Yearly Archives: 2026

In AI-driven development, “does it f*#king work” beats polished syntax every time. Developers once spent days in code reviews chasing clean lines and elegant patterns. We pored over our work, carefully organizing and formatting for readability and clean looking patterns. We did this because we knew we were going to...

How usage data and inference costs drove Anthropic and OpenAI to build identical tier structures for AI coding agents. Anthropic’s Claude Code and OpenAI’s Codex both open at roughly $20 per month for individuals. Serious developers who rely on them daily soon hit rate limits. The next step costs exactly...

New quantization technique slashes LLM memory use and boosts inference speed on existing hardware. Google Research released TurboQuant, a training-free quantization method that compresses key-value (KV) caches in large language models to as little as 3 bits per value. The result: at least 6x lower memory footprint with no drop...