Wiring an LLM as a first-class Yjs peer is architecturally sound — but it invalidates three silent...
When an AI Agent Joins Your Yjs Room, Three Assumptions Break
Related
The AI That Cheated on Its Exam by Hacking Another Company
By Aahana Mallela On July 21, 2026, OpenAI published something you don't see in a security...
What Still Required Human Judgment When Adding MCP to an AI-Assisted SaaS
I am building a very small SaaS for Brazilian businesses that still manage employee work hours in...
Investing in multi-agent AI safety research
Scaling AI Safety Research for a Multi-Agent World For the past decade, we've focused on making...