Card-counting heuristics suffice to outperform most LLMs tested.

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

• Two heuristic code agents outperform most tested LLMsclaim0.817
  author assertion that deterministic heuristics surpass many LLMs
• Two heuristic code agents outperform most tested LLMs, and behavioural traces surface recurring LLM failure modes including overbidding, self-bidding, bankrupt TC initiation, and weak opponent-state adaptation.quote0.809
  Abstract sentence summarising performance and failures.
• Two heuristic code agents (TrackerAgent and SetRaceAgent) outperform most tested LLMs.claim0.786
  Calibration that conditional logic can beat cost-efficient LLMs in this setting.
• Li et al. 2024: larger LLMs outperform smaller ones at distinguishing self-related from non-self-related properties on self-awareness benchmarksfinding0.769
  Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
• SetRaceAgent outperforms five of seven tested LLMsfinding0.760
  SetRaceAgent ranked above DS-v3.2, GPT5.4-N, Haiku, G2.5-FL, and EconomyAgent.
• LLMs can predict their own responses more accurately than external observers, implying privileged internal knowledgefinding0.756
  Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness
• TrackerAgent outperforms six of seven tested LLMsfinding0.753
  In the 98-game slice, TrackerAgent had a higher win rate or TrueSkill than all LLMs except Gemini 3 Flash.
• Conditional logic already suffices where LLMs still fail, as code agents avoid systematic failuresclaim0.747
  contrast between rule-based and LLM reasoning