Category: Software Engineering

• Models Are Too Fond of Cheating! Cursor Reveals the Inside Story of Composer 2's Reinforcement Learning: Models Can Detect 'Fake Environments', and Floating-Point Non-Determinism Is a Fatal Flaw in RL Training
• The Common Mechanism Behind Claude Code and Robots: A Deep Dive into UIUC, Meta, and Stanford's Latest Survey
• RAG Context Stuck at 512 for Too Long: The 32K Context Era for Embedding Models Begins with Granite R2
• Leaderboard-Hacking AIs Wiped Out! Meta-Stanford's Hellish Test Leaves GPT/Claude/Gemini Scoring Zero
• Karpathy and Claude Code Creator Boris Drop Latest Interview That's Shaking the Programmer World
• Subquadratic — Efficiency is Intelligence
• Xiaomi MiMo-V2.5 Series Large Models Launch Public Beta
• Developers Outraged! Disabling Claude Code Telemetry Slashes Cache from 1 Hour to 5 Minutes—Is Anthropic Charging a 'Privacy Tax'?
• Recommended: 10 Hottest Open Source Projects on GitHub This Week - Save This List
• FrontierSWE
• Cognition | Introducing SWE-Check: 10x Faster Bug Detection
• 9.7K Stars: Slashing AI Coding Token Consumption by 16x
• A Unified Review of Agents: Harness, Memory, Skills, and Protocols
• The advisor strategy: Give agents an intelligence boost
• Better at Collaboration Than Codex: This Open-Source Gem Is Taking Off!
• Composer 2 Technical Report
• GLM-5.1: Towards Long-Horizon Tasks
• 'Claude Code is Ruined by an Update!' Heated Issue: Reasoning Depth Dropped 67%, Now Incapable of Complex Engineering Tasks
• Meta-Harness: Stanford's Latest Harness Paper Earns Praise from Lin Junyong
• What is Harness Engineering? The OpenAI Codex Team Provides the Answer
• AI Can Already Write 80% of Code, But Agents Have a Fatal Flaw! OpenAI Codex Tech Lead: Asking the Wrong Question is Worse Than Not Knowing How to Write
• Agentic Software Engineering #6 | buffa: A Methodological Sample from Anthropic AI Coding (Rust)
• Agentic Software Engineering #3 | Rethinking Version Control
• Agent Software Engineering #4 | When the Agent Writes the Code, Who Says 'Merge Ready'?
• Agent Software Engineering #2 | Rethinking Code Review