SafetyWhite Circle·50d ago·3 min readSummaryListen 0:47
GLM-4.7-Flash-CoderGLM-4.7-Flash-Coder is a new coding model.
News Hub
What actually shipped in agent engineering, pulled from the labs, arXiv and Hacker News.
See who we follow3 articles
SafetyWhite Circle·135d ago·3 min read
RISE: Red-teaming via Iterative Strategy EvolutionWhite Circle presents RISE, a red-teaming method using iterative strategy evolution.
SafetyWhite Circle·210d ago·3 min read
KillBench: Discovering Hidden Biases of LLMsKillBench is a tool for identifying hidden biases in language models.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.