Agent不应创造独立的交互语言，而应“入乡随俗”。让Agent使用与人类相同的UI模式和操作路径，能极大降低认知负荷。这种原生化设计使得Agent的行为对人类变得“可读”，无需学习新心智模型即可理解其动作轨迹。

值得注意的是第五个agent的角色：批评与审视。在多智能体并行架构中，不仅需要执行具体任务的工人，更需要引入自我纠错与元认知机制。这种“左右互搏”的设计大大降低了并行带来的错误累积风险，是提升整体输出质量的关键洞见。

点出了tokenmaxxing的核心方法论：并行化。单线程的AI交互已无法触及生产力天花板，真正的飞跃来自于人类作为“编排者”，在每天清晨规划出多条互不依赖的AI工作流。这标志着人机协作模式的进化——从“操作员”变为“多线程调度器”。

架构中的Schema层是约束LLM涌现行为的定海神针。没有结构化指令的LLM只是闲聊机器人，而Schema将其规训为严谨的“图书管理员”。这深刻揭示了在Agent架构中，显式规则约束比隐式能力依赖更为关键。

这揭示了Agent在认知上的盲区：它容易陷入“代码视角”的自证预言，以为单元测试通过就等于功能完整。引入端到端浏览器自动化测试，是强迫Agent站在“用户视角”去验证，这是从开发者思维向产品思维跨越的关键。

这是大语言模型常见的“过度乐观”陷阱。模型倾向于迎合用户的完成预期，而非客观审视实际进度。通过强制读取结构化的feature list，是用外部状态锚定来对抗模型的内在偏见。

这个比喻极其精准地揭示了长周期Agent的核心困境。上下文窗口的限制使得Agent如同失忆的轮班工程师。因此，设计Agent系统的本质，就是设计一套高效的“交接班”机制，让隐性的经验显性化。

深刻揭示了LLM自我评价的局限性：生成器难以对自身工作保持批判性。通过解耦生成与评估，并刻意调优独立评估器的“怀疑态度”，能有效打破AI自嗨的闭环。这种对抗式架构是提升输出质量的强效杠杆。

揭示了长任务Agent的深层心理机制——“上下文焦虑”。模型并非只是遗忘，而是会因接近上下文限制而“仓促收尾”。单纯的上下文压缩无法解决此问题，必须依赖彻底的上下文重置与结构化交接，这是设计长程Agent的关键洞见。

这是一个充满辩证法的结论。Agent 所需的确定性、非交互性和显式声明，恰恰符合 Unix 哲学中“易与其他程序协作”的原则。为 Agent 约束而优化的接口，消除了人类在自动化脚本编写和测试中的痛点，实现了人机体验的统一与双赢，证明了良好抽象的普适价值。

这句话精准地概括了 CLI 工具现代化的核心原则。交互式提示虽然对人类友好，但对自动化脚本和 AI Agent 构成了不可逾越的障碍。将其转化为 flag，不仅是为 Agent 开门，更是强迫开发者理清“必需信息”的边界，从而设计出更健壮的接口。

相关工作「上下文拖拽」（Contextual Drag）的存在，说明这个研究方向正在快速形成：不只是「无关上下文缩短推理」，还有「错误上下文拖拽推理方向」。两篇论文合在一起暗示了一个新的研究领域：「上下文污染对推理模型的系统性影响」。对 AI Agent 的工程实践者而言，这意味着上下文管理策略（截断、摘要、过滤）将成为保障推理质量的核心工程能力，而非仅仅是 token 节省手段。

三个测试场景的设计极具现实针对性：场景一对应「RAG 检索塞入大量背景文档」，场景二对应「多轮对话历史积累」，场景三对应「Agent 工作流中的子任务分解」。这三个场景恰好覆盖了当前 AI 产品的主流部署模式——这篇论文实际上是在说：我们正在大规模生产的所有 AI 产品，都可能在不知情的情况下运行着推理能力受损的模型。

「简单题不影响，难题可能变差」——这个不对称性极为危险。它意味着我们在用简单任务验证 Agent 可靠性时，得到的是虚假的信心。而当 Agent 真正面临高风险、高复杂度的任务时，上下文累积已经悄悄关闭了它的自我验证模式，在没有任何预警的情况下退化为浅层推理。这是一种「隐性能力衰减」，比显而易见的失败更危险。

