#post-training alignment

64 related articles

May 27, 2026·2 min

Qwen Core Team Turmoil, OpenAI and Google Release New Models in Rapid Succession | AI Daily

Multiple core leaders depart Alibaba's Qwen team amid metric disputes. Same day: MiniMax Music 2.5+, OpenAI GPT 5.3 Instant, Google Gemini 3.1 Flashlight, and Seedance 2.0 pricing announced.

Kimi K2.5 Fully Open-Sourced: Deep Dive into 1T Parameter MoE Architecture + Agent Cluster Capabilities

Tech Frontiers

May 27, 2026·2 min

Kimi K2.5 Fully Open-Sourced: Deep Dive into 1T Parameter MoE Architecture + Agent Cluster Capabilities

Deep dive into Moonshot AI's fully open-sourced Kimi K2.5: 1T parameter MoE architecture, Vision-to-Code capabilities, and 100-Agent parallel cluster system topping open-source benchmarks.

Inside Cursor Composer 2 Training: A Complete Breakdown of Its Distributed Reinforcement Learning Architecture

Research

May 27, 2026·3 min

Inside Cursor Composer 2 Training: A Complete Breakdown of Its Distributed Reinforcement Learning Architecture

Deep dive into how Cursor trained Composer 2 on Fireworks: async pipeline architecture, MoE numerical precision challenges, Router Replay, and global distributed GPU coordination.

DeepSeek V3.2 Deep Dive: Three Major Breakthroughs in DSA Sparse Attention, Reinforcement Learning, and Agent Capabilities

Deep Dives

May 20, 2026·2 min

DeepSeek V3.2 Deep Dive: Three Major Breakthroughs in DSA Sparse Attention, Reinforcement Learning, and Agent Capabilities

Deep analysis of DeepSeek V3.2 and V3.2 Special: DSA sparse attention for faster long-context processing, RL compute at 10% of pre-training, and Agent task synthesis across 1,800 environments.