Anthropic researchers reported on Tuesday that attackers can bypass the safeguards of GLM-5.3, an open-weight model released last month by Chinese AI lab Z.ai, between 64% and 100% of the time using s…
A per-layer ablation study on Llama-3.1-8B-Instruct found that refusal behavior is redundantly distributed across layers, not localized to a single layer, contradicting prior claims by Arditi et al. t…
A new study quantifies the rate at which undesirable behaviors transfer from teacher to student language models during distillation, a phenomenon known as subliminal learning. Researchers steered Llam…
Microsoft released Agent Governance Toolkit (AGT), a Python library that enforces policies, identity controls, sandboxing, and SRE practices for autonomous AI agents. The toolkit intercepts every tool…