←News detail

AYi AI NotesUpdated Oct 25 21:29

Anthropic engineer shares Claude Code multi-agent orchestration playbook

AI summary

In a 30-minute workshop, an Anthropic engineer demonstrated an advanced use of Claude Code: running more than 100 agents simultaneously within one integrated loop, with 1 main agent in charge, while sub-agents act as project managers to break down tasks, distribute them, and cross-validate results. Based on this, the author suggests developers first use the main window to write task decomposition and acceptance rules, then spawn sub-agents to execute submodules concurrently. The author also warns that when a hundred agents run simultaneously, if termination conditions and permission boundaries are not hard-coded, it is easy to burn a large amount of tokens in an infinite loop, and beginners should start small with one main agent and three sub-agents.

Why read this

AI score 56

The original article recounts an Anthropic engineer's multi-agent orchestration approach and warns about token costs and permission-boundary risks when a hundred agents run simultaneously.

Topics

Tags

Quoted post

AYi

@AYi_AInotes

This is probably the fiercest yet most brilliant dimensional strike in the history of AI and the tech world. The day before, Anthropic was still loudly promoting that it would set aside 5% of its equity to establish a philanthropic fund to address the impact of technology, and Musk left a cold comment in the replies: I suggest you just give the shares directly to the public. Less than twelve hours later, he posted this tweet that stunned the entire internet: Next year, I will give every child in America one share of SpaceX stock I hold. This is just the first of many times. Based on the current market value, this is real money hitting more than 70 million families, with a total value exceeding 10 billion dollars. The most intriguing gap lies in these two completely different distribution paradigms. Traditional elite big tech in Silicon Valley loves to play with a refined set of moral rhetoric, putting shares into a charitable fund they control. On the surface it is giving back to society, but behind the scenes, how the money is spent, who it is invested in, and who draws the high salaries—all the power remains firmly in their own hands. Musk chose the path with the least room for retreat but also the purest one: truly cutting into his own personal assets, with no complicated intermediaries, directly distributing shareholder seats to every ordinary child at the bottom. This is why criticism can only ever bring arguments, but leading by example with action can end the game in an instant. When you accuse your opponent of empty posturing, the most forceful response is not to write a long essay to debate, but to pull out, within half a day, a set of real actions that the opponent simply dares not match and cannot afford to match, tearing away their moral fig leaf on the spot. What is even more formidable is the extremely far-reaching commercial gravitational field behind this move. More than 70 million children will hold a share of a rocket company flying into space in their accounts from childhood, which means that nearly every family in America will naturally become the company's most solid emotional community over the coming decades. Compared with spending billions of dollars on media PR and hollow advertising, this kind of move—binding interests directly to the fate of the next generation—is the truly insurmountable moat. People used to think that tech for good was empty talk written in social responsibility reports. From today on, someone has put the answer on the public screen: true goodness is not loftily setting up relief funds, but distributing the assets that belong to the future fairly, on day one, to the people who create the future. Do you think this approach of directly giving every child one share of hardcore assets, compared with the charitable funds run by a handful of elites at traditional big tech companies, is which one the future tech company should look like? Let me say this first: rather than watching institutions deduct large management fees in a black box every year, I would rather have a real rocket ownership share sitting under my child's name.

