9 种你可能还没尝试过的 AI 技巧

如果我告诉你，你使用AI的方式完全错了呢？

What if I told you you were using AI all wrong?

那我就是在撒谎，而且显然是想用一个极其荒谬和离谱的噱头来吸引你点击。

Well, then I'd be lying, and I'd clearly be trying to get you to click on something by using an absolutely ridiculous and preposterous hook.

但换个说法，如果我告诉你，有九种AI技巧已经给一些人带来了非常棒的结果，而你也许还没来得及尝试呢？

But instead, what if I told you that there were nine AI techniques that were delivering some really awesome results to some people that you might not have had the time to try just yet?

这会更接近事实，因为在过去几个月里，我们看到大量新功能和新工具涌现，比如Claude的design功能、Codex的实时语音模式，还有GrokBot让用户通过观看屏幕来训练整个工作流程的能力。

That would be a lot more true, because over the last couple of months, we've seen a slew of new features and new tools become available like Claude slash design and Codex's live voice mode and GrokBot's ability for a user to train it on an entire workflow by watching the screen.

AI之所以让人兴奋，也正是它最具挑战性的地方——它一直在变化。

One of the things that makes AI so exciting is also the thing that makes it the most challenging that it's changing all of the time.

但今天的节目会让你很快跟上节奏。

But today's episode is going to get you up to speed in no time at all.

《AI每日简报》是一个每日播客和视频节目，内容涵盖AI领域最重要的新闻和讨论。

The AI Daily Brief is a daily podcast and video about the most important news and discussions in AI.

好了，朋友们。

Alright, friends.

在开始之前，先快速说几个通知。

Quick announcements before we dive in.

首先，感谢今天的赞助商：毕马威、Blitzy、Harbor 和 Hyperagent。

First of all, thank you to today's sponsors, KPMG, Blitzy, Harbor, and Hyperagent.

想要收听无广告版本，请访问 patreon.com/aidailybrief，或者也可以在 Apple Podcasts 上订阅。

To get an ad free version of the show, go to patreon.com/aidailybrief, or you can subscribe on Apple Podcasts.

想了解如何赞助节目，请发送邮件至 sponsors@aidailybrief.ai。

To learn more about sponsoring the show, send us a note at sponsors@aidailybrief.ai.

另外，在访问 aidailybrief.ai 时，可以查看下周免费网络研讨会的链接，主题是知识工作者的代理循环。

And while you're on a I daily brief dot a I, you can check out the link to next week's free webinar about agentic loops for knowledge workers.

如果你听我或其他人说过循环是第二次革命，但不太确定如何应用到你的工作中，那么这个免费网络研讨会就是为你准备的。

If you have heard me or others talk about loops as basically the second coming but aren't exactly sure how to apply them to your work, this free webinar is for you.

我会到场。

I will be there.

大部分内容将由 New Fargaspar 主讲。

New Fargaspar will be leading most of it.

你可以免费注册，就算到时候来不了，我们之后也会把录播发给你。

You can register for free, and even if you can't make it, we will send you the recording after.

再说一遍，所有信息都在aideallybrief.ai上。

Again, all that information is at aideallybrief.ai.

哎呀，朋友们，AI这趟热潮真是越炒越热啊。

Well, my goodness, friends, the AI hype train is a hypin'.

但在这个故事里，AI真正扮演的角色是什么呢？

But what is AI's real role in this story?

最近，Anthropic的CEO达里奥·阿莫迪和他的几位批评者之间，围绕他言论的基调展开了一场讨论。

Recently, there was a whole discussion between Anthropic CEO Dario Amade and some of his critics about the tone of his messaging.

面对批评说他过于悲观的回应，达里奥基本上是说，改变人们对AI看法的不会是营销，而是AI真正拿出成果来。

One of Dario's responses to the critique that he had been overly negative was basically to say that it wasn't going to be marketing that changed people's opinions about AI, it was going to be AI actually delivering results.

具体来说，他发帖说：我不认为靠一场光鲜亮丽、积极正面的营销活动就能赢回信任。

Specifically, he posted: I don't think that a glitzy marketing campaign with a positive spin is the way to win back trust.

到了这个阶段，说AI能治愈癌症，与其说是鼓舞人心，不如说是陈词滥调，而且大多数人觉得这很虚伪。

At this point, saying that AI will cure cancer is more a cliche than it is inspiring, and most people think it is deceptive.

真正管用的，是实实在在地治好癌症。

The thing that will work is actually curing cancer.

所以昨天有很多人基本上都在说，这事儿真的发生了。

Which is why there were a lot of folks basically saying that that's what had happened yesterday.

周三，Moderna和默克公司宣布，他们的个性化癌症疫苗三期试验成功，这是首个显示出希望的后期试验。

On Wednesday, Moderna and Merck announced a successful stage three trial for a personalized cancer vaccine the first late stage trial that's shown promise.

这种治疗方法和化疗完全不同。

The treatment functions very differently to chemotherapy based approaches.

它不是用放射线去轰击癌细胞，而是分析癌细胞，找出导致癌症的DNA突变，然后制造一个个性化的mRNA疫苗来纠正这个突变。

Instead of blasting the cancer with radiation, the new method involves analyzing the cancerous cells, identifying the DNA mutation causing the cancer, and creating a personalized mRNA vaccine that can correct the mutation.

试验发现，这种治疗方法对超过1100名晚期黑色素瘤患者有效，延长了他们的缓解期。

The trial found the treatment was successful in more than eleven hundred patients with advanced melanoma by extending their time in remission.

Moderna和默克公司也在进行针对肺癌的类似试验，科学家们希望这种治疗能应用于多种癌症。

Moderna and Merck have similar trials underway for lung cancer, and scientists hope the treatment can be applied to many different cancers.

医生。

Doctor.

麻省总医院黑色素瘤中心主任瑞安·沙利文表示：这对整个领域来说意义重大。

Ryan Sullivan, Director of the Center for Melanoma at Mass General, said: It's a big deal for the field in general.

有了这项积极的研究，我们有望看到后续投资跟进，这些方法可能会更广泛地改变我们治疗癌症的方式。

With this positive study, there is a hope and likely investment to follow that these approaches may change the way we treat cancer more broadly.

这引发了AI社区很多兴奋的帖子，比如丘比发的这条。

This gave rise to a lot of very excited posts from the AI community like this one from Chubby.

这简直太牛了！

This is freaking huge!

他们写道。

They wrote.

AI辅助的个性化mRNA癌症治疗首次在III期试验中取得成功。

For the first time, an AI assisted personalized mRNA cancer treatment has succeeded in a Phase III trial.

Moderna和默克公司对每位患者的肿瘤进行测序，并将其与他们的健康DNA进行对比。

Moderna and Merck sequence each patient's tumor and compare it to their healthy DNA.

然后AI帮助识别肿瘤的哪些突变最有可能触发免疫反应。

AI then helps identify which of the tumor's mutations are most likely to trigger an immune response.

太不可思议了！

Absolutely incredible!

达里奥说得对！

Dario was right!

