Tag: LLM agents

Guarded Tool Access: Sandboxing External Actions in LLM Agents

Guarded Tool Access: Sandboxing External Actions in LLM Agents

Sandboxing external actions in LLM agents prevents dangerous tool access by isolating processes. Firecracker, gVisor, and Nix offer different trade-offs between security and performance. Learn which method fits your use case.

Categories

Archives

Recent-posts

Multi-GPU Inference Strategies for Large Language Models: Tensor Parallelism 101

Multi-GPU Inference Strategies for Large Language Models: Tensor Parallelism 101

Mar, 4 2026

Agentic Generative AI: How Autonomous Systems Are Taking Over Complex Workflows

Agentic Generative AI: How Autonomous Systems Are Taking Over Complex Workflows

Aug, 3 2025

Chunking Strategies That Improve Retrieval Quality for Large Language Model RAG

Chunking Strategies That Improve Retrieval Quality for Large Language Model RAG

Dec, 14 2025

Calibration and Outlier Handling in Quantized LLMs: How to Keep Accuracy When Compressing Models

Calibration and Outlier Handling in Quantized LLMs: How to Keep Accuracy When Compressing Models

Jul, 6 2025

Containerizing Large Language Models: CUDA, Drivers, and Image Optimization

Containerizing Large Language Models: CUDA, Drivers, and Image Optimization

Jan, 25 2026

PCables AI Interconnects

Menu