Anyone else noticing an uptick in confidently stated nonsense on HN? To write that JSON-RPC is "too heavy for editor", you have to not only misunderstand the cost of JSON encoding (trivial) but also the frequency of editor-tool interaction (seldom) and volume of data transferred (negligible). In addition, you have to look at LSP, MCP, and other JSON-y protocols and say "yep. There's where the UI latency is. Got it.". (Nope)
Are people who assert that JSON-RPC is "heavy" writing code we all rely on?