Weekly Digest — 2025-W31

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

A generative world for general-purpose robotics & embodied AI learning.

Examples and tutorials to help developers build AI systems

📚 Collaborative cheatsheets for console commands

21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

Best and simplest tool for website change detection, web page monitoring, and website change alerts. Perfect for tracking content changes, price drops, restock alerts, and website defacement monitoring—all for free or enjoy our SaaS plan!

Portable file server with accelerated resumable uploads, dedup, WebDAV, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file, no deps

The ultimate LLM/AI application development framework in Golang.

peer-2-peer that just works

Windows system utilities to maximize productivity

We write your reusable computer vision tools. 💜

The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.

Build browser automations with AI

Cursor for Microsoft Word

AI game engine to prototype 3D games in a day

Ultra-lightweight humanoid robot starting at $5900

A free and open-source, embeddable video conference app.

Remove vocals from any song

Design new features with AI

AI that doesn’t just respond—it resolves

Turn your podcasts into viral video content

Automatically draft Gmail replies that sound just like you

Quick notes on screen edge

The first open MoE model for AI video generation

Deep research agents, powered by Large Language Models (LLMs), are rapidly advancing; yet, their performance often plateaus when generating complex, long-form research reports using generic test-time scaling algorithms. Drawing inspiration from the iterative nature of human research, which involves cycles of searching, reasoning, and revision, we propose the Test-Time Diffusion Deep Researcher (TTD-DR). This novel framework conceptualizes research report generation as a diffusion process. TTD-DR initiates this process with a preliminary draft, an updatable skeleton that serves as an evolving foundation to guide the research direction. The draft is then iteratively refined through a "denoising" process, which is dynamically informed by a retrieval mechanism that incorporates external information at each step. The core process is further enhanced by a self-evolutionary algorithm applied to each component of the agentic workflow, ensuring the generation of high-quality context for the diffusion process. This draft-centric design makes the report writing process more timely and coherent while reducing information loss during the iterative search process. We demonstrate that our TTD-DR achieves state-of-the-art results on a wide array of benchmarks that require intensive search and multi-hop reasoning, significantly outperforming existing deep research agents.

Quantizing the weights of large language models (LLMs) from 16-bit to lower bitwidth is the de facto approach to deploy massive transformers onto more affordable accelerators. GPTQ emerged as one of the standard methods for one-shot post-training quantization at LLM scale. Yet, its inner workings are described as a sequence of ad-hoc algebraic updates that obscure any geometric meaning or worst-case guarantees. In this work, we show that, when executed back-to-front (from the last to first dimension) for a linear layer, GPTQ is mathematically identical to Babai's nearest plane algorithm for the classical closest vector problem (CVP) on a lattice defined by the Hessian matrix of the layer's inputs. This equivalence is based on a sophisticated mathematical argument, and has two analytical consequences: (i) the GPTQ error propagation step gains an intuitive geometric interpretation; (ii) GPTQ inherits the error upper bound of Babai's algorithm under the no-clipping condition. Taken together, these results place GPTQ on firm theoretical footing and open the door to importing decades of progress in lattice algorithms towards the design of future quantization algorithms for billion-parameter models.

We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web platforms. It comprises four levels: GUI Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents. In addition, we propose a novel Efficiency-Quality Area (EQA) metric to assess GUI agent execution efficiency in online automation scenarios. Through MMBench-GUI, we identify accurate visual grounding as a critical determinant of overall task success, emphasizing the substantial benefits of modular frameworks that integrate specialized grounding modules. Furthermore, to achieve reliable GUI automation, an agent requires strong task planning and cross-platform generalization abilities, with long-context memory, a broad action space, and long-term reasoning playing a critical role. More important, task efficiency remains a critically underexplored dimension, and all models suffer from substantial inefficiencies, with excessive redundant steps even when tasks are ultimately completed. The integration of precise localization, effective planning, and early stopping strategies is indispensable to enable truly efficient and scalable GUI automation. Our benchmark code, evaluation data, and running environment will be publicly available at https://github.com/open-compass/MMBench-GUI.

The evaluation of Large Language Models (LLMs) increasingly relies on other LLMs acting as judges. However, current evaluation paradigms typically yield a single score or ranking, answering which model is better but not why. While essential for benchmarking, these top-level scores obscure the specific, actionable reasons behind a model's performance. To bridge this gap, we introduce CLEAR, an interactive, open-source package for LLM-based error analysis. CLEAR first generates per-instance textual feedback, then it creates a set of system-level error issues, and quantifies the prevalence of each identified issue. Our package also provides users with an interactive dashboard that allows for a comprehensive error analysis through aggregate visualizations, applies interactive filters to isolate specific issues or score ranges, and drills down to the individual instances that exemplify a particular behavioral pattern. We demonstrate CLEAR analysis for RAG and Math benchmarks, and showcase its utility through a user case study.

