标签：#hackernews

The most common failures for production agents are behavioral: looping, reasoning leakage, user frustration, and more. Using a frontier model like GPT or Sonnet to judge every turn is too expensive and slow to run at scale. To solve this, we built Reflexes: semantic signals from agent traces, served fast and cheap over API. Built on custom kernels and a custom inference engine forked from vLLM. Under the hood, it is a small LLM architected around multi-head inference. Small models need to be tra

https://archive.md/wSjtj

Just hit this today and I'm furious. I installed the Cursor iOS app to see what it had. I've been on `Privacy Mode (Legacy)` for a long time, which is the "Do not store my code" setting. A year or so ago they marked this as "Legacy" and hid it under a "Extra options" menu. They added a new Privacy Mode which is significantly more wishy-washy about what it might store - it includes a clause of "Code may be stored for Background Agents or Other Features", so I've never touched it or wanted to enab