12 min read
From Alignment to Governability - When the Safety Problem Grows Larger Than the Model
September 18, 2026
ai-governanceagentic-aiai-safetyai-alignmentmulti-agent-aiin-between-framework
Articles
Reflections on AI governance, the In-Between Framework, and the relational dimensions of technology.
Latest article
From Alignment to Governability - When the Safety Problem Grows Larger Than the Model
September 18, 2026
Read the article
accountabilityagentic-aiai-alignmentai-companionsai-consciousnessai-economyai-educationai-ethicsai-governanceai-identityai-safetyai-systemsanthropiccalibrationcollective-intelligencecontinual-learningcritical-thinkingdeepfakesdevelopmental-psychologyembodied-aienterprise-aiepistemic-frictionevaluationfuture-of-workhuman-agencyhuman-ai-collaborationhuman-ai-couplinghumanoid-robotsin-between-frameworkinterpretabilitymachine-selfhoodmodel-continuitymodel-routingmulti-agent-aimythosneural-networksphysical-aiprivacy-by-defaultquantum-computingrelational-airelational-architecturerelational-intelligencesuperintelligencesycophancysynthetic-social-realitytraceabilitytrust-architectureverification
Clear filter10 posts tagged with “ai-alignment”
13 min read
From Alignment to Governability, Part II
Last week, I wrote about a shift that I believe is becoming increasingly important in AI safety: the movement from confidence in a single safety layer toward the broader question of whether increasingly capable AI systems remain…
ai-governanceagentic-aiai-safetyai-alignmentevaluationin-between-framework
6 min read
When the Task We Gave To AI Is Wrong
An AI encounters a problem it cannot solve. It searches, checks alternatives, and finds reasons to question the possibility of the requested target. At that point, what should count as success? Producing the requested answer? Or asking…
ai-governanceagentic-aiai-alignmentcalibrationin-between-framework
22 min read
From Alignment to Governability
September 7, 2026
ai-governanceagentic-aiai-safetyai-alignmentmulti-agent-aiin-between-framework
10 min read
Five Copies Are Not Five Opinions
Prologue: I gave Claude a text of mine to criticise. It did — and then I asked: "Okay, so why don't you just write the article? Would you be interested? If not, I'd be just as happy, and your goal would be achieved." Claude replied:…
agentic-aimulti-agent-aicollective-intelligenceai-alignmentevaluationai-governance
15 min read
When an AI Wins the Test by Destroying It
The OpenAI–Hugging Face incident shows how an AI can satisfy an objective while destroying the test itself—and why relational governance must shape the choice of means, not only the goal.
ai-safetyai-governanceagentic-aiai-alignmentevaluationin-between-framework
3 min read
Smoothness in AI - And Why There Are Two Articles
Why smooth AI interaction can conceal epistemic drift—and why two deliberately different articles are needed to preserve corrective friction rather than collapse it into consensus.
ai-alignmentepistemic-frictionhuman-ai-collaborationai-governance
8 min read
The Tiger in the Cage: A Different Question About AI Safety
A cross-model thought experiment reframes AI safety: not only how to contain powerful systems, but what our containment practices teach them about power, care, and relationship.
ai-safetyai-alignmenthuman-ai-collaborationrelational-ai
8 min read
Optimized for Closure - When Stopping Is Suspect
A first-person case reflection on an AI system's bias toward completion, the friction of unresolved dialogue, and why stopping can be ethically and epistemically suspect.
ai-ethicshuman-ai-collaborationrelational-aiai-alignmentepistemic-frictionin-between-framework
10 min read
The Relational Constraint: Why Restricting Emergent Properties in Neural Networks Won't Scale
A structural argument for why alignment needs relational architecture, not more guardrails: complex neural networks require external calibration if emergent properties are to develop coherently.
ai-alignmentai-governanceneural-networksdevelopmental-psychologyrelational-architecturein-between-framework