JailbreakBench

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…