View original

这大概是整个人工智能与科技界历史上,最凶狠、但也最漂亮的一场降维打击。 前一天 Anthropic 还在高调宣传要拿出 5% 股权设立公益基金来应对技术冲击,马斯克在评论区冷冷留了一句:我建议你们直接把股份给公众。 结果不到十二个小时,他直接发了这条推文把全网看傻了:
明年把我持有的 SpaceX 股票,给全美每一个孩子送一股,这只是很多次里的第一次。 按现在的市值粗算,这是一笔砸向七千多万个家庭、总额超过一百亿美元的真金白银。 最耐人寻味的差距,就藏在这两种完全不同的分配范式里。
硅谷传统的精英大厂最喜欢玩弄一套精致的道德话术,把股份放进自己掌控的慈善基金,表面上是在回馈社会,背地里资金怎么花、投给谁、由谁领高薪,所有权力依然死死握在自己手里;而马斯克选择了一条最不留退路、但也最纯粹的路径:从自己的个人资产里真刀真枪地割肉,不设复杂的中间环节,直接把股东席位分给最底层的每一个普通孩子。 这就是为什么批评永远只能带来争吵,但行动示范能在瞬间终结比赛。
当你指责对手的假把式时,最暴力的回应不是写小作文去辩论,而是在半天之内掏出一套对手根本不敢跟、也跟不起的真实动作,当场把对方的道德遮羞布扯得精光。 更可怕的是这一步棋背后极度深远的商业引力场。
七千多万个孩子从小在账户里持有一股飞向太空的火箭股票,这意味着几乎全美所有的家庭在未来的几十年里,都会天然成为这家公司最坚固的情感共同体;比起花几十亿美元去买媒体公关和虚浮广告,这种把利益直接和下一代命运绑死的手笔,才是真正不可逾越的护城河。 以前大家以为科技向善是写在社会责任报告里的空话,从今天起有人把答案打在公屏上:
真正的向善不是高高在上地设立救济金,而是把属于未来的资产,在第一天就公平地分给创造未来的人。 大家觉得这种直接给每个孩子发一股硬核资产的做法,和传统大厂搞的那些由少数精英掌管的慈善基金相比,哪一种才是未来科技公司该有的样子?我先说,与其看机构在暗箱里每年扣掉大笔管理费,我宁愿自己孩子名下躺着一张真实的火箭所有权。

View original post

Body · AI translation

If you're using Claude Code and it's still a case of you asking a question and it changing one line, then you're basically just treating it as an advanced version of Google Search.

An Anthropic engineer just revealed the internal advanced playbook in a 30-minute workshop: run more than 100 agents simultaneously in one integrated loop, with 1 main agent in charge, and everyone below acts as project managers leading teams.

Those so-called Vibe Coding training courses on the market that sell for $500 aren't worth as much combined as this 30-minute high-density workshop that the Anthropic engineer just released. He laid out plainly how to squeeze Claude Code dry at the lowest operating cost.

In his sharing, this internal engineer showed off his extremely hardcore daily setup: he runs more than 100 agents simultaneously in one integrated loop, with only one main agent in charge at the top, and the sub-agents below each act as project managers, leading and dispatching the entire R&D team themselves.

Normally when we open Claude Code to write code, the default action is a question-and-answer exchange. If there's an error, we paste it in and ask how to fix it. In essence, we're still using it as a Google Search engine that can write code, with one person watching one terminal window, and when you stop, it stops too.

But this Anthropic engineer pointed out the real watershed that creates a tenfold productivity gap. The true nuclear weapon of Claude Code has never been single-window conversational Q&A, but running it as a self-learning multi-agent swarm. While you're still hand-holding an intern to fix typos, people in the know have already spun up an entire 24/7 virtual engineering team of a hundred people in the background.

And his main-agent-plus-project-manager architecture directly upgrades you to general contractor. You only need to align on the blueprints with the chief foreman, while the project managers below split modules, distribute tasks, and cross-check acceptance themselves, packing the entire project into an automated closed-loop pipeline.

For everyone who heavily uses Claude Code and Cursor to write code every day, this is a level-up move you can copy right away. Starting tomorrow, stop piling all the context into one long conversation window until it explodes.

Try first writing the task breakdown and acceptance rules in the main window, then have it spawn sub-agents to execute different sub-modules concurrently, completely switching your own role from a coder who types code personally to an architect who only looks at the final test results.

But while enjoying the thrilling picture of a hundred agents running together, you also need to stay clear-headed. Although he emphasized in the video how to keep operating costs down, in a real project, once you start an integrated loop of a hundred agents, if the main agent's termination conditions and permission boundaries aren't hard-coded, it's extremely easy to burn through your Token bill in an infinite loop.

Moreover, as an engineer at Anthropic itself, his leeway in allocating internal compute is far beyond that of ordinary pay-as-you-go developers. For beginners, starting with a small swarm of one main and three sub-agents is the safest path.

Treating a top-tier coding agent as a search engine for Q&A is like buying an entire automated fleet but only taking the flagship out to row on a park pond every day.

The core multi-agent architecture and cost-reduction points of this 30-minute workshop are compiled in the first floor [comment]. I suggest watching it together with the original video. https://t.co/OAp6oUuseD

Source

AYi AI Notes