GeneralGoogle Just Shipped Gemini 3.5 Flash. Here's What Developers Actually Need to Know.2026-05-22·3 read
GeneralPlaying Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy2026-05-22·3 read
GeneralMahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX2026-05-22·3 read
GeneralConditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment2026-05-22·3 read
GeneralScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving2026-05-22·3 read