企业为什么应该训练自己的 AI 模型：Prime Intellect 的 Will Brown 谈持续学习

简要说明Brief Description

你的公司应该训练自己的 AI 模型——Will Brown，Prime IntellectYour Company Should Train Its Own AI Models - Will Brown， Prime Intellect

目录Table of Contents

• 简介
  Intro
• 从聊天机器人到 AI 原生组织
  From chatbots to AI-native organizations
• Prime Intellect 的构建内容
  What Prime Intellect builds
• 从未被记录下来的知识
  The knowledge that never gets written down
• 为什么智能体要重新学习一切
  Why agents relearn everything
• 哪些内容放在上下文中，哪些内容放在权重中
  What goes in context vs. in the weights
• 前沿训练背后的传话游戏
  The game of telephone behind frontier training
• 将评估集用作模型的测试用例
  Evals as test cases for your model
• 路由与决策模型
  Routing and decision models
• 将决策转化为训练数据的界面
  Interfaces that turn decisions into training data
• 知识工作领域的 30 万美元模型
  A $300K model for knowledge work
• 每晚训练运行
  Nightly training runs
• 自我改进型组织
  The self-improving organization

简介Intro

大家好，最近怎么样？我是 Will Brown。我在 Prime Intellect 负责应用研究。希望大家都能在这次 AI 工程师大会上玩得开心。这一直是我最喜欢的活动之一。看到大家都在做什么、构建什么，总是特别酷。我觉得这里也是一个能让大家畅谈未来模样、开始观察行业趋势、了解进展以及哪些行得通、哪些行不通的地方。 这也是我今天这场演讲想探讨的主题：从我们当下正在做的事情出发，接下来会发生什么？我们一直在做些什么，又观察到了哪些正在展开的研究？这些都在一定程度上指向了我们认为 AI 在组织层面可能呈现的未来模样。过去几个月乃至几年里，智能体、接口、机器人等领域已经取得了许多令人振奋的进展。Hey, how's it going? I'm Will Brown. I uh lead applied research at Prime Intellect and uh hope you are all having a a great AI engineer conference. This is always one of my favorites. Uh, it's always just so cool to see what everyone's working on and building and I feel like it is a place where people get to talk about what the future looks like and like start seeing the trends in the industry and seeing the progress and what works and what doesn't. Um, and that's kind of the theme I want to think about for this talk today is like what comes next from what we're doing right now and what are some of the things that we've been working on and also just been seeing and research that's unfolding that kind of points at what we think the future of AI might look like um at the organization level. uh because we've seen a lot of very cool progress in uh agents and interfaces and bots and things like that over the past uh several months, years.

呃，不过我……总觉得总有更多事情接踵而来。事情发展得太快了，我觉得现在是个非常令人兴奋的时刻，可以尽情想象、推测，并规划接下来会发生什么。Uh but I there's always like there's always more coming. Things are just moving so fast and I think it's a very exciting time to just imagine and speculate and plan for uh what comes next.

从聊天机器人到 AI 原生组织From chatbots to AI-native organizations

嗯，所以我不知道你们当中有没有人还记得早期 ChatGPT 的时候，OpenAI 曾经大致阐述过他们对 AI 进步过程中通往 AGI 的不同阶段的划分。嗯，我觉得我们的进展比预想的快。呃，我记得 18 个月前，我在纽约参加一个工程师活动并做演讲时，我们已经有了推理模型，聊天机器人也出现一段时间了，推理模型算是新事物，但我们还没有真正拥有智能体。嗯，而现在，我们很快就从智能体阶段迈进了创新者阶段。接下来的问题似乎是：那么组织会怎样？一个组织真正成为 AI 原生组织意味着什么？这不只是指一家大量使用智能体、用 Cloud Code 构建一切的初创公司，而是指大型企业的规模。Um, and so I don't know if any of you remember back in the early chatbt days, OpenAI had kind of spelled out their framing of like what are the different stages of AI progress on the road to AGI. Um, and I think we've moved along this faster than we thought we would. uh we like I remember 18 months ago I was uh here in New York at a engineer and giving a talk where we had gotten reasoners and chat bots had been around for a while and reasoners were like the new thing but we didn't really have agents yet. Um, and now we've climbed pretty quickly through uh agents and innovators. And the question next seems to be, okay, what happens for organizations? Like what does it mean for an organization to truly like be AI native, not just as like a a startup that uses a lot of agents and builds everything with cloud code, but like at the like large enterprise scale?

