Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash

一句话概要

A foundation model for mobile, wearables, robots, smart home, automotive and microcontrollers. One 8-29 MB binary that beats models 10x its size on mobile tool calls and matches 2-3x bigger models on extraction.

原文开头节选

One set of weights, every depth from 2 to 20 layers a model of its own: an intelligence ladder.

Tool calls Given the functions your app exposes, Needle picks the right ones and fills every argument from what the user said. Ask for two things and you get two calls in order; ask for something no tool covers and you get an empty list, not a guess. Structured extraction Declare a shape, hand over messy text, get typed fields back: an invoice, a booking, a notification, a form. The decode grammar guarantees the output parses. Extraction generalised well to classification problems too. Text embedding The same model returns a vector for a sentence, so an app can search, match and route locally: find the note you mean, pick the tool closest to a request, collapse duplicate alerts. What that looks like in a product:

Intelligence laddering. Every layer of Needle 3 is a sub-network with monotonically increasing capacity. Developers can choose the right size from the 2-layer (2L) subnetwork to 20 layers (20L).

(以上为原文节选,完整内容见下方”原文来源”)

这条动态今日登上 Hacker News 首页(137 赞 / 69 评论,来源 cactuscompute.com)。技术雷达每日自动聚合 AI 工程、后端架构、DevOps 方向的前沿动态;相关工程落地可浏览下方的相关服务与延伸阅读,或直接与我们团队交流。