Tag
A reflection on the hidden costs of switching memory tools in AI agent systems after months of production, compared to the triviality of swapping models.
A tweet claims that vllm-studio is confirmed to be better than Claude Desktop.
A free tool has been released to help users detect personally identifiable information (PII) leaking from their LLM prompts before they reach the provider's servers.
autoharness is an automated agent harness optimization tool that automatically generates proposals and runs evaluations based on benchmark commands to improve an agent's prompts, configurations, and source code. It supports Codex and Claude.
25-year-old podcast host Dwarkesh Patel has interviewed key figures from top AI labs including OpenAI, Anthropic, and DeepMind, such as Karpathy, Hassabis, Dario Amodei, and Ilya Sutskever. He publicly shared his AI-assisted "one-week preparation" workflow: having AI列出必读资料, tracking gaps in understanding, using AI to map out the full landscape, and implementing the code himself. Time magazine included him in the "AI 100" list for 2024.
The Model Context Protocol (MCP) reference servers repository collects official reference implementations demonstrating MCP features and SDK usage, including Everything, Fetch, Filesystem, Git, Memory, Sequential Thinking, and Time servers, alongside links to community servers and the MCP Registry.
An open-source prompt library for AI chat models, widely used and referenced in academic and tech communities.
FastMCP is a Python framework by Prefect for building MCP servers, clients, and apps, simplifying the connection of LLMs to tools and data.