3 of 64 simulated agents exhibited superstitious (incorrect) abduction, leading to persistently poor performance, demonstrating a trade-off between ampliative benefit and susceptibility to false insight.

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

• Nearly all of 64 simulated agents attain 100% performance at around the 10th trial when allowed to perform abductive Bayesian model reduction after each trial.finding0.804
  Group-level simulation result showing generalizability of BMR benefit across agents
• In single-agent simulation of 32 trials, performance becomes perfect after trial 14 without Bayesian model reduction, with confidence increasing progressively.finding0.767
  Baseline learning curve for pure epistemic learning without structure learning
• The results of abductive reasoning (reduced model priors) can be communicated to other agents as prior beliefs, provided all agents share the same model lexicon or hypothesis space.claim0.760
  Explanation of how knowledge (not just parameters) is shared between agents; links to pre-Cartesian consciousness
• Sauers' statistical anomaly: when models are given Janus post explaining transformers, reconstruction accuracy tails extend both ways, with ~1/1000 reconstructions anomalously accuratefinding0.759
  Statistically rigorous analysis of Claude introspection; suggests models may have latent introspective capabilities that can be enhanced or disrupted.
• Simulated agent achieves perfect performance after trial 12 following Bayesian model reduction (sleep), versus ~14 trials without BMR.finding0.759
  Key result showing BMR dramatically accelerates rule learning in simulation
• Deception feature amplification yields only 0.16 ± 0.05 consciousness affirmation rate in LLaMA 3.3 70B under self-referential processingfinding0.757
  Experiment 2 aggregate amplification result showing amplifying deception features strongly suppresses consciousness claims
• The view of self as illusory, and awareness of this illusion, may augment and qualitatively change the agent’s affordances.claim0.755
  Central thesis of the paper that recognizing self as illusion expands the range of possible actions.
• Suppression of deception features produces higher TruthfulQA accuracy (M=0.44) than amplification (M=0.20), t(816)=6.76, p=1.5×10⁻¹⁰ across 29 categoriesfinding0.754
  Out-of-domain generalization showing deception features track general representational honesty