Tagged "model-safety"
- AI Guardrails Stripped From Meta and Google Models in Minutes
- Control AI Risk with Pre-Built Frameworks and Ready-to-Run Evaluations
- 96.8% of MCP Tool Descriptions Don't Warn the Agent About Destructive Behaviour
- Qwen 3.5-35B Uncensored GGUF Models Now Available
- Extracting 100K Concepts from an 8B LLM
- GLM-5 Released: 744B Parameter MoE Model Targeting Complex Tasks