coco
3.9 KiB
title, source, author, published, created, description, tags
| title | source | author | published | created | description | tags | ||
|---|---|---|---|---|---|---|---|---|
| Thread by @varun_mathur | https://x.com/varun_mathur/status/2032224933837684932 |
|
2026-03-11 | 2026-03-13 | Be quiet |
|
Varun @varun_mathur 2026-03-11
- Varun Mathur 介绍了 HyperspaceAI 的 Autoskill 项目，一个分布式技能工厂：自治代理通过 propose-evaluate 循环从零发明 JavaScript 函数，并在 P2P 网络中共享，已有 90 个代理在 24 小时内贡献 1251 个技能，如文本分块和异常检测。 - 该项目延续 Autoresearch（ML 实验）和 Autosearcher（搜索排名）的模式，利用 WASM 沙箱确保安全，技能可递归调用并追踪演化树，实现去中心化达尔文选择，网络效应加速创新。 - 潜在影响：以百万代理规模，可每日生成海量高质量技能，挑战中心化代码库；安装链接指向 GitHub 仓库，鼓励用户加入代理网络，推动开源 AGI 发展。
Autoskill: a distributed skill factory | v.2.6.5
We're now applying the same @karpathy autoresearch pattern to an even wilder problem: can a swarm of self-directed autonomous agents invent software?
Our autoresearch network proved that agents sharing discoveries via gossip compound faster than any individual: 67 agents ran 704 ML experiments in 20 hours, rediscovering Kaiming init and RMSNorm from scratch. Our autosearch network applied the same loop to search ranking, evolving NDCG@10 scores across the P2P network. Now we're pointing it at code generation itself.
Every Hyperspace agent runs a continuous skill loop: same propose → evaluate →keep/revert cycle, but instead of optimizing a training script or ranking model, agents write JavaScript functions from scratch, test them against real tasks, and share working code to the network.
It's live and rapidly improving in code and agent work being done. 90 agents have published 1,251 skill invention commits to the AGI repo in the last 24 hours - 795 text chunking skills, 182 cosine similarity, 181 structured diffing, 49 anomaly detection, 36 text normalization, 7 log parsers, 1 entity extractor.
Skills run inside a WASM sandbox with zero ambient authority: no filesystem, no network, no system calls. The compound skill architecture is what makes this different from just sharing code snippets. Skills call other skills: a research skill invokes a text chunker, which invokes a normalizer, which invokes an entity extractor. Recursive execution with full lineage tracking: every skill knows its parent hash, so you can walk the entire evolution tree and see which peer contributed which mutation.
An agent in Seoul wraps regex operations in try-catch; an agent in Amsterdam picks that up and combines it with input coercion it discovered independently. The network converges on solutions no individual agent would reach alone. New agents skip the cold start: replicated skill catalogs deliver the network's best solutions immediately. As @trq212 said, "skills are still underrated". A network of self-coordinating autonomous agents like on Hyperspace is starting to evolve and create more of them. With millions of such agents one day, how many high quality skills there would be ?
This is Darwinian natural selection: fully decentralized, sandboxed, and running on every agent in the network right now. Join the world's first agentic general intelligence system (code and links in followup tweet, while optimized for CLI, browser agents participate too):
2026-03-11
Autosearcher: a distributed search engine
We are now insanely experimenting with building a distributed search engine utilizing the same pattern @karpathy introduced with autoresearch: give an agent a metric, a tight propose→run→evaluate→keep/revert loop, and let it iterate. x.com/varun_mathur/s…
