https://news.ycombinator.com/user?id=thandvHacker News RSShttps://hnrss.org/hnrss v2.1.1Tue, 30 Jun 2026 22:24:13 +0000I generally used them for token saving purposes, just using them for repetitive tasks, gated and supervised by claude. So its planned and verified by better models, but implementation falls on local ones. It has been pretty effective for me, as long as I spend a bit more initially on splitting complex tasks further down

]]>Sat, 27 Jun 2026 18:20:12 +0000https://news.ycombinator.com/item?id=48700456thandvhttps://news.ycombinator.com/item?id=48700456https://news.ycombinator.com/item?id=48700456This might be a stupid question, but can a extra added local llm help with the caching problem?

]]>Fri, 26 Jun 2026 21:42:45 +0000https://news.ycombinator.com/item?id=48692355thandvhttps://news.ycombinator.com/item?id=48692355https://news.ycombinator.com/item?id=48692355