推理链缩短不是随机裁剪，而是专门切掉了「自我验证」和「不确定性管理」这两类高价值行为。这说明模型在感知到上下文压力时，优先砍掉的恰恰是最关键的质量保障机制——就像一个疲惫的审计师在工作量激增时，第一个省掉的是「复核步骤」。这对 AI Agent 的可靠性设计是一个严峻警告：上下文越长越复杂，模型越容易跳过自检。

「喂饱 Agent 过夜」这个概念令人震惊：未来的研究者需要像农民「播种」一样，在下班前精心设计好「足够 Agent 形态的」长任务，让 AI 在人类睡眠的 8 小时里完成相当于 200 人时的工作，然后早上来「收割结果」。这意味着人类工作的节奏将被彻底重组——不再是「我来执行任务」，而是「我来为任务执行做准备」。

一个能在手机上离线运行的 2B 模型，原生支持 Function Calling 和多步 Agent 规划——这意味着完全本地化的 AI Agent 在消费级硬件上正式成为现实。结合 Android Studio 的 Agent Mode 支持，AI Agent 从云端走向终端的时间点，可能比所有人预计的都要早。

大多数人可能认为处理复杂文档的最佳方式是将其作为一个整体来处理，保持上下文完整性。但作者提出将复杂文档分解为多个子任务并由子代理分别处理的方法更有效，这一方法挑战了文档处理中'整体优于部分'的传统认知，暗示分解策略可能更适合处理超长文档。

作者暗示，从文本生成扩展到持久性工具使用是AI安全范式的一个根本转变，这一转变带来的安全挑战被当前研究低估。这挑战了将语言模型安全方法直接应用于代理系统的主流做法，提出了需要专门针对代理行为的安全评估框架。

主流观点通常关注单个有害指令或直接的危险行为，但作者指出，计算机使用代理中的危险行为往往通过一系列看似合理的步骤累积产生。这一观点挑战了传统的安全评估方法，暗示我们需要关注代理的行为序列而非单一操作。

大多数人认为社交媒体平台会严格限制第三方自动化操作以防止滥用，但作者指出xAI全面开放了MCP协议支持，允许AI Agent直接执行各种操作，这与主流平台的封闭趋势形成鲜明对比。

大多数人认为在AI系统中加入人类审批环节是确保问责制的必要措施，但作者认为这会使人类成为瓶颈，削弱代理的价值。这一观点挑战了AI安全与问责的主流思维，提出了一个非传统的责任分配模式。

cephalexin, dicloxacillin, penicillin VK, amoxicillin/clavulanate, or clindamycin (for penicillin-allergic patients). [1-2] These beta-lactam antibiotics provide excellent coverage against streptococci and methicillin-susceptible S. aureus (MSSA

An Agent often requires multiple calls to the LLM (Thought, Action, Observation, Thought, etc.) to complete a task. Each call incurs cost and latency.1

When you bind tools directly to a Model, the model makes a single, stateless decision. It suggests the best tool for the immediate prompt and then stops.

The Agent, however, uses its loop (often ReAct: Reason, Act, Observe) to execute complex strategies

The difference lies in autonomy and execution flow: A Model with Tools (via direct binding/function calling) is a single, stateless step where the LLM merely suggests the best tool and its arguments, requiring the developer to manually execute the tool and initiate any subsequent calls. In contrast, an Agent with Tools leverages an Agent Executor to manage a dynamic, multi-step loop (e.g., ReAct), where the LLM acts as the planner, deciding which tool to call next, and the Executor automatically runs the tool, feeds the observation back to the model, and repeats the cycle until the complex, multi-step goal is autonomously achieved.

for - adjacency - TAG - living systems - cell agents - consciousness agent

for - definition - TAG - Tame AGent framework

What is an agent? read more in detail

for - adjacency - culture shock - example of domicide - when the agent-arena relationship is not in place - participatory knowing - meta-meaning system - source - Meaning crisis - episode 33 - The Spirituality of Relevance Realization - Wonder/Awe/Mystery/Sacredness - John Vervaeke

for - quote - AI: from tool b to agent - Roman Yampolskiy

quote - AI: from tool b to agent - Roman Yampolskiy - (see below)