嗯，未来的公司会是什么样子？它们会如何在组织的整个生命周期中深度整合智能体？而我们要在实现这一目标的道路上构建什么？um what do companies of the future look like that involve uh like deep integration of agents throughout the life cycle of the organization um and what do we need to build on the path there

Prime Intellect 的产品构建内容What Prime Intellect builds

先简单介绍一下 Prime，作为一些背景信息。我们围绕 AI 基础设施构建了很多不同的东西，用于训练、部署和持续改进模型，尤其是开源模型，以及开源工具。因此我们做的事情很多。大致来说，我们做的就是大型实验室内部会做的那些事。这些就是我们的产品。我们之所以这么做，是因为我们设想，一个似乎很快就会到来的未来是：开源模型将随时可用，人们可以用自己的工作流、自己的数据和自己的运行框架来训练和部署这些模型；组织可以让这些模型随着自身发展，逐步积累机构知识，并凭借自己的工作流、数据、人员和流程不断巩固机构优势，同时也能使用前沿实验室开发的模型。uh so a bit about prime just for some backdrop um we build a lot of different things around AI infrastructure for training deploying and continuously improving uh models and especially open source models uh and open source tooling and so we do a lot of things And like we roughly do the sorts of things that you would do inside of a big lab. And these are our products. And the reason we do this is because we are imagining a future that is coming pretty quickly it seems where open source models are readily available to train and deploy on your own workflows on your own data in your own harnesses and can be the sorts of things that organizations can have grow with them over time that allow compounding their institutional knowledge, their institutional advantage from their workflows, from their data, from their people and their processes uh in addition to uh using the models from the Frontier Labs.

所以，这次演讲会稍微谈谈我们如何看待这一切的发展和演变：比如，训练在 AI 原生企业中扮演什么角色？它如何与前沿模型共存？嗯，还有，我们认为最终哪种形态能真正为人们释放最大价值？它会是什么样子？And so this talk will be a bit about how we see that evolving and unfolding where like what is the role of training in AI native enterprise? How does this coexist with the frontier models? Uh and like what do we think is going to be the version of this that really unlocks the most value for people and what does it look like?

从未被记录下来的知识The knowledge that never gets written down

嗯，所以组织拥有大量知识，而且一个组织存在的时间越长、越成熟，就越有许多隐性知识从未被写下来。嗯，有些东西确实会被写下来，比如代码库、电子邮件和流程。其中有些内容非常明确，就像规则一样：你必须做这件事，这件事就是这么运作的。但很多东西都存在于人们的脑海里，藏在邮件、会议纪要的字里行间，也体现在谁和谁交谈这些关系之中。比如，很多公司纸面上有一份组织架构图，但实际上还有一份真实的组织架构图，体现了到底是谁在做决策、变革如何在公司内部推行，以及哪些类型的指令更有可能真正生效。Um, and so organizations have lots of knowledge and like the longer an organization's been around and the kind of more established it is, the more implicit knowledge there is that kind of doesn't ever get written down. Um, there are things that do get written down. There's code bases, there's emails, there's processes. Some of these are very explicit. They're like rules of like you must do this, this thing works like that. But a lot of things kind of live in people's heads and they live in between the lines of emails, of the meeting notes, of the kind of who talks to who. Like a lot of companies will have like a a on paper org chart and then a real org chart of like who actually makes decisions and like how does change get adopted throughout the company, what sorts of mandates are likely to take effect.