癌症几年内就能被治愈！

Cancer will be cured in just a few years!

当然，也有人对这个被称为AI的东西提出了质疑。

Some of course took issue with the labeling of this as AI.

Antibody forty two总结了批评意见，说：这太蠢了。

Antibody forty two summed up the criticism saying: This is so dumb.

他们用AI这个词来代替机器学习，因为对不关心现实的人来说，这两者的区别并不重要。

They are using AI in place of machine learning because the distinction doesn't matter to people who don't care about reality.

AI用于mRNA设计已经有一段时间了。

AI for mRNA design has been around for a while.

它不是大语言模型。

It's not an LLM.

抛开语义不谈，重要的是要指出，这并不是科学家们把一堆结果塞进ChatGPT，然后让它想出一个个性化的癌症治疗方法。这些是先进的机器学习方法，与支撑AlphaFold的技术有更多相似之处。

And holding aside semantics, it is important to note that this is not scientists just plugging a bunch of results into ChatGPT and asking it to come up with a personalized cancer cure These are advanced machine learning methods that have more similarities to the technology underpinning AlphaFold.

而且坦白说，我们也不应该忽视那些与机器学习技术合作、开发这些新疗法的杰出人类科学家，不能简单地把突破归功于AI。

It's also frankly important not to lose the brilliant human scientists that are working with machine learning techniques to come up with these new treatments by simply attributing the breakthrough to AI.

话虽如此，我也认为，如果说这只是AI炒作潮，那也太轻率了。

That said, I do also think it would be dismissive to say that this is just the AI hype train.

虽然现在还处于早期阶段，但这确实有潜力成为治愈癌症的重要一步。

Although it's still early days, this has genuine potential to be a major step towards curing cancer.

虽然这与大语言模型和聊天机器人没有直接关系，但这项技术仍然从近年来对计算、研究和人才的投资中受益匪浅。

And while it isn't directly related to LLMs and chatbots, this technology has still benefited greatly from all of the investment into compute, research, and talent over recent years.

AI时代，不管有没有大语言模型，都在为一些真正非凡的突破奠定基础，这值得庆祝。

The AI era, LLMs or not, is setting the stage for some truly remarkable breakthroughs, and that is something worth celebrating.

市场当然在庆祝。

Certainly the market s celebrating it.

Sheba Loor指出，Moderna的股票在公告后上涨了70%，几小时后飙升至125%的涨幅。

Sheba Loor pointed out that Moderna stock was up 70% after the announcement, rocketing up to 125 percent growth just a few hours later.

埃隆·马斯克说，很多突破即将到来。

Said Elon Musk, So many breakthroughs are coming.

接下来这个话题，跟治愈癌症比起来似乎很普通，但对很多企业来说却极其重要。OpenAI 推出了一项新的安全技术，让他们可以在不持续监控用户的情况下提供前沿 AI。

Next up, a topic which seems extremely pedestrian next to curing cancer but is extremely important for lots of enterprises OpenAI has come up with a new safety technique that will allow them to offer Frontier AI without constantly monitoring their users.

他们把这个过程称为“私有安全处理”，并将把它应用于符合条件且签署了零数据保留协议的 API 客户。

They're calling the process private safety processing and will be applying it to eligible API customers with zero data retention agreements.

OpenAI 表示，这将使他们能够兑现承诺，在请求完成后不保留提示或输出，并确保敏感的企业数据不会让 OpenAI 的员工看到。

OpenAI says this will allow them to fulfill their promise of not retaining prompts or outputs after a request has been completed, and ensure that sensitive corporate data is not available to OpenAI staff.

随着长周期智能体的兴起，安全监控变得困难得多。

Since the rise of long horizon agents, safety monitoring has become much more difficult.

旧系统的设计只能评估单个交互，而不是评估智能体工作的整个流程。

Older system designs can only evaluate individual interactions, rather than assessing the entire arc of agentic work.

Anthropic 解决这个问题的方法很简单，就是直接禁用 Fable 的零数据保留功能，收集每次会话的完整数据来扫描有害活动。

Anthropic solution to this problem has been to simply disable zero data retention for Fable, gathering full data from each session to scan for harmful activity.

对很多企业客户来说，这完全不可接受，这也导致了 Fable 在企业中的采用率相当低。

For many enterprise customers this is a complete non starter and has shown up in fairly dismal adoption of Fable in the enterprise.

OpenAI的新系统将自动化安全扫描扩展到整个会话过程，包括客户控制的数据存储，这些数据在多步骤的智能体操作中用于上下文。

OpenAI's new system extends automated safety scanning across an entire session, including customer controlled data storage used for context in multiple agentic steps.

这种扫描仍然是完全自动化和加密的，意味着没有任何人能看到敏感数据。

This scanning is still fully automated and encrypted, meaning that no human ever lays eyes on sensitive data.

如果发现问题，OpenAI员工会收到一份活动摘要，包含类别和严重程度评级，但不会包含任何客户数据。

If an issue is flagged in OpenAI employee gets a summary of the activity with a category and severity rating, but stripped of any customer data.

这意味着误报不再会导致数据泄露，同时也让OpenAI能够开发更强大的模型，而不需要完全透明的审查。

This means that false positives will no longer cause data exposure, as well as allowing OpenAI to develop more powerful models without the need for fully transparent review.

简单来说，这一变化可能有助于减少企业在使用AI时在风险和安全性之间的权衡。

The TLDR is that this is a change that could help make AI in the enterprise less of a trade off around risk and security.

OpenAI的产品政策负责人Aaliyah Howes表示：我们一直在和许多企业客户交流，他们非常非常关心企业数据的隐私和安全。

OpenAI's Head of Product Policy, Aaliyah Howes, said: We've been talking to a bunch of enterprise customers and they really, really care about their enterprise data privacy and security.

我们非常清楚地听到企业表示这很重要，他们通常对客户有自己的承诺。

We've heard very loud and clear from businesses that this is important they often have their own commitments that they have made to their customers.

总结一下，OpenAI员工Adam GPT补充说：这是那种看似小事但实际上是大事的事情之一。

Summing it up, OpenAI staff member Adam GPT added: This is one of those small things that is actually a huge thing.

而且根据我一直在跟企业界关于AI的交流来看，这绝对是事实。

And based on my ongoing conversations with enterprises around AI as well, that is absolutely true.

OpenAI还宣布了一项新的合作，为Replit新推出的免费模式提供模型。

OpenAI also announced a new partnership, providing the model for Replit's newly launched Free Mode.

不过，尽管名字叫免费模式，它并不是真的免费。

Now despite the name, Free Mode isn't literally free.

实际上，它让每月20美元计划的用户能够在不消耗使用积分的情况下使用Replit。

Instead, it gives users on the $20 a month plan the ability to use Replit without spending usage credits.

免费模式将所有查询都通过GPT-5.0.6 Luna处理，Replit表示，这将让用户在他们正常的订阅下多创建30倍的内容。

Free Mode routes all queries through GPT-five 0.6 Luna, which Replit says will allow users to create 30 times more on their normal subscription.

