Failure episodes are primarily caused by hand occluding the sticker in the mirror or sticker leaving the visual field due to head rotation, plus kinematic reachability limits

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

• A sensory anomaly (sticker mismatch) can itself become an intrinsic drive for action under active inference, even without external rewardclaim0.751
  Core mechanism claim linking mismatch detection to behavior through EFE minimization
• Some failures may reflect prompt design rather than model limitations, but the underlying issue is one of reasoning rather than instruction-following.claim0.737
  Acknowledges the confound of not explicitly instructing models to track wealth, yet points to reasoning gaps given code agents avoid errors without prompts.
• Overbidding, self-bidding spirals, and undisciplined bluffing characterise failure.claim0.732
  Concrete failure signatures extracted from traces.
• Clamping code error feature to high activation causes the model to hallucinate error messages on bug-free code.finding0.732
  Causal effect: feature induces perception of bugs.
• The sticker-removal behavior induced by the self-prior corresponds to stimulus-elicited intention rather than endogenous intention, aligning with the developmental view of early intentional agencyclaim0.731
  Connects the model's behavior to Zaadnoordijk and Bayne's taxonomy of intentional agency
• Lesioning active, sensory, or internal states causes rapid structural disintegration and loss of spatial organization.finding0.730
  Demonstrates autopoietic maintenance: Markov blanket integrity is necessary for preserving internal state configuration.
• Behavioural traces surface recurring LLM failure modes including overbidding, self-bidding, bankrupt TC initiation, and weak opponent-state adaptation that never appear in code agents.claim0.719
  LLMs exhibit systematic errors that deterministic logic avoids.
• Overbid frequency, self-bidding rate, bankrupt-initiation patterns, and context-dependent offer calibration are failure modes invisible to both static evaluations and aggregate rankings like Eloclaim0.716
  key claim about the benchmark's unique diagnostic value