While end-to-end autonomous driving models show promising results, their practical deployment is often hindered by large model sizes, a reliance on expensive LiDAR sensors and computationally intensive BEV feature representations. This limits their scalability, especially for mass-market vehicles equipped only with cameras. To address these challenges, we propose PRIX (Plan from Raw Pixels). Our novel and efficient end-to-end driving architecture operates using only camera data, without explicit BEV representation and forgoing the need for LiDAR. PRIX leverages a visual feature extractor coupled with a generative planning head to predict safe trajectories from raw pixel inputs directly. A core component of our architecture is the Context-aware Recalibration Transformer (CaRT), a novel module designed to effectively enhance multi-level visual features for more robust planning. We demonstrate through comprehensive experiments that PRIX achieves state-of-the-art performance on the NavSim and nuScenes benchmarks, matching the capabilities of larger, multimodal diffusion planners while being significantly more efficient in terms of inference speed and model size, making it a practical solution for real-world deployment. Our work is open-source and the code will be at https://maxiuw.github.io/prix.

Language models (LMs) are susceptible to in-context reward hacking, where they exploit flaws in tainted or faulty written specifications or rubrics to achieve high scores without fulfilling the user's true intent. We introduce Specification Self-Correction (SSC), a novel, test-time framework that enables an LM to identify and correct flaws within its own guiding specification. SSC employs a multi-step inference process where the model first generates a response based on a potentially tainted specification, critiques its output, and then revises the specification itself to remove the exploitable loophole. A final, more robust response is then generated using this self-corrected specification. Across experiments spanning creative writing and agentic coding tasks with several LMs, we demonstrate that while models initially game tainted specifications in 50-70\% of cases, the SSC process reduces this vulnerability by over 90\%. This dynamic repair occurs at inference time, requires no weight modification, and leads to more robustly aligned model behavior. Code at https://github.com/vicgalle/specification-self-correction .

Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can often utilize external tools to assist in task-solving processes. However, current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions. To bridge this gap, we propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents. Through preliminary experiments, we observe that LLMs tend to exhibit highly uncertain behavior, characterized by an increase in the entropy distribution of generated tokens, immediately following interactions with external tools. Motivated by this observation, ARPO incorporates an entropy-based adaptive rollout mechanism, dynamically balancing global trajectory sampling and step-level sampling, thereby promoting exploration at steps with high uncertainty after tool usage. By integrating an advantage attribution estimation, ARPO enables LLMs to internalize advantage differences in stepwise tool-use interactions. Our experiments across 13 challenging benchmarks in computational reasoning, knowledge reasoning, and deep search domains demonstrate ARPO's superiority over trajectory-level RL algorithms. Remarkably, ARPO achieves improved performance using only half of the tool-use budget required by existing methods, offering a scalable solution for aligning LLM-based agents with real-time dynamic environments. Our code and datasets are released at https://github.com/dongguanting/ARPO

Real-world user-generated short videos, especially those distributed on platforms such as WeChat Channel and TikTok, dominate the mobile internet. However, current large multimodal models lack essential temporally-structured, detailed, and in-depth video comprehension capabilities, which are the cornerstone of effective video search and recommendation, as well as emerging video applications. Understanding real-world shorts is actually challenging due to their complex visual elements, high information density in both visuals and audio, and fast pacing that focuses on emotional expression and viewpoint delivery. This requires advanced reasoning to effectively integrate multimodal information, including visual, audio, and text. In this work, we introduce ARC-Hunyuan-Video, a multimodal model that processes visual, audio, and textual signals from raw video inputs end-to-end for structured comprehension. The model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning. Leveraging high-quality data from an automated annotation pipeline, our compact 7B-parameter model is trained through a comprehensive regimen: pre-training, instruction fine-tuning, cold start, reinforcement learning (RL) post-training, and final instruction fine-tuning. Quantitative evaluations on our introduced benchmark ShortVid-Bench and qualitative comparisons demonstrate its strong performance in real-world video comprehension, and it supports zero-shot or fine-tuning with a few samples for diverse downstream applications. The real-world production deployment of our model has yielded tangible and measurable improvements in user engagement and satisfaction, a success supported by its remarkable efficiency, with stress tests indicating an inference time of just 10 seconds for a one-minute video on H20 GPU.