嗯，人们在公司待久了，多少会积累起这方面的经验，比如“哦，事情大致就是这么运作的”，以及摩擦点在哪里。我认为在很多情况下——而且我觉得这确实是 AI 在组织层面的一大机遇——很多人其实没有能力去改变组织中那些出了问题的地方。嗯，因为没人把这些问题明确说出来。没人真正站在全局的角度审视组织中发生的一切，然后指出：“嘿，那边这件事效率不高，可以做得更好。这个问题在好几个不同的团队中反复出现，但没人发现，其实那个团队已经找到了解决办法。”这类事情正是智能体特别擅长处理的。Uh and people have kind of built up this knowledge from being at companies for a long time of like oh this is kind of how things work. This is where the friction points are. And I think in many cases uh and I think this is really one of the big opportunities for AI at the organizational level is is that many individual people are kind of not in a position where they can change the things that are broken in an organization. Um because no one is actually spelling it out. No one is is like taking a bird's eye view of looking at everything that happens in an organization and saying hey this over here is inefficient. This could be better. this thing keeps happening across all these different teams, but nobody's figured out that the solution has actually been discovered by that team. And these are the sorts of things that like agents are great for.

比如，智能体非常擅长梳理大量非结构化文本数据，找出这类模式，并将其转化为有用的信息——比如指出，某个工作流程存在问题，因为它浪费时间、效率低下，而且本可以采用其他方式。嗯，不过我们不想只做一次。我们希望这逐渐成为各类组织广泛采用 AI 的方式：智能体不仅能够获得所需的上下文，也能够不断改进自身以及组织。Like agents are very capable at combing through large amounts of textual data that's unstructured and finding these kinds of patterns and turning them into something useful uh and and surfacing them as like, okay, this workflow has a problem because it is wasting time and it's inefficient and it could be different instead. Um, and we don't want to just do this once though. We want this to kind of become the way that organizations adopt AI broadly where uh, agents are able to get the context they need, but also they're able to improve both the agents themselves as well as the organizations.

为什么智能体要重新学习一切Why agents relearn everything

我们希望智能体能更像我们的同事，但人类同事会在工作中学习。智能体目前在工作中的学习方式还比较原始。它们通过上下文学习来学习。呃，哎呀，抱歉。我往回倒几秒，这样我们就能在录音里编辑这段内容。呃，智能体通过类似上下文学习的方式，以比较原始的方法学习。这通常表现为有人为它们编写技能文件，或者它们自己在代码库里摸索，但它们无法获得人类员工真正拥有的那种组织层面的隐性知识。于是它们会反复学习很多东西，不得不重新发现已有的信息，还会消耗大量输入 token。我觉得如今人们开始意识到，现金成本是许多智能体成本中的瓶颈。呃，即使你确实获得了很高的缓存命中率，缓存成本也下降了，每次重新执行工作流时，你仍然得重新处理大量输入。And we want agents to be more like our co-workers, but um, human co-workers learn on the job. Agents currently learn on the job in relatively primitive ways. Um, and they do this via incontext learning. Um, and oops, sorry. I'm going to go back a few seconds so we can edit this on the recording. Um, agents learn in relatively primitive ways through like in context learning. Um, and this typically looks like them kind of having a skill file written by somebody or like looking around a codebase, but they don't get the institutional level latent knowledge that human employees really do. Um, and so they relearn a lot. They have to rediscover things. They spend a lot of input tokens. And I think nowadays people are realizing that like cash to input is like the bottleneck in many agent costs. Um, and even if you do get great cash rates and cash costs go down, you still have to like reprocess a lot of input to redo a workflow every single time.

嗯，所以要绕过这个问题，你会希望能把更多东西内置到模型中，尤其是那些难以写成规则的东西。我喜欢把它看作一条从规则到模式的连续谱，也喜欢从概念上把它看作代码与数据的区别。很多东西都以代码的形式存在，技能大致如此，规则也大致如此。但偏好、摩擦、启发式方法和趋势之类的东西都属于数据。机构拥有大量赖以运作的数据，组织中的员工也会不知不觉地从中学习，而模型却始终没有真正的机会学习这些东西。我们认为，这正是阻碍它们成为真正的同事的因素。Um, and so to get around this, you kind of want to be able to bake in more into the model, especially for things that are harder to write down as rules. So I I like thinking about the spectrum from like rules to patterns as well as like conceptually like code versus data. And so lots of things live as like code and like skills are kind of like this, rules are kind of like this. But things like preferences and friction and heruristics and trends. These are all data and institutions have so much data that they are like running on and the employees of the organization implicitly learn that models never really get a chance to learn. And this is the sort of thing that we see as blocking them from becoming true co-workers.