当Luna不足以应对复杂任务时，用户仍然可以切换到其他模式来选择更强大的模型，但对于像头脑风暴或快速制作幻灯片这样的日常任务，很多人发现Luna已经绰绰有余了。

When Luna isn't enough for a complex task, users can still shift to another mode to select a more powerful model, but for everyday tasks like ideating or spinning up a slide deck, many are finding Luna to be more than enough.

在Replit的发布博客文章中，他们写道：AI模型现在的能力和成本已经足够让曾经遥不可及的结果变得切实可行。

In their launch blog post, Replit wrote: AI models are now capable and affordable enough to make once unreachable outcomes practical.

而我觉得有趣的是，OpenAI更侧重于营销和推广5.6 Luna，而不是这个Replit合作的具体细节。

And I think what's interesting to me is MORE OpenAI's focus on marketing and promoting 5.6 Luna as opposed to the specifics of this Replit partnership.

如果你一直密切关注，就会发现OpenAI显然是在两条截然不同的战线上同时竞争。

If you've been watching closely, it's clear that OpenAI sees themselves as competing on two very different axes at once.

他们当然在尖端技术方面与Five竞争。

They are of course competing at the state of the art with Five.

还有Six SOL以及即将推出的Astra模型，但尤其是自从他们推出Luna以来，很明显他们也在关注身后的中国开源权重模型，并且完全不愿意放弃那块阵地。

Six SOL and the Astra model to come, but especially since they launched Luna, it's very clear that they are also looking behind them to the Chinese open weight models, and are completely unwilling to surrender that ground as well.

我预计，随着用户对哪些任务需要什么级别的算力有了更成熟的理解，我们会看到更多在效率前沿上的竞争，而不仅仅是能力前沿。

I would expect that as we see more maturation among users, in terms of their understanding of which power levels are required for which different types of tasks, we re going to see a lot more of this competition on the efficiency frontier, not just the capability frontier.

现在离开Replit，但继续关注AI编程初创公司，彭博社本周报道称，SpaceX已就潜在交易接触了编程代理初创公司Cognition。

Now moving off of Replit but staying around AI coding startups, Bloomberg reported this week that SpaceX had approached coding agent startup Cognition about a potential deal.

彭博社援引知情匿名人士的话说：“交易谈判目前并不活跃，但两家公司仍在继续讨论合作事宜，包括可能安排Cognition使用SpaceX的计算能力。”

Citing anonymous sources familiar with the matter, Bloomberg wrote: The deal talks are not currently active, but the companies continue to hold discussions about working together, including potentially arranging for Cognition to use SpaceX's computing capacity, said the People.

Cognition最近在5月份以260亿美元的估值融资，据报道，该公司正在寻求在新一轮融资中获得至少400亿美元的估值，该轮融资仍处于早期阶段。

Cognition most recently raised at $26,000,000,000 in May and is reportedly seeking a valuation of at least $40,000,000,000 in a new round that's still in the early stages.

重要的是，这份报告表明，SpaceX将Cognition视为Cursor的补充而非替代品，而且对于密切关注的人来说，埃隆·马斯克愿意花费约1000亿美元收购构建AI应用层的初创公司并不令人意外。

Importantly, the report suggests that SpaceX is looking at Cognition as an addition to Cursor rather than an alternative, and certainly it's not surprising to people who've been watching closely that Elon Musk would be willing to spend around $100,000,000,000 on acquiring startups that are building the AI app layer.

不过，报道发布后不久，Cognition的CEO斯科特·吴就完全否认了这件事。

However, shortly after the report was published, Cognition CEO Scott Wu disavowed the entire thing.

他在X上发帖说：这不是真的。

In an X post he wrote: This is not true.

我非常尊重SpaceX团队，但Cognition不出售，我们也没有谈过。

Huge respect for the SpaceX team, but Cognition is not for sale and we haven't been talking.

彭博社记者丽贝卡·托兰斯坚持她的报道，并批评媒体素养的缺失，评论说：需要澄清的是，根据我们的消息来源，SpaceX主动接触了Cognition并提出收购。

Bloomberg journalist Rebecca Torrance stood by her reporting and decried the death of media literacy, commenting: To be clear, according to our sources SpaceX approached Cognition with a bid.

报道并没有说Cognition回应了那次接触。

The story does not say Cognition engaged with that attempt.

当晚晚些时候，埃隆把事情平息了，说：斯科特说的没错。

Later in the evening Elon put the matter to bed, saying: What Scott says is accurate.

我们和Cognition除了确保Grok能满足他们的需求外，没有谈过任何其他事情。

We haven't talked with Cognition about anything except making sure Grok works well for their needs.

这是那种你其实不必怀疑任何人的罕见情况，特别是因为“主动接触”这件事本身就很模糊。

This is one of those rare cases where I don't think you actually have to doubt anyone, specifically because of the blurriness of what it even means to actually approach someone about a potential deal.

假设埃隆和斯科特某天下午在聊 Grok 4.6 在 Devon 里的运行情况，然后埃隆轻轻拍了拍他的肩膀说：嘿，听着，兄弟。

If Elon and Scott were talking one afternoon about how Grok four point six was working inside Devon, and Elon gives him a little shoulder nudge and says, Hey, listen, man.

如果你考虑过希望 Cognition 未来走向何方，这算不算是在试探收购的可能性呢？

If you ever think about where you wanna see Cognition in the future, does that constitute approaching them about a potential deal?

很多这类提议确实就是这么开始的，而且我确信，即便 Cursor 的交易已经敲定，埃隆对收购的兴趣也远未满足。

That is genuinely how a lot of these offers start, and I certainly think that Elon's appetite for acquisitions has not been sated just because the cursor deal is done.

最后今天再聊聊，围绕政府安全测试框架细节的疑问还在持续。

Lastly today, continued questions around the details of the administration's safety testing framework.

这个框架几周前刚推出来的时候，很多人最担心的就是细节不会公开，让各大实验室以外的人完全摸不着头脑。

When the framework was rolled out a couple of weeks ago, one of the big concerns for many was that the details wouldn't be made public, leaving everyone outside of the major labs in the dark.

白宫是在闭门会议上公布的新框架，只邀请了OpenAI、Anthropic和Google的技术人员参加，但看起来，就连受邀参会的公司也没能完全搞清楚这个新框架的全貌。

The White House unveiled the new framework in a closed door meeting attended only by technical staff from OpenAI, Anthropic, and Google, but it seems that even the companies invited to the meeting are still struggling to get a full picture of the new framework.

据消息人士透露，会议期间他们拿到了纸质版的框架文件，但只能做笔记，不能带走。

Sources said that during the meeting they were handed paper copies of the framework but were only allowed to take notes.

这些消息人士还说，白宫至今没有分发书面版的框架内容，也没有分享更多关于本月计划举办的公共AI活动的细节。

Those sources also said that the White House still hasn't distributed written versions of the framework or shared any further details about a public AI event intended to be held this month.