Despite the promise of Multi-Task Learning in leveraging complementary knowledge across tasks, existing multi-task optimization (MTO) techniques remain fixated on resolving conflicts via optimizer-centric loss scaling and gradient manipulation strategies, yet fail to deliver consistent gains. In this paper, we argue that the shared representation space, where task interactions naturally occur, offers rich information and potential for operations complementary to existing optimizers, especially for facilitating the inter-task complementarity, which is rarely explored in MTO. This intuition leads to Rep-MTL, which exploits the representation-level task saliency to quantify interactions between task-specific optimization and shared representation learning. By steering these saliencies through entropy-based penalization and sample-wise cross-task alignment, Rep-MTL aims to mitigate negative transfer by maintaining the effective training of individual tasks instead pure conflict-solving, while explicitly promoting complementary information sharing. Experiments are conducted on four challenging MTL benchmarks covering both task-shift and domain-shift scenarios. The results show that Rep-MTL, even paired with the basic equal weighting policy, achieves competitive performance gains with favorable efficiency. Beyond standard performance metrics, Power Law exponent analysis demonstrates Rep-MTL's efficacy in balancing task-specific learning and cross-task sharing. The project page is available at HERE.

While frontier large language models (LLMs) continue to push capability boundaries, their deployment remains confined to GPU-powered cloud infrastructure. We challenge this paradigm with SmallThinker, a family of LLMs natively designed - not adapted - for the unique constraints of local devices: weak computational power, limited memory, and slow storage. Unlike traditional approaches that mainly compress existing models built for clouds, we architect SmallThinker from the ground up to thrive within these limitations. Our innovation lies in a deployment-aware architecture that transforms constraints into design principles. First, We introduce a two-level sparse structure combining fine-grained Mixture-of-Experts (MoE) with sparse feed-forward networks, drastically reducing computational demands without sacrificing model capacity. Second, to conquer the I/O bottleneck of slow storage, we design a pre-attention router that enables our co-designed inference engine to prefetch expert parameters from storage while computing attention, effectively hiding storage latency that would otherwise cripple on-device inference. Third, for memory efficiency, we utilize NoPE-RoPE hybrid sparse attention mechanism to slash KV cache requirements. We release SmallThinker-4B-A0.6B and SmallThinker-21B-A3B, which achieve state-of-the-art performance scores and even outperform larger LLMs. Remarkably, our co-designed system mostly eliminates the need for expensive GPU hardware: with Q4_0 quantization, both models exceed 20 tokens/s on ordinary consumer CPUs, while consuming only 1GB and 8GB of memory respectively. SmallThinker is publicly available at hf.co/PowerInfer/SmallThinker-4BA0.6B-Instruct and hf.co/PowerInfer/SmallThinker-21BA3B-Instruct.

Reconstructing 4D spatial intelligence from visual observations has long been a central yet challenging task in computer vision, with broad real-world applications. These range from entertainment domains like movies, where the focus is often on reconstructing fundamental visual elements, to embodied AI, which emphasizes interaction modeling and physical realism. Fueled by rapid advances in 3D representations and deep learning architectures, the field has evolved quickly, outpacing the scope of previous surveys. Additionally, existing surveys rarely offer a comprehensive analysis of the hierarchical structure of 4D scene reconstruction. To address this gap, we present a new perspective that organizes existing methods into five progressive levels of 4D spatial intelligence: (1) Level 1 -- reconstruction of low-level 3D attributes (e.g., depth, pose, and point maps); (2) Level 2 -- reconstruction of 3D scene components (e.g., objects, humans, structures); (3) Level 3 -- reconstruction of 4D dynamic scenes; (4) Level 4 -- modeling of interactions among scene components; and (5) Level 5 -- incorporation of physical laws and constraints. We conclude the survey by discussing the key challenges at each level and highlighting promising directions for advancing toward even richer levels of 4D spatial intelligence. To track ongoing developments, we maintain an up-to-date project page: https://github.com/yukangcao/Awesome-4D-Spatial-Intelligence.

