Tagged "model-safety"
7 articles tagged model-safety, 12 February 2026 to 20 July 2026. Newest first.
-
Topological Control of LLMs: A Route to Trustworthy AI
Research on controlling LLM behavior through topological methods offers new approaches for ensuring safety and reliability in locally-deployed models.
-
AI Guardrails Stripped From Meta and Google Models in Minutes
Security researchers demonstrate vulnerabilities allowing rapid removal of safety guidelines from commercial LLMs. Critical implications for organizations relying on guardrails in locally-deployed or fine-tuned models.
-
Control AI Risk with Pre-Built Frameworks and Ready-to-Run Evaluations
Atlas provides pre-built frameworks and evaluation tools for assessing and controlling risks in AI systems, offering practical solutions for local LLM operators who need robust safety and reliability measures.
-
96.8% of MCP Tool Descriptions Don't Warn the Agent About Destructive Behaviour
A critical safety analysis of Model Context Protocol tool descriptions reveals widespread gaps in agent safety guardrails, with implications for local LLM applications using autonomous agents.
-
Qwen 3.5-35B Uncensored GGUF Models Now Available
Community releases optimized GGUF quantizations of Qwen 3.5-35B uncensored variants, enabling local deployment without refusal mechanisms. Multiple quantization levels tested on consumer GPUs.
-
Extracting 100K Concepts from an 8B LLM
Research demonstrates how to extract and discover 100,000 interpretable concepts from an 8-billion parameter language model, enabling better understanding and control of smaller models suitable for local deployment.
-
GLM-5 Released: 744B Parameter MoE Model Targeting Complex Tasks
Zhipu AI releases GLM-5, a massive 744B parameter MoE model with 32B active parameters, designed for complex systems engineering and long-horizon agentic tasks with significant performance improvements over GLM-4.5.