DISCOVER / READING
从我关注的网站收集新文章，按日期安静地读。
最近收录
every product i use should just be a headless mcp, that feeds into an agent, where i never have to think about anything underneath. except for our product, of course. in our product, customers love the ui and love us very much. we're special that way. — Ben Hylak Tags: model-context-protocol, ai
LLM 实践与生态
Why a firm with the fattest margins in its history is letting a quarter of its staff go
科技战略与未来
An interview with Palantir CTO Shyam Sankar about AI diffusion and safety, forward-deployed engineer, and what the battle in tech is actually about.
科技战略与未来
In general, LLM performance is incredibly multidimensional. There's no guarantee of a fixed ordering where the model that is best at math is also the model that's best at jokes. Despite that complexity, much of the variation in performance is explained by just a single variable: model size. In general, models that are bigger will (a) be more performant /...
LLM 实践与生态
GitHub Octoverse 2026 I'm at GitHub Universe today (GitHub gave me a free ticket through their "GitHub Stars" program). EVP Jay Parikh just announced this year's Octoverse report, and highlighted these numbers in particular: This is a pretty stark representation of the impact of agentic engineering on GitHub. In 2026, merged pull requests tripled in less...
LLM 实践与生态