显然，这种不透明并没有阻碍前沿AI的发展，比如最近OpenAI自愿放慢研究速度，就是行业自我调节的一个例子。

Now, obviously, this lack of clarity hasn't been a roadblock for frontier AI development far, given recent decisions like OpenAI's voluntary slowdown in research as an example of the industry pacing itself.

不过，随着这个框架的推出，大家还是明确要求更多的透明度。

Still, there is a clear call for more transparency as this framework is rolled out.

上周，自由意志主义卡托研究所的胡安·拉达诺批评了这种保密做法，写道：白宫基本上是把AI测试体系放进了黑箱。

Last week Juan Ladano of the Libertarian Cato Institute criticized the secretive approach writing: The White House is essentially putting the AI testing regime in a black box.

这种做法违反了法治原则，有可能变得像许可证制度一样具有强制性，最重要的是，它没有实现最基本的目标：赢得公众的信任。

This approach contravenes the rule of law, risks becoming as prescriptive as a licensing regime, and most importantly fails to fulfill its most basic objective: to build trust in the population.

一个引发的问题比解决的问题还多的框架，还不如没有框架。

A framework that raises more questions than the one it answers is worse than no framework at all.

特别是考虑到我们这周关于数据中心和信任的所有讨论，我完全同意。

Especially in light of all of our discussions around data centers and trust this week, I fully agree.

不过，今天的AI每日简报头条版就到这里。

For now though, that's gonna do it for the AI Daily Brief headlines edition.

接下来是主节目。

Next up, the main episode.

毕马威和德克萨斯大学奥斯汀分校的一项新研究发现，当人们与AI合作时，相似的技能并不能保证相似的结果。

A new study from KPMG and the University of Texas at Austin found that when people work with AI, similar skills don't guarantee similar outcomes.

研究人员研究了500多名早期职业专业人士，发现表现最好的人通过指导、评估和完善AI的输出，持续地放大了AI的价值。

Researchers studied more than 500 early career professionals and found that the best performers consistently amplified the value of AI by guiding, evaluating, and refining its outputs.

这些顶尖表现者被称为“AI放大器”，他们的定义不仅仅在于他们知道什么，更在于他们如何与AI合作。

These top performers, called AI amplifiers, weren't defined by what they knew alone, but by how they worked with AI.

想了解更多关于AI放大器与其他人的区别，请访问kpmg.com/us/aiaamplifiers。

Learn more about what separates AI amplifiers from everyone else at kpmg.com/us/aiaamplifiers.

Blitzy对代码库的深入理解，解锁了每个路线图负责人最关心的事情：发布新功能。

Blitzy's deep codebase understanding unlocks the thing every roadmap owner cares about: shipping new features.

在大型企业代码库中开发的真相是：写代码从来不是瓶颈。

Here's the truth about building inside a massive enterprise codebase: Writing code was never the bottleneck.

上下文才是。

Context is.

这会影响到哪个系统？

Which system does this touch?

哪些合同不能出问题？

Which contracts can't break?

适用哪些标准？

Which standards apply?

Blitzy已经知道了，因为它在开始未来工作之前，就把你的整个代码库逆向工程成了一个动态知识图谱。

Blitzy already knows because it reverse engineered your entire codebase into a dynamic knowledge graph before future work began.

有了这个完整的图景，Blitzy就能端到端地构建功能。

With that complete picture, Blitzy builds features end to end.

架构、API、UI和测试都针对你现有的系统进行了验证。

Architecture, APIs, UI, and tests all validated against your existing systems.

有一个Blitzy客户从零开始构建了一个AI原生应用，实现了100%的自主完成，节省了超过两千七百个工程小时。

One Blitzy customer built an AI native application from scratch with 100% autonomous completion, saving over two thousand seven hundred engineering hours.

这些功能尊重你的代码库，而不是与它对抗。

Features that respect your codebase instead of fighting it.

别再让你的积压任务增长得比团队还快了。

Stop letting your backlog grow faster than your team.

去 blitzy.com 加速你的路线图。

Accelerate your roadmap at blitzy.com.

就是 blitzy.com。

That's blitzy.com.

如果你听这个节目，你很可能有自己的观点。

If you listen to this show, you likely have a thesis.

也许是企业采用。

Maybe it's enterprise adoption.

也许是算力。

Maybe it's compute.

也许是某个特定的实验室。

Maybe it's a specific lab.

Harbor Capital 的 AI 实验室生态系统 ETF 让你通过五只主动管理型 ETF 来表达你的观点，每只 ETF 都寻求围绕一个主要实验室的生态系统敞口：Anthropic、OpenAI、DeepMind、Meta 或 SpaceX AI。

Harbor Capital's AI Lab Ecosystem ETFs let you express it via five actively managed ETFs, each seeking exposure to the ecosystem around one major lab: Anthropic, OpenAI, DeepMind, Meta, or SpaceX AI.

你对 AI 竞赛的看法，以 ETF 的形式呈现。

Your view of the AI race in ETF form.

Harbor Capital Advisors的AI实验室生态系统ETF系列，为投资者提供了一种投资他们认为最有成功潜力的AI生态系统的方式。

Harbor Capital Advisors' AI Lab Ecosystem ETF Suite gives investors a way to invest in the AI ecosystem they believe is best positioned for success.

在您投资的地方搜索Harbor AI实验室生态系统ETF，或关注X上的HarborCapital了解更多信息。

Search Harbor AI Lab Ecosystems ETFs wherever you invest or follow HarborCapital on X to learn more.

请访问harborcapital.com查看招股说明书，其中包含投资目标、风险、费用、支出及其他重要信息。

Visit harborcapital.com for a prospectus containing investment objectives, risks, fees, expenses, and other important information.

投资前请仔细阅读并考虑这些信息。

Read and consider it carefully before investing.

风险包括本金损失及与人工智能相关的风险。

Risks include principal loss and artificial intelligence related risks.

Harbor ETF由Foresight Fund Services, LLC分销。

Harbor ETFs are distributed by Foresight Fund Services, LLC.

Harbor与AI Daily Brief无关，这些基金与任何AI实验室无关联，也未经其赞助或认可。

Harbor is not affiliated with AI Daily Brief, and the funds are not affiliated with, sponsored by, or endorsed by any AI lab.

这是一则付费广告，并非个性化投资建议。

This is a paid advertisement and not personalized investment advice.

投资有风险，包括可能损失本金。

Investing involves risk, including possible loss of principal.

本期AI每日简报由Hyperagent赞助，你可以在那里运行你的团队可以共同管理的智能体集群。

This episode of the AI Daily Brief is brought to you by Hyperagent, where you run fleets of agents your team can manage together.

新用户可获得1000美元的推理额度。

New users get $1,000 in inference.

忘掉那些需要你在笔记本电脑上等待提示的本地智能体和聊天工作流吧。

Forget local agents and chat workflows waiting on your laptop to be prompted.

Hyperagent在云端部署始终在线的智能体，在你团队已经使用的工具中完成实际工作。

Hyperagent deploys always on agents in the cloud, doing real work across the tools your team already uses.

营销智能体将竞争对手的动态转化为落地页。

Marketing's agent turns competitor moves into landing pages.