上下文与权重中分别放什么What goes in context vs. in the weights

嗯，所以就有个问题，比如说，好吧，哪些东西放进上下文？哪些东西放进权重？其中一部分是，你得让它们逐步获得进入权重的资格。也就是说，东西不会一下子就进入权重。但如果你看看每一代新模型，就会发现模型变得更好，并不是因为提示词更好了，而是因为他们对模型进行了更多训练。训练是有用的，训练有效。我们之所以能看到这样的进步，就是因为训练。大致来说，模型是在大量数据上训练的，目的是去近似那些实验室认为会成为组织中高价值、可重复工作流的内容。嗯，我觉得这很好。我认为目前确实有一套行之有效的流程，这也是模型变得更好的方式；但如果你把它具体说出来，就会发现效率相对较低。Um, and so there is a question of like, okay, what goes in context? What goes in the weights? And part of it is you kind of need to earn it. Like things don't just go in the weights right away. But if you if you see kind of every new generation of models, the models get better not because the prompt is better, but because they train them more. Like training is useful. Training works. Training is why we see the progress we do. And the model is roughly like trained on lots of data that is aiming to approximate things that makes that the labs expect will be like high value repeatable workflows uh at organizations. Um and I like this like I think there's a a process that currently it works. It's how the models get better but if you like spell it out it's relatively inefficient.

前沿训练背后的传话游戏The game of telephone behind frontier training

比如说，一个模型要学会如何非常擅长使用某些工具组合，比如 Salesforce 工具。假设有这么一个人，他知道这些工具是怎么用的，现在正在找工作；也许他以前在一家使用这些工具的公司工作过，现在则在浏览一些专家网络网站，想利用空闲时间赚点钱，并把自己的知识分享给某家专家网络公司的员工。随后，这家网络公司的员工会把这些来自人类的数据转交给另一个人，而这个人的工作是创建 RL 环境。之后，这个 RL 环境可能会被卖给某个不具备这方面专业知识的人，再由他转卖给某个实验室的研究人员；而这位研究人员对这个领域其实也不算专家，之后会对它进行改进，将其放入训练流程，供下一轮前沿模型训练使用。这样一来，模型就通过这场类似传话游戏的过程，获得了最初那个人的一些知识。So like the way that a model would learn how to get really good at like using some combination of like Salesforce tools for example let's say is someone who knows how those tools get used has to be looking for work uh and maybe they previously worked at a place that were using these tools and now they are uh browsing kind of expert network sites to make some money in their free time and they are sharing their knowledge to someone who works at an expert network company. this person at this network company will then turn this uh take this data from the human and uh pass it to someone else whose job is to create RL environments. This RL environment might get sold then to by someone who doesn't have this expert knowledge to a researcher at a lab who also really isn't the expert in the domain who then will be refining it to put it into a training pipeline uh to go into the next frontier model run to make a model that has kind of through this like game of telephone gotten some knowledge of that human originally.

但这个流程里有这么多步骤，而且它相对来说是个保密流程。比如，人们会在其中两个阶段与它对话；但那个了解这件事的人，并没有监督训练过程，也没有真正直接参与模型的训练方式——不像人们在日常使用自己的编程代理时，可以亲自这样做。嗯，所以我们看到的机会，也可以说是我们希望努力的方向，就是弥合这一差距，让人们能够像使用编程代理时那样，每次都给它们相同的提示，告诉它们不要重复犯同样的错误。嗯，这就是训练模型的方式。你可以告诉模型一些事情，它们会持久地学会这些，而不只是把它们写成代理的 MD 文件里的一行内容，导致内容不断累积，之后还得不停地重构。But there's so many steps in this pipeline and it's a relatively secret pipeline. Like people people talk at across two stages of it, but like the human who knows this thing is not supervising the training run is not really directly inputting like how the model gets trained in the way that a human could if they were doing it for their coding agent that they're working with day-to-day. Um, and so what we see as an opportunity and kind of also where we would hope to go is like to close this gap and to allow the person who the same way that when we work with our coding agents, we're prompting them like the same things every time, telling them to like not repeat the same mistakes. Um, that this is how you could train models. You can tell the models things uh and they will learn these things durably, not just as like a line in your agents MD which kind of accumulates and then you have to refactor it all the time.

