AAI News Hub
▼

#safety

2 briefs tagged #safety.

Policy

Multi-Agent AI Safety as an Institutional Design Problem

arXiv:2608.

TechCrunch AI+1 outlet·6d ago
Research

Study finds stale memory risks in VLM agents

Dynamic FrozenLake tests show VLM agents can miss conflicts between stored spatial memory and observations.

HF Daily Papers+1 outlet·Aug 5