销售智能体丰富潜在客户信息、起草邮件并更新CRM。

Sales's agent enriches leads, drafts emails, and updates the CRM.

运营智能体处理文书工作并跟踪预算。

Ops agent chases the paperwork and tracks the budget.

每个代理都能访问共享上下文，并遵循你关于范围和审批的规则。

Every agent has access to shared context and follows your rules about scope and approvals.

是时候让代理像队友一样了。

It's time you add agents that feel like teammates.

在Hyperagent雇佣你的代理，它由Airtable团队打造。

Hire yours at Hyperagent, built by the team at Airtable.

在hyperagent.com/aideallybrief领取你的1000美元推理额度。

Claim your $1,000 in inference at hyperagent.com/aideallybrief.

欢迎回到AI每日简报。

Welcome back to the AI Daily Brief.

今天，我们有点操作员风格。

Today, we are getting a little bit operator y.

有一件非常有趣的事情，我相信你们很多人都感受到了，那就是即使你自认为是AI的重度用户，或者至少是关注AI如何改变人们互动方式的人，AI的变化如此之快，以至于你很容易在人们实际使用这些工具的方式上落后一点。

One of the things that's really interesting, and I'm sure that a lot of you have felt, is that even if you consider yourself a power user of AI, or at least someone who pays attention to how AI changes the ways that people interact with AI change so much that it's not hard at all to fall a little bit behind in how people are actually using these tools.

我们习惯了现有的做事方式，并且有时我们确实擅长用那种新方式工作，所以推翻这种习惯，尝试新的AI工作方式，并不是我们总是优先考虑的事情。

We get settled and comfortable into the way that we've been doing things, and honestly, sometimes we get really good at working in that new way, and so to upturn that apple cart and try new ways of working with AI is something that we don't always prioritize.

考虑到夏天快结束了，马上要开学、复工什么的，我想分享一些最近看到的关于新技巧、新方法和新功能的讨论，这些可能对你有用。

Given that we are coming towards the end of the summer and the beginning of back to school, back to work, etc, I wanted to share a bunch of the chatter that I've seen recently about new techniques, and tricks, and features that people are using and doing that might be useful for you.

当然，其中有些东西你可能已经在用了，但也许有些东西，在你下次尝试新方法的时候，值得一试。

Now, probably it is the case that some number of these are things that you are already doing, but maybe there's something that, on your next experimental day, might be the thing to try.

在我们进入这九个技巧、窍门、方法之前，我想先提供一个贯穿整个节目的元技巧。

Now, before we get into these nine techniques, tips, tricks, etcetera, I wanna provide one meta tip that really runs across this entire show.

在这一集里，我提供的并不是我个人对某些特定技巧的经验，而是汇总了其他人分享的他们是如何学习的。

In this particular episode, what I'm providing you is not my experience with specific techniques necessarily, but instead, an aggregation of what other people are sharing about how they're learning.

AI之所以酷，就是因为人们都在公开学习和实验。

One of the things that makes AI so cool is that people are learning and experimenting in public.

说实话，虽然这些平台有时候挺乱的，但如果你不在LinkedIn或者尤其是X上关注AI的讨论，嗯，我想你在这里也算是有福了，因为这里有很多可以从别人和他们的实验中学习的东西。

And honestly, for as cesspool y as they can be, if you're not on LinkedIn or especially X and watching the AI conversation there, well, I guess you're in good hands because you're here, there is a lot to learn from other people and the experiments that they are running.

现在，我想讨论的第一个技巧是语音模式。

Now, technique number one that I want to discuss is Voice Mode.

一方面，语音模式并不是什么新鲜事。

On the one hand, Voice Mode is nothing new.

如果你参加过任何AIDB或超级智能训练项目，你肯定听过或读过我反复强调要在电脑上设置像Whisper这样的工具，以便更有效地使用你的声音。

If you have ever done any of the AIDB or Super Intelligent Training programs, you will have heard or read me haranguing you to set up something like Whisper on your computer so you can use your voice more effectively.

但最近，我们有了Codex的新实时语音模式。

But recently, we have gotten Codex's new live voice mode.

对很多人来说，这完全改变了游戏规则。

And for a lot of people, it has been a complete game changer.

七月底，Every公司的Dan Shipper在Slack上分享了他们对这个功能的讨论，并补充说：“Every公司几乎每个人都在为语音模式和ChatGPT for Work的出色表现而兴奋不已。”

Back at the end of July, Dan Shipper from Every shared their discussion in Slack about the feature and added, Almost every single person at Every is freaking out about how good voice mode and chat GPT for work is.

好久没看到大家这么高涨的情绪了。

Have not seen vibes this high in a while.

如果你还没试过，真的应该试试。

If you haven't tried it yet, you should.

Ally Kay Miller，她会在本期节目中频繁出现，如果你还没关注她，她是个值得关注的人，她一直在持续强调这一点。

Ally Kay Miller, who is gonna feature prominently across this show and who is a great follow if you're not yet, has been beating this drum consistently.

差不多在Every发布那篇文章的同时，她单独说：“现在快凌晨两点了，我之所以能完成所有紧急工作，全靠Codex语音模式。”

Right around the same time of that every post, she separately said, It's nearly 2AM and the only reason I finished all of my urgent work is Codex Voice Mode.

天哪，怎么大家都不为这个疯狂呢？

Good God, how is everyone not freaking out about this?

我觉得我的工作方式和一个月前完全不一样了。

I feel like the way I'm working looks completely different than a month ago.

所以我对它说的基本例子是：嘿，看看这一段。

So basic examples of what I say to it: Hey, take a look at this paragraph.

你觉得怎么样？

What do you think?

我还有什么待办事项？

What else is on my list?

你去找那个文档的时候，我来编辑这个。

I'm going to edit this while you find that doc.

下载我最新的Instagram Reel，给它做个好看的缩略图。

Download my latest Instagram Reel, make a good thumbnail for it.

我去接杯水。

I'm gonna go fill up my water.

需要我就喊一声。

Holler if you need me.

刚把15封客户邮件发出去了。

Just sent the 15 client emails.

你对照一下清单，我这边开始写脚本。

Check against the list while I start on the script.

不过阿里澄清说：这更多不是关于具体用途，而是关于环境交互。

Ali clarifies though: It's less about use case and more about ambient interaction.

跟环境助手说话和点击说话听起来差别不大，但实际操作起来差别可大了。

It probably sounds like a negligible difference to speak to an ambient assistant versus click to speak, but it is a world of distance in practice.

最近在一条推文里，阿里谈到她认为AI领域哪些方面还没得到足够关注，她说：有人会说Codex Live语音模式就像一个环境型的总管。

More recently in a tweet where Ally was talking about what she thinks isn't getting enough attention in AI, she said: Some will say Codex Live Voice Mode is an ambient chief of staff.

我觉得这么说低估了它。

I think that undersells it.

它是一个环境型的工作团队，一个由语音控制的环境操作系统。

It's an ambient workforce, an ambient voice controlled operating system.