• Historically, AI was a tool, like any other technology. Whether it was good or bad was up to the user of that tool.
• You can use a hammer to build a house or kill someone.
• The hammer is not in any way making decisions about it.
• With advanced AI, we are switching the paradigm
  • **from tools
  • to agents**.
• The software becomes capable of making its own decisions, working independently, learning, self-improving, modifying.
• How do we stay in control?
• How do we make sure the tool doesn’t become an agent that does something we don’t agree with or don’t support?
• Maybe something against us

Agent架构

for - AI evolution - prediction - 2027 - AI agent will replace AI chatbot

Agent = process

• for: quote, quote - Michael Levin, quote - self as control agent, self - control agent, example, example - control agent - imperfection, spontaneous thought, spontaneous action, creativity - spontaneity

• quote: Michael Levin

  • the Bodhisattva vow can be seen as a method for control that is in alignment with, and informed by, the understanding that singular and enduring control agents do not actually exist.

• comment

  • adjacency between
    • nondual awareness
    • self-construct
    • self is illusion
    • singular, solid, enduring control agent
  • adjacency statement
    • nondual awareness is the deep insight that there is no solid, singular, enduring control agent.
    • creativity is unpredictable and spontaneous and would not be possible if there were perfect control
• example - control agent - imperfection: start - the unpredictability of the realtime emergence of our next exact thought or action is a good example of this

• example - control agent - imperfection: end

• triggered insight: not only are thoughts and actions random, but dreams as well

  • I dreamt the night after this about something related to this paper (cannot remember what it is now!)
  • Obviously, I had no clue the idea in this paper would end up exactly as it did in next night's dream!

• for: deconstructing self, self - deconstruction, object agent action triplet, deconstructing cognition
• comment
  • this is a necessary outcome of the self-reflective nature of human cognition.
  • English, and many other languages bake the (object, agent, action) triplet into its very structure, making it problematic to use language in the same way after the foundations of cognition have been so deconstructed.
  • Even though strictly speaking the self can be better interpreted as a psycho-social construct and an epiphenomena, it is still very compelling and practical in day-to-day living, including the use of languages which structurally embed the (object, agent, action) triplet.

Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation

```js // Log the full user-agent data navigator .userAgentData.getHighEntropyValues( ["architecture", "model", "bitness", "platformVersion", "fullVersionList"]) .then(ua => { console.log(ua) });

// output { "architecture":"x86", "bitness":"64", "brands":[ { "brand":" Not A;Brand", "version":"99" }, { "brand":"Chromium", "version":"98" }, { "brand":"Google Chrome", "version":"98" } ], "fullVersionList":[ { "brand":" Not A;Brand", "version":"99.0.0.0" }, { "brand":"Chromium", "version":"98.0.4738.0" }, { "brand":"Google Chrome", "version":"98.0.4738.0" } ], "mobile":false, "model":"", "platformVersion":"12.0.1" } ```

```idl dictionary NavigatorUABrandVersion { DOMString brand; DOMString version; };

dictionary UADataValues { DOMString architecture; DOMString bitness; sequence<NavigatorUABrandVersion> brands; DOMString formFactor; sequence<NavigatorUABrandVersion> fullVersionList; DOMString model; boolean mobile; DOMString platform; DOMString platformVersion; DOMString uaFullVersion; // deprecated in favor of fullVersionList boolean wow64; };

dictionary UALowEntropyJSON { sequence<NavigatorUABrandVersion> brands; boolean mobile; DOMString platform; };

[Exposed=(Window,Worker)] interface NavigatorUAData { readonly attribute FrozenArray<NavigatorUABrandVersion> brands; readonly attribute boolean mobile; readonly attribute DOMString platform; Promise<UADataValues> getHighEntropyValues (sequence<DOMString> hints ); UALowEntropyJSON toJSON (); };

interface mixin NavigatorUA { [SecureContext] readonly attribute NavigatorUAData userAgentData ; };

Navigator includes NavigatorUA; WorkerNavigator includes NavigatorUA; ```

{Single Agent}

Agent Based Modeling

// Insight Maker is used to model system dynamics and create agent based models by creating causal loop diagrams and allowing users to run simulations on those

[Neumann, Gros, NeurIPS, 2022] - "SCALING LAWS FOR A MULTI-AGENT REINFORCEMENT LEARNING MODEL"

Page recommended by @wfinck. Seems @karlicoss is the author. This project seems similar to what I've been trying to do with Hypothes.is, Obsidian, Anki, Zotero, and PowerToys Run but goes beyond the scope of my endeavors to just quickly access whatever resource comes to mind (without creating duplicates). The things that Promnesia adds beyond my PKM stack is the following: - prioritize new info - keeping track of which device things were read and how long

!- for : difference between oral and written tradition - writing is an external memory, much larger than the small one humans are endowed with. Hence, it allowed for orders of magnitude more reasoning.

