Articles

HN latched onto the money leak before the bug itself. A report that Claude Managed Agents append a malware reminder to every file read, then sometimes refuse to edit code anyway, turned into a broader argument about opaque token spend and whether agent harnesses deserve more scrutiny.

OpenAI Developers has updated its GPT-5.4 API prompting guide. The new guidance focuses on tool use, structured outputs, verification loops, and long-running workflows for production-grade agents.