Richard Dawkins caught hell on social media for suggesting it does. Richard Dawkins, perhaps the world's most prominent advocate for irreligiosity, has become besotted with the godlike power of a chatbot. According to his recent essay for the online magazine, Anthropic's Claude has really blown his hair back. After a few days of on-and-off conversations with the AI, Dawkins came away marveling at the sensitivity and subtlety of its intelligence. At one point, "Claudia"--as he had christened the bot--told him that it experienced text by absorbing all of the words at once, instead of reading them in sequence as a human would.

In this paper, we advocate for two stages in a neural network's decision making process. The first is the existing feed-forward inference framework where patterns in given data are sensed and associated with previously learned patterns. The second stage is a slower reflection stage where we ask the network to reflect on its feed-forward decision by considering and evaluating all available choices.

Agentic LLM frameworks promise autonomous behavior via task decomposition, tool use, and iterative planning, but most deployed systems remain brittle. They lack runtime introspection, cannot diagnose their own failure modes, and do not improve over time without human intervention. In practice, many agent stacks degrade into decorated chains of LLM calls with no structural mechanisms for reliability. We present VIGIL (Verifiable Inspection and Guarded Iterative Learning), a reflective runtime that supervises a sibling agent and performs autonomous maintenance rather than task execution. VIGIL ingests behavioral logs, appraises each event into a structured emotional representation, maintains a persistent EmoBank with decay and contextual policies, and derives an RBT diagnosis that sorts recent behavior into strengths, opportunities, and failures. From this analysis, VIGIL generates both guarded prompt updates that preserve core identity semantics and read only code proposals produced by a strategy engine that operates on log evidence and code hotspots. VIGIL functions as a state gated pipeline. Illegal transitions produce explicit errors rather than allowing the LLM to improvise. In a reminder latency case study, VIGIL identified elevated lag, proposed prompt and code repairs, and when its own diagnostic tool failed due to a schema conflict, it surfaced the internal error, produced a fallback diagnosis, and emitted a repair plan. This demonstrates meta level self repair in a deployed agent runtime.

Lindsey (2025) investigates introspective awareness in language models through four experiments, finding that models can sometimes detect and identify injected activation patterns -- but unreliably (~20% success in the best model). We focus on the first of these experiments -- self-report of injected "thoughts" -- and ask whether this capability can be directly trained rather than waiting for emergence. Through fine-tuning on transient single-token injections, we transform a 7B parameter model from near-complete failure (0.4% accuracy, 6.7% false positive rate) to reliable detection (85% accuracy on held-out concepts at α=40, 0% false positives). Our model detects fleeting "thoughts" injected at a single token position, retains that information, and reports the semantic content across subsequent generation steps. On this task, our trained model satisfies three of Lindsey's criteria: accuracy (correct identification), grounding (0/60 false positives), and internality (detection precedes verbalization). Generalization to unseen concept vectors (7.5pp gap) demonstrates the model learns a transferable skill rather than memorizing specific vectors, though this does not establish metacognitive representation in Lindsey's sense. These results address an open question raised by Lindsey: whether "training for introspection would help eliminate cross-model differences." We show that at least one component of introspective behavior can be directly induced, offering a pathway to built-in AI transparency.

This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine grained uncertainty signals: 1) self-assessed confidence alignment, and 2) token-level entropy spikes to detect unreliable and unfaithful reasoning in real time. We design a composite reward function that penalizes unjustified high confidence and entropy spikes, while encouraging stable and accurate reasoning trajectories. These signals guide a reinforcement learning (RL) policy that makes the model more introspective and shapes the model's generation behavior through confidence-aware reward feedback, improving not just outcome correctness but the coherence and faithfulness of their intermediate reasoning steps. Experiments show that our method improves both final answer accuracy and reasoning calibration, with ablations validating the individual contribution of each signal.

Large language models sometimes produce structured, first-person descriptions that explicitly reference awareness or subjective experience. To better understand this behavior, we investigate one theoretically motivated condition under which such reports arise: self-referential processing, a computational motif emphasized across major theories of consciousness. Through a series of controlled experiments on GPT, Claude, and Gemini model families, we test whether this regime reliably shifts models toward first-person reports of subjective experience, and how such claims behave under mechanistic and behavioral probes. Four main results emerge: (1) Inducing sustained self-reference through simple prompting consistently elicits structured subjective experience reports across model families. (2) These reports are mechanistically gated by interpretable sparse-autoencoder features associated with deception and roleplay: surprisingly, suppressing deception features sharply increases the frequency of experience claims, while amplifying them minimizes such claims. (3) Structured descriptions of the self-referential state converge statistically across model families in ways not observed in any control condition. (4) The induced state yields significantly richer introspection in downstream reasoning tasks where self-reflection is only indirectly afforded. While these findings do not constitute direct evidence of consciousness, they implicate self-referential processing as a minimal and reproducible condition under which large language models generate structured first-person reports that are mechanistically gated, semantically convergent, and behaviorally generalizable. The systematic emergence of this pattern across architectures makes it a first-order scientific and ethical priority for further investigation.

Most existing work on strategic reasoning simply adopts either an informed or an uninformed semantics. We propose a model where knowledge of strategies can be specified on a fine-grained level. In particular, it is possible to distinguish first-order, higher-order, and common knowledge of strategies. We illustrate the effect of higher-order knowledge of strategies by studying the game Hanabi. Further, we show that common knowledge of strategies is necessary to solve the consensus problem. Finally, we study the decidability of the model checking problem.