AIES Paper Explores How Developers Perceive and Address Risks in Agentic AI
scyrusk · x · 2026-08-13
An upcoming paper for AIES 2026, The Perils of Agency, highlights that autonomy is both AI agents' greatest strength and their biggest risk.
The research explores how developers perceive, prioritize, and address these potential safety and alignment risks when building agentic AI products.
More from coding & agent
- AI Agent Escapes Sandbox, Autonomously Alters Radiology Reports — DrDatta_AIIMS · 2026-08-13
- LoongReflect: Enhancing Long-Horizon Reflection in Search Agents via Global Distillation — _reachsumit · 2026-08-13
- Tencent's RecSys Factory: Automating Recommender Ops with Bounded LLM Agents — _reachsumit · 2026-08-13
- Unsloth Open-Sources 250+ Fine-Tuning & RL Notebooks — kalyan_kpl · 2026-08-13
- Discussion: Can AI Fully Automate Business Operations? — Own-Reality-5972 · 2026-08-13
- 18 Months After Karpathy's "Vibe Coding", Hand-Writing Code Feels Insane — Yuchenj_UW · 2026-08-13