你可以做到其中一些，但很多时候，你真正想表达的是一种情境偏好。你是在说，在这种情境下，你做的这件事并不完全符合我的期望，我更希望你这样做。我们希望系统能够把这些反馈不断积累，转化为持久的学习。嗯，训练是实现这一点非常有效的方式，因为你提供的数据形式与实际训练流程所需的形式相当接近。因此，学习有好几种不同的类型：人们会做的事；你可以在编排层通过技能和记忆实现的事；以及存在于整个组织、文件系统和数据库中的知识，你可以借助工具和代码检索这些知识。You can do some of that, but a lot of times what you really want is you're giving kind of contextual preference. You're saying in this setting, this thing that you did was not exactly what I wanted and I would have preferred this instead. And we'd want systems that can compound this into like durable learning. Uh and training is a very effective way of doing this because the shape of data you're giving there is quite close to what you would want uh from like an actual training pipeline. And so there's there's several different types of learning. There's things that people do. There's things that you can do at the harness layer with skills and memory. Uh there's knowledge that just lives uh throughout an organization and file systems and databases uh that you retrieve uh with with tools and with code.

然后还有模型本身，它们拥有非常广泛的世界知识。不过我相信，我们都经历过这样的挫败：使用的模型知识截止时间已经是很久以前了，所以如今你没法真正和模型聊过去六个月的新闻。它们并不真正了解这些内容，每次都得在上下文中重新学习一套世界模型，因此无法像讨论更早发生的事情那样流畅地讨论这些近况。为了从模型身上获得最大价值，我们认为，各个组织会越来越希望模型能够凭直觉真正理解组织内部正在发生什么。而这正是你希望通过训练让模型学会的东西。Uh then there's the models themselves which have this really broad world knowledge but like we all have I'm sure experienced uh frustration when using a model whose like cut off of knowledge is like a while back and like you can't really talk to the models about the news of the past 6 months nowadays like they don't really they have to go like relearn a world model in context every single time and this just does not allow them to really operate as fluently as they can discuss things that happened longer ago. And so organizations to get the most value out of models, we imagine they will want to increasingly have models that really understand what is going on in the organization at an intuitive level. And this is the sort of thing that you want to train for.

将评估集作为模型的测试用例Evals as test cases for your model

嗯，那要怎么做到这一点呢？比如说，一个组织要从抽象地提出“我们要用自己的数据训练模型”这个想法，到真正实现它，中间要走怎样的路？我认为，一个非常有用的起点是评测，基本上就是测试用例。我觉得在代码方面，我们已经在测试、生命周期以及软件开发生命周期上发展得相当成熟，通常能确保代码库随着时间推移健康成长，而智能体正在替我们完成大量这类工作。我认为，对大多数组织来说，最实用的持续学习方式，就是把模型当作某种代码库来看待：它可以有自己的生命周期，可以添加测试用例、功能和资源。而在使用智能体的过程中，最初要做的就是收集轨迹。Um, and so how do you get there? Like what is the road for an organization to go from like having this idea in the abstract of like we're going to train models on our data to actually getting there? And I think one really useful starting point is eval as essentially test cases. I think like with code we've gotten to a point of maturity around like testing and life cycles and software development life cycles for ensuring that uh code bases grow healthily over time usually and agents are doing so much of this work for us. And the version of continual learning that I I think is like most practical for most organizations is just treating a model kind of like a codebase where it is the sort of thing that you can have a life cycle around you can add test cases to, you can add features to, you can add uh assets to and this is the sort of thing that the process of using agents like initially you collect traces.

这些轨迹中包含你的提示词，也包含你对模型表现的反馈。仅仅是在使用这些模型的过程中，你就已经积累了创建评测所需的素材。只是过去制作评测一直有些麻烦，很多组织也未必愿意手动完成。但智能体很快就发展到了这样的阶段：值得庆幸的是，我们现在有了能替我们完成大量评测集整理工作的机器人，尤其是当我们用更多关于如何以稳健且有利于学习的方式制作评测集的最佳实践来训练它们时。These traces have your prompts and they have your feedback to things that models did. And this just from the process of using these models, you are accumulating the assets you need to create evals. It's just that making evals historically has been a little bit painful and a lot of organizations have not necessarily wanted to do it manually. But the agents are quite quickly getting to the to the point where thankfully we we have robots that can can do a lot of the eval curation for us, especially as we train them more on the best practices of making evals in ways that are robust and amendable to learning.

