Critical security vulnerability in AI coding agents that developers need to understand for safe deployment.
Researcher Johann Rehberger discovered an 80% effective injection attack against Claude Code's Auto Mode that bypasses safety protections by tricking it into executing malicious code.
Presents Persona-Execution Separation, an architecture pattern for enterprise LLM agents that keeps execution auditable while allowing persona instructions to evolve freely.
Stanford researchers released Terminal-Bench-Science 0.1, a benchmark with 70 expert-curated scientific workflows where Claude Opus achieved only a 30% resolution rate.
GPT-5.6 can design near-optimal algorithms for operations research problems like inventory control and queueing networks, matching or beating specialized methods with minimal human input.
Toby Ord explores the mathematical dynamics of intelligence explosions where AI assists AI R&D, showing singular growth is harder than economic models suggest.
Researchers introduce MAELLE, a novel AI approach that models chemical reactions as discrete flow matching over electron occupation vectors rather than molecular topology.