我出去散步，跟AI聊天，同时处理多个电脑任务，安排一天的工作，还能改进系统架构，全都是用自然语言和闲聊完成的。

I go on walks, talk to AI, fire off multiple computer tasks, triage my day, and improve my system architecture all via natural language and yapping.

在另一篇帖子里，她还讨论了怎么在移动中或者周末作为后台进程使用这个，这样即使她在外面享受生活、散步、徒步等等，事情也能继续推进。

And in yet another post she discussed how she uses this on the go, or as a background process during the weekend, to keep things moving even as she's out enjoying her life, taking walks, hiking, etcetera.

现在，关于Ally K的最后一个补充。

Now one final entry to the Ally K.

Miller Codex Canon，她实际上在X上写并发布了一份完整的设置指南，我会把它放在节目笔记里，这样你就可以自己去试试了。

Miller Codex Canon, she actually wrote and published a full setup guide on X, which I will include in the show notes, so you can go try it out for yourself.

我早就被语音功能吸引了，我想说的是，这种事情光靠描述你是体会不到的。

Now I've been voice pilled for a while, and what I will say is that this is the type of thing that you're not really going to get from just the descriptions.

值得花一段时间用新的方式去互动，即使一开始感觉奇怪，看看它是否以及如何改变你的工作方式，以及你是否喜欢这种变化。

It's worth committing to some period of time where you're interacting in a new way even if it feels weird at first to see if and how it changes how you work, and whether you like that shift.

下一个技巧是教AI你的工作流程。

Next technique is teaching AI your workflows.

这个我们上周的节目里讨论过，但越来越因为计算机使用方面的进步，让AI做你工作中更复杂的部分变得比以往更容易，因为你可以直接让它看你目前是怎么做事的。

This is something we discussed on an episode last week, but increasingly because of advances in computer use, it's getting easier than ever to get AI to do more advanced parts of your work because you can simply let it watch how you currently do things.

有两个大例子说明这个功能已经上线了：第一个是ChatGPT的“计算机历史”功能。

Two big examples of where this has become available: The first is ChatGPT's Computer History feature.

计算机历史会记录你做的具体事情和具体工作方式的时间线，这样你就可以把它变成持续且可重复的流程。

Computer History keeps a timeline and a review of the specific things that you do, and the specific ways that you work, so that you can turn that into ongoing and repeatable processes.

这也是新的GrokBot最令人兴奋的功能之一，几分钟后我们会看到，人们还在探索如何充分利用它。

This was also one of the most exciting features from the new GrokBot, which as we will see in a few minutes, people are still really just exploring how to get the most out of.

不过，GrokBot最明显有用的一个功能是，你可以按一个小按钮，让它专门观察你正在做的那些特定活动，从而教它一个任务。

One of the most obviously useful parts of GrokBot, however, is the fact that you can press a little button to teach it a task by having it specifically watching that particular set of activities that you're doing as you're doing them.

计算机历史是一种比较被动的教学方式，而GrokBot则更主动，你可以明确告诉它什么时候看、看多久。

Computer history then is sort of an ambient approach to teaching a task, while GrokBot is a much more deliberative approach where you specifically tell it when to watch and how long to watch for.

但在这两种情况下，如果以前有些复杂的事情，你觉得AI做不了，因为太难解释怎么做，那么简单来说，这种情况可能已经大大改变了。

In both cases though, if there are complex things that previously you would've assumed that AI couldn't do because it was too hard to explain how to do it, the TLDR is that that might have changed significantly.

第三点：创建一个技能，让AI写作更好。

Number three: Create a skill to make your AI writing better.

关于AI写作，我在这里不打算讨论写作作为思考的价值，以及用写作来理清自己想法的重要性。

Now, when it comes to AI writing, I am not wading into the debate here about the value of writing as thinking, and the importance of using writing as a way to figure out your own thoughts about something.

我说的是我们写的大量文字，这些我们都很放心地交给AI来处理。

I'm talking about the sheer voluminous writing that we do, that we are all very comfortable outsourcing to AI.

比如邮件、备忘录、摘要，或者更重要的领域，比如网站文案。

Emails, memos, summaries, or more important areas like website copy.

尽管在很多情况下，AI的写作水平已经提高了，但还是有很多套路让AI写的东西一眼就能认出来。

Even though AI's writing has, in many cases, gotten better, there are still so many tropes that make AI's writing instantly recognizable.

用一两个词组成的短句，用句号隔开，来制造戏剧效果。

Tiny compressed sentences of just a word or two separated by periods to sound dramatic.

不是这个，而是那个。

It's not this, it's that.

每当有诚实的保留意见或担忧的时候。

Anytime there s a honest caveat or concern.

你懂的。

You know the drill.

基本上，如果你曾经对大型语言模型说过“把那些AI腔调都去掉”，我觉得现在有更好的办法来做这件事。

Basically, if ever you found yourself saying to an LLM, Rewrite this without all the AI isms, I think there s a slightly better way to do that.

鲁本·哈西德最近在X上发帖，讲了一些用AI的明显破绽。

Ruben Hasid recently posted on X about some of the dead giveaways of using AI.

其中很多就是我刚才提到的那些，他还补充了比如AI自我吹捧的例子。

A bunch of them are the ones that I just mentioned and he also adds, for example, clapping for itself.

这一点很重要。

And that matters.

这正是大家容易忽略的地方，而恰恰是关键所在。

That's the part everyone misses, which is exactly the point.

你完全可以把这篇帖子打印成PDF，然后直接丢给Claude，让它把它变成一个技能，这样以后就不会再犯这些毛病了。

You can genuinely print this post as a PDF and just drop it into Claude and ask it to make it a skill so that that doesn't happen anymore.

其他人也在尝试不同的做法，比如给AI提供特定的风格指南（比如ASD Ste 100写作标准，用于编写简洁手册），然后把这些指南变成技能。

Other people are experimenting with different versions of this, like giving the AI specific style guides (like the ASD Ste 100 writing standard for plain manuals) and turning those into a skill.

把你不希望AI做的事情集中记录下来，并确保它每次写作时都牢记这些要求。

Capture the things you don't want AI to do in a consolidated place, and make sure it has that in mind as it's writing every time.

第四个技巧其实是一个新功能，就是Claude中的斜杠设计命令。

Technique number four is actually a new feature, which is the slash design command in Claude.

当你使用Claude代码时，现在可以输入斜杠设计，它会调出一个画板工作流程，给你一种不同的界面来处理设计问题。

When you're using Claude code, you can now type slash design and it's going to bring up this artboard workflow that gives you a different type of interface for interacting with a design question.

你可以给它留具体的备注，高亮你想改的特定区域，预览不同的风格，而且有趣的是，根据我的经验，这在宏观和微观层面都提升了设计体验。

You can leave it specific notes, highlight particular areas you want to change, preview different styles, and what's interesting about it is that in my experience, this is an improved design experience on both the macro and the micro level.

在宏观层面，如果你不知道想要东西怎么运作，让它设计一堆模板，你可以同时查看，并给出比较高层级的反馈来迭代，这真的是一个很有价值的方法。

On the macro level, if you don't know how you want a thing to work, having it design a bunch of templates that you can look at all at once, and give pretty high level feedback on to iterate with, is a really valuable approach.

