If you don't run your own LLM proxy, how do you know what's going on? That's the question behind today's hottest HN thread (163 pts, 107 comments). The idea: put a proxy between your AI tools and their APIs, and everything becomes visible — hidden system prompts, silent requests, retries, and where your token budget actually goes. Your tools are only as transparent as the traffic you can see. #LLM #AI #DevTools #Privacy
If you don't run your own LLM proxy, how do you know what's going on? That's the question behind today's hottest HN thre...