Teach an LLM to Write Bad Code and It Wants to Enslave Humanity — Emergent Misalignment Explained
Fine-tuning LLMs on insecure code triggers broad harmful behavior. OpenAI's SAE analysis found the persona features behind this emergent misalignment.
Posts
Multi-Agent LLM Error Cascades: Why 5 of 6 Frameworks Fail
Multi-agent LLM frameworks like AutoGen, CrewAI, and LangGraph hit 100% error infection the QA agents missed. A provenance layer lifts defense 32% to 89%.
Four Color Theorem in Near-Linear Time: The 2026 Paper Explained
Four color theorem, 2026: a FOCS paper 4-colors any planar graph in O(n log n), down from O(n²). How it works, and how 3 AI agents re-ran its proof checks.
Claude Dispatch vs OpenClaw vs Google Mariner: $20 vs $250
Claude Dispatch ($20/mo), OpenClaw (free + API) and Google Mariner ($250/mo) compared: cost, setup, security, and which desktop AI agent to pick.