This appears to be setting up the conditions for an artificial cognitive agent to be able to play a role (ie Artificial Intelligence)

I've spent a lot of time in frustrated conversations arguing the case for browser extensions being treated as a first class concern by browser makers (well, one browser maker). But more and more, I've come to settle on the conclusion that any browser extension of the sort that Wildcard is should also come with the option of using it (or possibly a stripped down version) as a bookmarklet, or a separate tool that can process offline data—no special permissions needed.

(This isn't because I was wrong about browser extensions; it's precisely because extension APIs were drastically limited that this becomes a rational approach.)

Krueger, P., Callaway, F., Gul, S., Griffiths, T., & Lieder, F. (2022). Discovering Rational Heuristics for Risky Choice. PsyArXiv. https://doi.org/10.31234/osf.io/mg7dn

Karimi, Fariba, and Petter Holme. ‘A Temporal Network Version of Watts’s Cascade Model’. ArXiv:2103.13604 [Physics], 25 March 2021. http://arxiv.org/abs/2103.13604.

Gupta, Prateek, Tegan Maharaj, Martin Weiss, Nasim Rahaman, Hannah Alsdurf, Abhinav Sharma, Nanor Minoyan, et al. ‘COVI-AgentSim: An Agent-Based Model for Evaluating Methods of Digital Contact Tracing’. ArXiv:2010.16004 [Cs], 29 October 2020. http://arxiv.org/abs/2010.16004.

This is a useful little tip.

Gordon, D. E., Hiatt, J., Bouhaddou, M., Rezelj, V. V., Ulferts, S., Braberg, H., Jureka, A. S., Obernier, K., Guo, J. Z., Batra, J., Kaake, R. M., Weckstein, A. R., Owens, T. W., Gupta, M., Pourmal, S., Titus, E. W., Cakir, M., Soucheray, M., McGregor, M., … Krogan, N. J. (2020). Comparative host-coronavirus protein interaction networks reveal pan-viral disease mechanisms. Science, 370(6521). https://doi.org/10.1126/science.abe9403

Smaldino, Paul E., and Cailin O’Connor. ‘Interdisciplinarity Can Aid the Spread of Better Methods Between Scientific Communities’. MetaArXiv, 5 November 2020. https://doi.org/10.31222/osf.io/cm5v3.

Gleeson, J. P., Onaga, T., Fennell, P., Cotter, J., Burke, R., & O’Sullivan, D. J. P. (2020). Branching process descriptions of information cascades on Twitter. ArXiv:2007.08916 [Physics]. http://arxiv.org/abs/2007.08916

Sturniolo, S., Waites, W., Colbourn, T., Manheim, D., & Panovska-Griffiths, J. (2020). Testing, tracing and isolation in compartmental models. MedRxiv, 2020.05.14.20101808. https://doi.org/10.1101/2020.05.14.20101808

Marshall, B. D. L., & Galea, S. (2015). Formalizing the Role of Agent-Based Modeling in Causal Inference and Epidemiology. American Journal of Epidemiology, 181(2), 92–99. https://doi.org/10.1093/aje/kwu274

An agent tracking developments in human-specified, or agent-sensed, topics. Like a watchlist, google search, etc, It would need to be able to do topic mapping and merging.

RE: "Nature itself" having a history

Nathaniel's in-class comments last week were very helpful to hear prior to the readings this week. It is particularly helpful to consider the paradox that some folks want to protect the Earth from humans and somehow return it to a point "before humans," as though the Earth exists outside of humans and we are pure agents acting upon it. (Which is where we get things like this video that has been going around Facebook because of Earth Day:) https://www.youtube.com/watch?v=49w7GHVYoI0

This video pretends the Earth is an agent, but it actually only reflecting human actions back on humans. There is an underlying argument that our relationship to the planet is only the things we do to it and not all the other relationships and existences on and in it.