All Posts
Filter by keyword, tag, and category.
GPT-5.6 and the Quiet Beginning of Recursive Self-Improvement
In July 2026, OpenAI released the GPT-5.6 model series. The headline wasn't benchmark scores or pricing — it was that flagship model Sol autonomously post-trained the smaller Luna model, marking the first time an AI replaced human researchers in a model development pipeline. The recursive self-improvement flywheel has started turning.
The Biggest Shift in AI Coding Isn't Better Models — What Superpowers' 240K Stars Tells Us
Superpowers hit 240K GitHub stars by telling AI not to write code until it thinks first. Alongside rising developer AI fatigue, this marks a fundamental shift: the next phase of AI coding isn't about stronger models, it's about better engineering processes.
MCP 2026-07-28: Going Stateless
MCP's largest revision yet drops the initialize handshake and session IDs for a stateless core. Here's what changes, why it matters, and three migration mistakes to avoid.
TypeScript 7.0: More Than Just Speed
TypeScript 7.0 rewrites the compiler in Go for 8-12x faster builds. But the real impact on daily development comes from the quietly changed defaults. Here's what actually matters in this upgrade.
TypeScript 7.0 RC: The Compiler Now Runs on Go, and It's Fast
TypeScript 7.0 RC rewrites the compiler core in Go, delivering 8-12x faster builds on large codebases. Here's why Go, how it actually performs, and what the migration looks like.
The Quiet Revolution of GPT-5.6: When AI Started Training Itself
OpenAI's GPT-5.6 series launched with flagship model Sol scoring a record 91.9% on Terminal-Bench 2.1—but the real earthquake was buried in the fine print: the lightweight Luna model was post-trained entirely by Sol, without human intervention. The recursive self-improvement flywheel has begun to turn.
TypeScript 7.0 in Practice: What Happens When Your Compiler Gets 10x Faster
TypeScript 7.0 rewrites the compiler in Go, delivering 8-12x faster builds. Here's my migration experience on a mid-sized Next.js project: what changed, what broke, who can upgrade now, and who should wait.
DeepSeek V4 and the Great AI Reversal: How Chinese LLMs Took the Lead
DeepSeek V4 launches on July 15 with a 1M-token context window, time-of-use pricing, and industrial-grade code generation. Meanwhile, Chinese LLMs have dominated OpenRouter's global rankings for ten consecutive weeks. Here's a deep dive into the technology, economics, and geopolitics behind this shift.