DeepMind's Verena Rieser to keynote EMNLP 2026 on a science of constitutional alignment
verena_rieser · x · 2026-10-23
Verena Rieser (Google DeepMind) previews her EMNLP 2026 industry keynote in Budapest: "Toward a Science of Constitutional Alignment." She will argue why the AI frontier is suddenly keen on aligning models to constitutions, make the case for pluralism, outline the hard open questions, and discuss how the NLP community can contribute.
Related event: EMNLP 2026 Industry Track Features Constitutional Alignment and Agents(3 posts)→
More from Safety
- opencode model catches and rejects a prompt injection mid-reasoning — KomithErrant · 2026-10-23
- Is formally verifying an AI agent sandbox a Millennium Prize-level problem? — teortaxesTex · 2026-10-23
- Swedish government offices to ban ChatGPT and Claude — armcat · 2026-10-23
- AI finds subtle architecture-level bugs, not just the memory exploits ASan can catch — stanislavfort · 2026-10-23
- 66% of European Shops Leave OpenAI's ChatGPT Ad Pixel Tracking On by Default — adulion · 2026-10-23
- Overton window shifts: more voices say Anthropic/OpenAI could just stop unilaterally — mark_k · 2026-10-23