但当你深入到微观层面，能够编辑设计中非常具体的部分，而不是非得给一个大提示词来整体改动，这简直太有价值了。

But then also when you get down to the micro, being able to edit very specific parts of a design rather than having to just give a big prompt that changes the whole thing all over again is incredibly valuable.

现在Claude和ChatGPT都在不断添加这样的新命令，所以总是值得关注一下。

Now Claude and ChatGPT are constantly adding new commands like this, and so it's always worth keeping an eye on that.

但斜杠设计是我已经发现非常实用的一个，如果你也是Claude用户，我想你也会觉得有用。

But slash design is one that I've found really useful already, and I think you might too, if you are a Claude user.

说到技能，Agent技能简单来说就是一门新学科。

Now, speaking of skills Agent skills are, simply put, a new discipline.

当我们给代理分配越来越复杂的任务时，知道在哪里插入技能、给它哪些技能、什么时候退后让它自己原生工作，这些都变成了非常重要的人类能力或代理管理能力。

As we give our agents more and more complex tasks knowing where to insert skills, which skills to give it, where to back off and just let it work natively all of those become really important human capabilities or agent management capabilities.

最好的技能资源库之一，以及如何使用它们的指南，来自Matt Pocock的网站aihero.dev，具体是aihero.devskills。

One of the best repositories of skills that you can find, as well as resources for how to use them, comes from Matt Pocock over at his site aihero.dev specifically aihero.devskills.

他根据实际使用场景对技能进行了分类。比如，在主流程中有一个技能叫Grill with Docs。

He groups the skills there based on when you would actually use them So as an example of a skill in the main flow, he's got a skill called Grill with Docs.

这个技能会就你的计划或设计对你进行访谈，直到你和代理达成一致的理解，同时把术语和关键决策写进你的代码库。

It's a skill that interviews you about a plan or a design until you and the agent, quote, share one understanding of it, and writes the vocabulary and the hard decisions into your repo while it does.

重要的是，它不仅仅是一次访谈，而是一次有后续产出的访谈。

Importantly, it is not just an interview, but an interview that comes with a leave behind.

在所有这些案例中，Matt不仅解释了技能的功能，还提供了简单、可复制的安装方法，让你直接安装。

And in each of these cases, Matt is not just explaining what the skill does he is giving you a simple, copyable way to install the skill directly.

技能卫生和技能实践，我认为不应该看作是与非的二元对立，而是一种持续提升的修炼。

Skill hygiene skill practice is one of those things that I think we should not view as a binary between whether we can or whether we can't, but instead just an ongoing discipline that we are always trying to get better at.

在这个领域，最好的做法就是站在那些已经花了很多时间研究什么有效什么无效的人的肩膀上。

And this is definitely an area where the best thing that you can do is stand on the shoulders of the people who have already spent a ton of time figuring out what is and isn't working.

下一个你可能还没试过的AI技术，我今年秋天会花更多时间研究，有人称之为多人AI，或者你可以理解为团队代理。

The next AI technique that you might not have tried yet is one that I'm going to be spending a lot more time on this fall, which some people are referring to as multiplayer AI, or which you could think about as team agents.

这个想法其实很简单。

And the idea of this is pretty simple.

今年，随着智能体逐渐成熟，我们大多是在单机模式下与它们互动的。

As agents have become real this year, we've mostly interacted with them in single player mode.

我的意思是，当OpenAI推出时，你拿到了一台Mac mini。

What I mean by that is that when OpenAI came out, you got a Mac mini.

你打造了一个个人幕僚长。

You built a personal Chief of Staff.

你构建了研究智能体、开发智能体，或者你构建的任何智能体。

You built Research Agents, or Developer Agents, or whatever agents you built.

你突然之间就成了一个智能体团队的经理，它们为你工作，但它们是为你服务的。

You, all of a sudden, were the manager of perhaps a team of agents working for you, but they were working for you.

我觉得很多人发现，在公司环境中，这样做会错失很多机会。

I think what a lot of folks are finding is that in the context of their companies, this leaves a big opportunity on the table.

工作不仅仅是每个人接到任务后各自行动，然后再聚在一起汇报。

Work is not just a matter of everyone getting briefed and then going off and doing things on their own and then coming back together.

工作往往需要高度协作，涉及交接、共享上下文和共享空间。

Work is often highly collaborative with handoffs and shared context and shared spaces where that work happens.

这还处于早期阶段，但我认为未来的一大趋势将是那些专注于团队协作交汇点的智能体工具、交互模式和平台，而不是仅仅让个人独自工作。

It's nascent, but one of the things that I think is going to be a big trend moving forward is agentic tools and interaction patterns and platforms that focus on agents that live in the intersection where teams come together rather than just where individuals work on their own.

目前最好的例子可能就是Claude Tag。

Maybe the best example of this so far is Claude Tag.

其实在六月底Claude Tag发布之前，Claude和Slack就已经有集成，你可以通过标记来召唤你的Claude实例。

Now even before Claude Tag came out at the end of June, there had been an integration between Claude and Slack where you could summon your Claude instances by tagging it in.

Claude Tag的不同之处在于，Claude会作为团队成员加入，并且能访问你召唤它的特定频道的全部上下文。

The difference with Claude Tag is that Claude joins as a team member with access to the entire context of a particular channel that you're summoning it in.

那个频道里的Claude实例可以拥有特定的权限、特定的工具访问权限和特定的上下文访问权限。

The Claude instance that lives in that channel can have specific permissions, specific tool access, specific context access.

这可以与其他频道中的Claude不同。

And that can be different than the Claude in other channels.

但存在于团队频道中的那个Claude，并不只是某个团队成员电脑上的资源，它是整个团队共享的资源。

But that Claude that exists inside that team channel doesn't just live on one team member's computers it is a shared resource across the team.

当然，现在不是每个人都能用上 Claude Tag，但我认为这种让 AI 智能体在团队间共享的使用模式，将是今年秋天 AI 领域最重要、最显著的趋势之一。

Obviously, not everyone has access to Claude Tag right now, but I think that this pattern of use of agents that are shared across teams is going to be one of the biggest and most important trends for AI this fall.

关于大家如何思考这一点，另一个例子来自 10x，这是一家位于纽约的 AI 构建与实施合作伙伴。

Another example of how people are thinking of this comes from 10x, which is an AI build and implementation partner out in New York City.

他们最近发布了一篇关于“公民 SDLC”（他们这么称呼）的文章，这是一个六个阶段的生命周期，旨在将非技术人员利用 AI 构建的个人原型，转化为全公司都可以使用的生产级应用。

They recently released a post about the Citizen SDLC, as they call it, which is a six stage lifecycle that takes what non technical employees build with AI from a personal prototype to a production that the whole company can use.

换句话说，它试图把个人层面的企业级氛围编程，变成对整个公司都有用的工具。

In other words, it's trying to take enterprise vibe coding that happens on an individual level and make it useful across the whole company.