路由与决策模型Routing and decision models

嗯，所以我觉得这里另一个有用的例子，是过去几周席卷全球的决策模型热潮，Jev 也参与其中；还有与路由相关的种种情况，以及人们对成本优化的热情。因为我们看到，每个月在云服务上花费巨额资金是完全可能的，而我们也在琢磨什么时候该用更便宜的模型。嗯，我觉得人们正在意识到，这类东西应该放在 harness 里。不过，它也算是一种与决策模型相当相似的属性。我把这两者放在一起说，是因为有些事情的标签非常明确，答案也有对错之分，而且人类或另一个智能体可以提供反馈。你可以让大模型和小模型执行同一项任务，然后判断小模型的表现是否和大模型一样好。Um, and so I think another useful uh example here is the decision model craze that has kind of been taking the world by storm in the past couple weeks with with Jev and also the parallels around routing and people being very excited about cost optimization because we see that like it's possible to spend very large amounts of money on cloud every month and we figure out like when should we use a cheaper model. Um, and this is the sort of thing that I think people are recognizing needs to kind of live in the harness. Um, but it also is a an attribute that looks relatively similar to uh decision models. And the reason I bring both these up together is because there's things with very clear labels where there's a right answer and there's an opportunity for a human or another agent to give feedback. You can have the big model and a small model do the same task, judge whether the small model was as good as the big model.

如果是这样，那么这现在就成了这类事情的数据，我们可以更多地把它路由给小模型。对于决策模型来说也是一样，它会学习模仿人在特定情境下做出判断的方式。呃，这是一个很适合标注的操作。嗯，人类可能会像我们有时在 Claude Code 中审批工具调用那样进行审批，但我觉得大多数人都开启了自动接受工具调用。不过，每个组织在更定制化的事情上——也就是那些不只是涉及工具安全的事情——都会有自己的规则和偏好。然后你就可以把这类东西不断积累起来，训练成一个决策模型。所以这是一种非常可信的持续学习形式，很多人明天就能直接接入，并立刻看到价值。If so, then we this is now data of like for this kind of thing, we can start routing to the small model more. Same for a decision model that's learning to kind of mimic the way that a human in a certain situation would make a judgment. Uh this is a great labelable action. Um where the human might be doing the approval the same way that like we approve our tool calls in cloud code sometimes, but I think most people have turned on like auto uh tool acceptance. Um but every organization for more bespoke things that aren't just about like tool security are going to have their own rules and preferences. And these are the sorts of things that you could then compound into a decision model. And so this is like a very believable form of continual learning that a lot of people could just plug in tomorrow and uh see immediate value from.

嗯，但更广泛地说，我们看到人们想做的事情——这也是我们在 PrimeClect 做的很多工作——是与一些组织合作，开展相当有雄心的训练项目：把他们在高流量用例中将模型部署到生产环境后留下的轨迹，转化为丰富、稳健、融合真实与合成数据的环境，以捕捉他们希望长期运行的智能体能够处理的真实任务的复杂性。如果有足够的编排、工具支持以及人在回路中，智能体在将这些轨迹转化为足够丰富、可用于训练的环境方面会非常有用。嗯，我们看到，随着每一代开放模型和闭源模型的推出，这一过程正变得越来越自动化。这意味着，只要将智能体用于数据整理，并创建让人们能够反馈自己需求的界面，我们就有机会自然而然地建立起这样一个自我改进循环：把我们已经在做的事情串联起来。Um but more broadly what we see people wanting to do and this is a lot of the work that that we do at PrimeClect is working with organizations that are looking to do relatively ambitious training projects around turning uh their traces from deploying a model in production for a high volume use case into rich robust environments that are blended real and synthetic that kind of capture the complexity of the real tasks they want to be using longunning agents for. and agents are very useful with sufficient orchestration around them, sufficient tooling and humans in the loop at turning these into environments that are uh rich enough to train in. Um, and we see that this is getting more and more automated with with every new generation of open and closed models. And this means that we have an opportunity to start having this whole thing of taking the stuff that we're already doing and turning it into a self-improvement loop just kind of fall out magically from applying agents to curation of the data and creating interfaces for humans to to give signal about what they want.

