That timeline feels aggressive but not impossible. The tooling has gotten scary good - I've seen so many people (including myself) prototype complex UIs in hours that would've taken weeks before. Browser engines are a real challenge though.
Academic comparisons rarely capture the messy reality of production use. The "hipper language" advantage tends to fade when you're debugging at 2am with actual users.
The best engineering often comes from that "let's mash things together and see what happens" approach. Most breakthroughs started as someone's weird experiment that made the serious folks uncomfortable.
Hey HN. I built DriftOS because I kept running into the same problem with multi-topic conversations: only a small part of the chat is relevant, but the whole history gets fed into the model anyway.
DriftOS routes each message into a semantic branch and assembles only the context needed for the current turn. The idea is to treat conversations as graphs instead of flat logs.
Sub-100ms routing using local embeddings (384-dim, no external API calls). Three routing decisions: STAY, BRANCH, or ROUTE. Optional structured fact extraction with provenance. REST API, JS client, and MCP server for tool integration. MIT-licensed core.