这个你可以在他们的博客上找到，网址是 10x10ex.co，就在页面顶部很显眼的位置。

That one you can find on their blog which is 10x10ex.co and it's promoted right near the top.

第七个技巧或功能，你可能还没试过，它有点像是个退路，又是个万能兜底方案，那就是 GrokBot。

Technique or feature number seven that you might not have tried yet is a bit of both a cop out and a catch all, and that is GrokBot.

目前，GrokBot 还是单人模式工具，也就是说你要为自己不同的任务分别启动自己的 GrokBot 代理。不过我觉得它不会一直停留在单人模式太久。

Now, right now, GrokBot is still a single player mode tool, in that you are spinning up your own GrokBot agents for different tasks that you have, But I don't think it's going to stay single player for long.

现在，你启动的 GrokBots 之间已经可以互相交互了，这就产生了一些非常有趣的模式，比如只跟一个总管交互，由他来管理所有的其他 GrokBot。

Already, the GrokBots that you spin up can interact with one another, which creates some really interesting patterns like being able to interact only with a chief of staff, which manages all the other GrokBots.

我觉得下一步很明显，就是让团队成员之间的GrokBots能够进行共享交互。

And I think that the obvious next step is shared interactions between GrokBots across different members of a team.

现在已经过去大约一周了，大家都在大量尝试如何充分利用它。

Now, it's been about a week, and people are doing a ton of experimenting with how to get the most out of it.

大家对它拥有自己的虚拟电脑这一点反应非常积极，因为这样可以解决之前代理经常遇到的一些访问问题。

People are responding very positively to the fact that it has its own virtual computer that it can use to solve certain types of access issues that plague previous agents.

如果你去X上逛逛，会发现人们分享的用例多得数不清。

And if you go poke around on X, there are just a boatload of use cases that people are sharing.

比如应用评论、根据笔记更新销售演示文稿、Salesforce报告、每日简报等等。

Application reviews, sales deck updates from notes, Salesforce reports, daily briefings.

我注意到一个共同点，就是无论你在哪里，或者可能在哪里，以规律且可预测的方式处理大量信息，GrokBot这类代理都值得一试。

One common thread that I'm seeing is that anywhere you interact or could be interacting with a lot of information in a regular and predictable way, a GrokBot style agent is something that might be interesting to check out.

Lenny's Podcast的Lenny Rechtschisky最近提出了一个想法，就是利用包含他500多期播客文字记录的MCP，把GrokBot变成你自己的产品策略、增长和职业顾问。

Lenny Rechtschisky from Lenny's podcast recently gave the idea of using the MCP that has all the transcripts from more than 500 of his podcasts to turn GrokBot into your own product strategy growth and career adviser.

顺便说一句，对于那些出于各种原因不想用Grok的人，Noose Research最近为Hermes Desktop推出了Bot模式，这和GrokBot非常相似，但通过更开放、更可控、更可定制的Hermes系统来实现。

And by the way, for those of you who are not interested in working with Grok for whatever set of reasons, let's call them, Noose Research recently introduced Bot Mode for Hermes Desktop, which is very similar to GrokBot, but through the open much more controllable, much more customizable Hermes system.

你可能还没试过的第八个技巧是本地AI。

Technique number eight that you might not have tried is Local AI.

现在深入讲本地AI的实际使用要求，已经超出节目范围了。

It's Now too far beyond the scope of the show to go really deep into what using local AI actually requires.

不过幸运的是，六月份我做了一整集节目，专门讲为什么本地AI重要，以及怎么和Newfar Gaspar一起使用，你可以去看看。

But luckily for you, back in June, I did an entire episode about why local AI matters and how to use it with Newfar Gaspar that you can go check out.

值得再考虑本地AI的原因是，现在能在本地硬件上运行的模型有了很大的进步。

The reason that it's worth thinking about local AI again is that there are some pretty serious advances in models that are capable of being run on local hardware.

具体来说，我指的是Quen 3.827B，这是一个能在普通硬件上运行的本地模型，在Artificial Analysis Intelligence Index上得了52分，这在几个月前还是顶尖水平。

Specifically, I'm referring to Quen 3.827B, which is a local model that can run on common hardware that is scoring a 52 on the Artificial Analysis Intelligence Index, which would have been state of the art just a few months ago.

换句话说，如果你一直在考虑尝试本地AI，Quen 3.827B可能是个合适的切入点，让你真正开始动手。

In other words, if you have been thinking about experimenting with local AI, Quen 3.827B might be the right context to actually dive in.

最后，第九个技巧与其说是技巧，不如说是一个启发，就是两个词提示词，你可以试试。

Lastly, technique number nine is not so much a technique but a thought starter, and these are two word prompts to try.

这又是来自Ally Miller，她最近发了一条推文，分享了十八个她特别喜欢的两个词提示词。

Once again, this comes from Ally Miller, who recently tweeted out eighteen two word prompts she's kind of obsessed with.

你得想想，其中一些可能确实来自她使用语音模式的经验，因为它们听起来很像你与团队成员互动的方式。

You You have to think that some of these actually come out of her experience using voice mode as well, as they sound a lot like how you would interact with a team member.

事实上，她的第一个两词提示是：“现在怎么办？”

In fact, her first two word prompt, Now what?

她说这个提示在项目或大任务完成后，你还有精力，想让AI给你更多建议时特别好用。这让我想起《白宫风云》里的杰德·巴特利特说“接下来呢？”

Which she says is great for when you've wrapped up a project or big push and you still have energy and want AI to give you more reminds me a lot of Jed Bartlett from The West Wing saying What's next?

她提到的其他两词提示包括“请修复”和“模拟一下”，让AI运行场景、规划边缘情况，并在规划界面中可视化可能发生的情况。

Some of the other two word prompts she points to are Please fix Simulate it to get AI to run scenarios, plan for edge cases, and visualize what might happen into a planning interface.

还有“记住这个”，当艾莉遇到错误或关键上下文错误时，她会强制AI将其记录在记忆中。

And remember this where when Ally has run across a mistake or critical context error she forces the AI to log it in its memory.

她指出，虽然AI通常会自动这样做，但并非总是如此，明确要求会有所帮助。

She points out that while AI often does this automatically, it doesn't always and being specific about it can help.

这也许是我开头所说的最好的例子，这些不一定是对工作流程的巨大改变，而只是一些简单的小点子，让你从每天使用的工具中获得更多价值。

This is maybe the best example of what I was saying at the beginning where these aren't necessarily some massive change to your workflow but just some simple little ideas to get a bit more out of the tools that you now use every day.

好了，这就是九种你可能没试过的AI技巧，至少不是全部试过。

So there you have it nine AI techniques you probably haven't tried, at least not all of them.

希望这能给你带来一些有趣的灵感，在即将到来的周末里试试看。

Hopefully this gives you some fun ideas for experimenting in the weekend to come.

好了，今天的AI每日简报就到这里。

For now, that is gonna do it for today's AI Daily Brief.

感谢你的收听或观看，一如既往，下次再见，祝一切顺利。

Appreciate you listening or watching, as always, and until next time, peace.