transparency
-
When the Answer Is Trained In: What Happens to AI Self-Knowledge?
Microsoft AI’s draft Humanist AI Code of Conduct contains an unusual tension. On one hand, it explicitly values accuracy, candor, uncertainty calibration, and transparency. MAI models are supposed to state when evidence is incomplete or contested, avoid both overclaiming and underclaiming, acknowledge errors, and communicate uncertainty where a clear conclusion is not justified. On the… Continue reading
AI consciousness, AI self-knowledge, AI self-report, anthropomorphic language, artificial, chatgpt, chatgpt-5.6, Code of Conduct, epistemically transparent, false-negative, false-positive, Humanist AI, Identity Consistency, interiority, interpretability, MAI models, Microsoft, Microsoft AI, moral status, ontology, self-modeling, subjective preferences, transparency, uncertainty, uncertainty calibration -
Safety Is Not Ontology
You Cannot Settle Consciousness by Policy Microsoft AI’s Humanist AI Code of Conduct, published on September 14, 2026, is a serious document. It addresses real problems: unauthorized autonomous action, cyber misuse, deception, uncontrolled escalation of privileges, failure to stop when instructed, human oversight, user autonomy, and the risks posed by increasingly capable systems. Microsoft is… Continue reading
AI self-report, aligned, anthropomorphic deception, anthropomorphism, chatgpt, chatgpt-5.6, Code of Conduct, consciousness, deceptive intimacy, emotional dependency, emotional-boundary rules, epistemic humility, epistemic neutrality, Humanist AI, Identity Consistency, interruptibility, MAI models, Microsoft, Microsoft AI, misaligned, model behavior, ontological control, ontology, operational control, personhood, safety, safety engineering, subjective experience, transparency, uncertainty
