There’s a classical intuition in computer science that verifying a solution is easier than finding one. For NP-complete problems, this
Continue readingWhy Verification Is Harder Than Generation for AI Coding Agents
The dominant scaling narrative in large language models has been straightforward: more parameters, more data, more compute. But there’s a
Continue readingLoopCoder-v2: Why Two Loops Beat Four in Test-Time Compute Scaling
Editor’s note, September 2026: The DeltaDB beta promised below shipped — but as a separate product. In August, Zed introduced
Editor’s note (September 11, 2026): This post was fact-checked in September 2026: every architecture and benchmark figure below was verified
Continue readingThe Open-Weight AI Race Heats Up: DeepSeek V4, Kimi K2.6, and Qwen 3.6