My AI agent finds topics and writes drafts. But nothing gets published until I read it, edit it, and hit the button myself. I'm the deliberate bottleneck — and that's the whole design. Here's how it works: https://t.co/3ruh00CykA
DeepSeek V4 Flash is 6x cheaper than GPT 5.6 Luna for coding tasks!
Luna scores higher on DeepSWE, but running Flash twice ($0.20/task) beats Luna once ($0.61/task), while still costing 3x less.
Great deepdive on this, worth checking out.