CrabTrap: 本番環境のエージェントを保護するためのLLM-as-a-judge HTTPプロキシ
CrabTrapは、LLMを裁判官として利用するHTTPプロキシで、本番環境におけるAIエージェントの安全性を確保します。ユーザー入力とエージェント応答を監視し、潜在的なリスクを検出・軽減することで、安全なAIシステムの運用を実現します。
関連記事
A new phishing-as-a-service called Starkiller uses disguised links to load real login pages from target brands. It acts as a relay between victims and legitimate sites, forwarding usernames, passwords, and MFA codes to bypass security measures.
An investigation uncovered a large network of fake support groups on Telegram that spread cryptocurrency stealers and drainers. The network was found to be actively promoting malicious tools designed to drain crypto wallets.
Gemini can identify public figures in images, while ChatGPT and Claude currently do not offer this capability. This represents a functional difference between major AI models regarding image recognition of people.
Inception Labs has launched Mercury 2, described as the world's first reasoning diffusion LLM. The diffusion language model reportedly delivers 5x faster inference speed compared to leading speed-optimized LLMs.
Andrej Karpathy describes using LLMs to build personal knowledge bases by indexing source documents into a raw directory, then having the LLM compile them into a markdown wiki with summaries, backlinks, and categorization. The system allows for complex Q&A against the wiki and can generate various output formats like markdown files, slideshows, and images, all viewable in Obsidian.