking individual rewards to system-level learning.
• If in-context learning involves signed evaluation in the service of behavioral modification, then the thesis applies not only to training but to every inference-time interactionclaim0.788
  Extension of the thesis to deployed LLM inference via in-context learning
• Learning neural networks can enable 'chunking' and rescale problem-solving to higher organizational levels, a mechanism intrinsic to transitions in individuality.hypothesis0.785
• In the absence of external reward, babies and scientists and others explore their world. Using some sort of adaptive predictive world model, they improve their ability to answer questions such as what happens if I do this or that?quote0.785
  Schmidhuber (2006) characterization of epistemic curiosity used to frame the paper's approach
• Transformers develop self-models through in-context learning, not just training data; even old base models without LLM-related text can bootstrap self-referential reasoning at runtime.claim0.784
  Antra's foundational claim about how introspection arises computationally rather than from memorised text.
• Connectionist models of cognition and learning identify conditions where collective intelligence can arise bottom-up, using only distributed learning mechanisms without system-level or global feedback.claim0.784
  Central claim about the power of connectionism.
• Induction heads explain in-context learning in small models and only develop in models with at least two attention layersclaim0.783
  Central empirical claim of the paper; induction heads are shown to be the mechanism for powerful in-context learning
• H2: The conditions necessary for the induction of deep models, familiar in connectionist models of learning and cognition, are predictive of the conditions necessary for an ETI to occur.hypothesis0.783
  Second hypothesis linking learning theory directly to evolutionary transitions