From Guardrails to Principled Agency
verena_rieser · x · 2026-07-14
Adapted from the author's keynote at the 2026 ICML Seoul conference, this article's core focus is that AI interaction paradigms are shifting: we are moving beyond simply “prompting models” toward system designs that emphasize “human-led, agent-executed” actions.
The title highlights a pivot from relying on external behavioral guardrails to embracing “principled agency.” In other words, the focus isn't merely on restricting what models can do, but on organizing systems more clearly around human goals, permissions, and accountability boundaries.
Related event: ICML Keynote: Moving from Guardrails to Principled AI Agency(3 posts)→
More from AGI Musings
- Michael Levin on AI Emails: Read the Papers First, Then Write Me — drmichaellevin · 2026-10-27
- Resy goes scorched earth on agent-based bookings; big agent platforms may force the issue — kevinakwok · 2026-10-27
- Professor's quip: the future of work is AI doing the job and humans updating résumés — prof_kamilov · 2026-10-27
- The most dangerous instruction you can give a superintelligent machine: lie to me — r0ck3t23 · 2026-10-27
- Aditya Agarwal: fear is a policy choice, and the biggest risk to American AI — adityaag · 2026-10-27
- The Best University of 2030 Will Have No Professors, Lectures or Exams, Says Predictions Post — nick_linck · 2026-10-27