EthicsSafetyTransparencycs.CY
Competing Visions of Ethical AI: A Case Study of OpenAI
Melissa Wilfley, Mengting Ai, Madelyn Rose Sanfilippo
January 23, 2026
Information research. An international electronic journal
1 citations
Key Takeaways
-
Safety and risk dominate OpenAI's public messaging, but traditional ethics frameworks are largely absent. The study found that OpenAI's communications emphasize "safety" and "risk" language rather than drawing on established academic ethics vocabularies and frameworks, suggesting a narrower framing of ethical AI than what ethicists typically advocate for.
-
Different messaging for different audiences. OpenAI uses distinctly different ethical language when communicating with general audiences versus academic audiences, indicating strategic framing choices rather than consistent ethical principles across all stakeholder groups.
-
Potential "ethics-washing" in industry practice. The research raises concerns that companies may use ethics-related terminology in public discourse without substantively implementing the comprehensive ethical approaches that academics and advocates recommend, which has important implications for how we evaluate corporate AI governance claims.
-
Ethical AI means different things to different actors. The case study demonstrates that "ethical AI" is not a unified concept—how companies frame ethics depends on their priorities and audiences, which could create confusion about what responsible AI actually entails for policymakers and the public.
Abstract
Introduction. AI Ethics is framed distinctly across actors and stakeholder groups. We report results from a case study of OpenAI analysing ethical AI discourse. Method. Research addressed: How has OpenAI's public discourse leveraged 'ethics', 'safety', 'alignment' and adjacent related concepts over time, and what does discourse signal about framing in practice? A structured corpus, differentiating between communication for a general audience and communication with an academic audience, was assembled from public documentation. Analysis. Qualitative content analysis of ethical themes combined inductively derived and deductively applied codes. Quantitative analysis leveraged computational content analysis methods via NLP to model topics and quantify changes in rhetoric over time. Visualizations report aggregate results. For reproducible results, we have released our code at https://github.com/famous-blue-raincoat/AI_Ethics_Discourse. Results. Results indicate that safety and risk discourse dominate OpenAI's public communication and documentation, without applying academic and advocacy ethics frameworks or vocabularies. Conclusions. Implications for governance are presented, along with discussion of ethics-washing practices in industry.