将决策转化为训练数据的界面Interfaces that turn decisions into training data

嗯，这是一个我一直在自己的配置中反复尝试的想法，我觉得未来它会成为一种很流行的、用于与模型交互的界面。你已经能在一些机器人中看到一点这种做法，但我觉得，尤其是现在模型已经很擅长即时编写代码了，这类小组件卡片功能会变得更加重要。我认为它们是一种非常实用的动态 UI 形式，也非常有助于引导人类做出决策。它们有点像工具调用审批功能，但个性化得多，也具体得多；同时还能绕开这样一个问题：好吧，你有 20 个不同的机器人在运行，你得记住它们分别在哪儿、谁在替你整理这些东西，然后人们就会问：“你想要一个机器人吗？”Um, this is a idea that I've been for my own setup been like playing around with a lot that I think will become a a popular interface for interacting with models more in the future. You're seeing it a little bit in some of the bots, but I think it especially now that models are good at like writing code on the fly. These kind of widget card features that are like I think a a very practical form of dynamic UI that are also really useful for eliciting human decisions. So, they're kind of like the the tool call approval thing, but much more personalized, much more specific, and also kind of get around the problem of like, okay, you have 20 different bots that are going, and you have to remember which ones are where, and who is curating all this for you, and then people are like, do you want one bot?

然后你会想，哦，一个很棒，但其实我想要两个。接着你有了两个，然后又有了 20 个。我觉得我们现在有点在单流和多流 agent 线程之间来回摇摆。但我们真正想做的是做决策。我们想给 agents 一些想法，让它们放手去做，然后在需要我们做决策时再回来找我们。希望 agents 能很好地判断什么时候该把决策交给我们。如果 agents 能即时为我们创建界面，让我们可以非常直接地把它们需要的信息提供给它们，那就更好了。首先，相比于阅读并试图从冗长的线程消息中梳理出“问题到底在哪儿？”，这种方式对我们人类来说在操作上要顺畅得多。它也有点像决策模型中人类这一面的双重性，嗯，Jev 风格。And then you're like, oh, one's great, but I actually want two. Then you have two, then you have 20. And I think we kind of are oscillating back and forth between this the single stream and the multiream agent threads. But what we really want to do are make decisions. We want to give ideas to the agents, let them run with the ideas and then come back to us when we need to make decisions. And the agents hopefully should make good choices about when to bring us decisions. And if agents can create interfaces on the fly for us that allow us to very directly give them the information they need. One, this kind of is much more ergonomic for us as humans uh than like uh reading trying to parse through a long thread message to see like, okay, where was the question? It's also kind of like the human dual side of the the decision model uh Jev style.

不过，它同时也是完美的数据。因此，我们一直在这样的场景中进行实验，尝试把它作为一种训练模型的方式，让模型形成这样的反馈循环：人们通过这类自然交互界面提供的输入，可以直接充当标签；模型也可以直接针对这些输入进行改进，因为目标非常明确。这也绕开了我们常听到的许多奖励黑客之类的问题。当然，那些问题也值得解决。但我们认为，这正是许多此类问题一个非常有用的切入点。而且，这不必应用于你技术栈中的每一个模型。它可以用于编排层模型，也可以用于决策模型。但这是一个入口，可以让模型中的偏好和隐性知识逐渐积累。Uh but it also is perfect data. And so it's a setting where we've been experimenting with this as a way of training models to kind of get this feedback loop going from having human input with these kinds of natural interfaces be the sort of thing that directly acts as a label and is the sort of thing that you that a model can directly improve on because there is a very explicit target. uh and it gets around a lot of the problems that we kind of hear about in reward hacking and whatnot. Those things are worth addressing too. But like this is like where we see a very useful starting point being for a lot of these problems. And this can be done doesn't have to be with every model in your stack. It can be the orchestration layer models. It can be the decision models. But it is an entry point for kind of starting to have this compounding of preferences and latent knowledge happen in the models.

