AI+X Summit to Host Workshop on Where Safety Interventions in LLM Training Are Most Impactful

valentina__py · x · 2026-08-14

The AI+X Summit, organized by ETH AI Center, will feature a workshop on October 1 in Zurich titled 'Staging x Misalignment Science: When, Where and How Safety Enters LLM Training'. Co-organized by Anna Hedström and Valentina, the session will explore at which stages of the LLM lifecycle (data curation, pre-training, post-training, evaluation, deployment) safety interventions are most impactful. It includes keynotes by BlancheMinerva and cervisiarius, followed by a panel with researchers holding opposing views.

Original post →

More from AGI Musings

AGI Musings channel →