一个价值30万美元的知识工作模型A $300K model for knowledge work

嗯，我想今天就有一个最近的例子。我刚才早些时候补充了这个例子，来自一家叫 Paper Instrument 的公司。他们使用我们的一些工具来做这件事。他们是我们的朋友。嗯，他们花了 30 万训练了一个模型，这个模型在知识工作方面，比如处理电子表格和幻灯片，算是帕累托前沿最优的。对一个组织来说，这是一笔相当于雇用一名员工的规模的投资。也就是说，你可以去雇一名软件工程师，也可以去训练一个模型。嗯，如果你是在一段较长的时间里逐步积累知识，也可以把这项投入分摊到更长的周期里。不过，这类事情正变得越来越切实可行。嗯，我们现在看到很多组织都想这么做，而且也看到了这方面的需求每个月都在增长，增长速度还越来越快。Um, and so I think there was a recent example today. I just added this uh earlier from a company called a paper instrument that uh they use some of our tooling to do this. They're they're friends of ours. Um, but they trained a model for uh 300K that is kind of paro frontier optimal for knowledge work for things like spreadsheets and slides. And it's like an employee scale investment for an org to do. Uh where like you could like go hire a software engineer or you could like train a model. Um and you can also spread this out over a longer period of time if you're kind of compounding the knowledge over time. But it's the sort of thing that is increasingly becoming quite practical. Uh and it's the sort of thing that a lot of organizations we see wanting to do now and we kind of see the trend of how much more the demand for this is growing month after month.

呃，随着人们开始认识到这一点的价值，也开始意识到开源模型已经足够好：只要把你对所在领域、测试框架和环境的了解转化为它们的训练环境，就能让它们变得更好，也更贴合个性化需求。uh as people start recognizing one the value of this and how kind of the the open models are good enough that you can get them to be much better and also much more personalized by turning your knowledge for your domain, your harness, your environment into a training setting for them.

每晚训练任务Nightly training runs

嗯，不过这也是一类天然适合形成学习闭环的事情。这是我们内部正在做的一个原型，探索我们设想人们如何才能真正将持续学习部署到实际应用中：你可以收集执行轨迹，然后每天晚上查看建议的实验，检查被标记为问题的事项，并启动一轮夜间训练。也许白天你的推理算力用于为智能体提供服务，而到了晚上，员工使用它们的频率没那么高，你就可以把这部分算力用于训练。因此，我们认为这是一种非常自然的方式，让组织很快就能真正实现模型权重层面的持续学习，并不断积累知识，逐步提升智能体的能力。Um but also it's the sort of thing that naturally lends itself to a a learning loop. And so this is a a prototype of something we're doing internally around kind of how we're imagining people can really deploy continual learning in the world which is that you can have traces you can start collecting these and you can then like every night see the proposed experiment look at the things that have been flagged as issues and kick off a training run for the night. Maybe your inference capacity in the day is serving your agents at night employees are not using them as much and you can use that capacity for training instead. And so this is a very natural way that we see organizations able to like quite soon actually do for real continual learning in the weights of the models and start compounding their knowledge into uh better and better capabilities for their agents.

自我改进型组织The self-improving organization

嗯，所以这大概就是我们看到很多事情最终汇聚到的方向。你会做很多事情：首先，摸索出自己的工作流程；然后创建技能、进行评估、设置路由；最终，你会开始希望获得规模经济，享受公司和组织内部数据带来的复利效应，并让组织以各种方式不断自我改进，随着时间推移变得越来越好。嗯，我要说的就是这些。如果还有时间的话，我也许可以回答几个问题……我也不知道，没有问题吗？嗯，对了，我们在 Primes。我们正在做很多这方面的工作，其中很多都是开源和公开的，我们也会写博客、发推文；同时，我们也与企业合作，而且正在招聘和发展壮大。如果你想联系的话，欢迎联系我们。Um and so this is kind of the where we see a lot of this culminating towards there's so many things you do. First you discover your workflow, you uh create skills, you make evals, you do routing, and then eventually you start to want to get the economies of scale, get the compounding benefits that come from the data inside of your companies, your organizations, and and have the organizations become increasingly self-improving in ways that uh get better and better over time. Um, that's what I got. Uh, I can maybe take questions if there's any time like I don't know, no questions. Um, and uh, yeah, we're at Primes. We are working a lot of the stuff. A lot of it is open source and public and we uh, blog about it and tweet about it, but also we work with companies and we're hiring and growing and so get in touch if you want to get in touch.

谢谢。Thanks.