Large Language Models (LLMs) have demonstrated strong capabilities but remain fundamentally static, unable to adapt their internal parameters to novel tasks, evolving knowledge domains, or dynamic interaction contexts. As LLMs are increasingly deployed in open-ended, interactive environments, this static nature has become a critical bottleneck, necessitating agents that can adaptively reason, act, and evolve in real time. This paradigm shift -- from scaling static models to developing self-evolving agents -- has sparked growing interest in architectures and methods enabling continual learning and adaptation from data, interactions, and experiences. This survey provides the first systematic and comprehensive review of self-evolving agents, organized around three foundational dimensions -- what to evolve, when to evolve, and how to evolve. We examine evolutionary mechanisms across agent components (e.g., models, memory, tools, architecture), categorize adaptation methods by stages (e.g., intra-test-time, inter-test-time), and analyze the algorithmic and architectural designs that guide evolutionary adaptation (e.g., scalar rewards, textual feedback, single-agent and multi-agent systems). Additionally, we analyze evaluation metrics and benchmarks tailored for self-evolving agents, highlight applications in domains such as coding, education, and healthcare, and identify critical challenges and research directions in safety, scalability, and co-evolutionary dynamics. By providing a structured framework for understanding and designing self-evolving agents, this survey establishes a roadmap for advancing adaptive agentic systems in both research and real-world deployments, ultimately shedding lights to pave the way for the realization of Artificial Super Intelligence (ASI), where agents evolve autonomously, performing at or beyond human-level intelligence across a wide array of tasks.

编程问答平台 Stack Exchange 宣布迁移到云端，放弃使用自己的服务器。Stack Exchange 自 2010 年起就在新泽西州的数据中心托管旗下网站，它使用了大约 50 台服务器。如果服务器出现问题，工程师需要去现场更换或重启硬件。2023 年它的 Stack Overflow for Teams 迁移到了微软的 Azure 云，现在 Stack Overflow 和 Stack Exchange 网络托管在了 Google Cloud 云服务上。Stack Overflow 从此不再拥有任何物理数据中心或办公室，完全在云端远程工作。

分析显示，今天的环法自行车选手已经超越了兴奋剂时代的阿姆斯特朗（Lance Armstrong）。去年环法自行车赛的一个山地赛段中 Tadej Pogacar 在近 40 分钟内的功率输出约 7瓦/千克。Jonas Vingegaard 曾在近 15 分钟内功率输出超过 7瓦/千克。相比下，阿姆斯特朗在 20 年前靠兴奋剂实现了 6瓦/千克的功率输出，他完成路段的时间比今天的顶尖选手慢。阿姆斯特朗靠服用兴奋剂从 1999 年到 2005 年连续七次获得环法自行车赛冠军。于 2012年 被取消自 1998 年 8 月之后的所有成绩，被终身禁赛。今天的选手表现更出色源于技术进步：每位选手都使用提供实时性能数据的功率计；营养摄入使用精确测量的食物摄入量持续补充热量；自行车使用风洞测试以降低阻力系数，等等。

《科学》期刊撤下了受争议的砷基生命论文。2010 年《科学》期刊发表了 F. Wolfe-Simon 等人的论文《A bacterium that can grow by using arsenic instead of phosphorus》，声称在加州湖泊中发现了一种砷基细菌 GFAJ-1，它利用砷而不是磷生长。论文发表之后引发了很多争议，2012 年《科学》发表了两篇未能复制这一发现的论文。《科学》期刊主编 Holden Thorp 在声明中称，他们没有在 2012 年撤回论文是因为当时的政策主要针对存在科学不端行为，而这篇论文的作者没有故意欺骗或犯有不端行为。《科学》后来扩大了撤稿的政策：如果一篇论文报告的实验结果不支持其核心结论，撤下是合适的。

Pebble 创始人 Eric Migicovsky 宣布他拿回了原始商标，因此他的公司准备推出的智能手表产品将使用 Pebble 商标：Core 2 Duo 改为 Pebble 2 Duo，Core Time 2 改名 Pebble Time 2。Pebble 诞生于 2012 年，Eric Migicovsky 通过 Kickstarter 筹集到了创纪录的 1030 万美元，而其第二代智能手表通过 Kickstarter 再次筹集到破纪录的 2030 万美元。但在 2016 年 12 月 Pebble 出售给 Fitbit 后关闭，创始人也离开了公司。Google 通过收购 Fitbit 获得了 Pebble 的所有权。今年初 Google 宣布在 Apache License 2.0 下开源 Pebble 智能手表操作系统，源代码托管在 GitHub 上。而 Migicovsky 同一时间宣布推出能运行 Pebble OS 的新智能手表产品。

一项初步研究显示，全球的民用机场与军事设施所操作的雷达系统，可能正无意间将地球的存在广播给科技先进的外星文明，这些讯号可被视为智慧生命的间接证据。研究调查了雷达系统泄漏出的电波讯号若由距离地球 200 光年的观测者侦测到，会呈现出怎样的样貌，前提是他们拥有与地球上同等级的电波望远镜。研究结果同时也意味着，理论上我们也能在相同范围内侦测到类似等级的外星文明。研究人员的目标是评估六个邻近的恒星系统，尤其是巴纳德星（Barnard’s Star，5.98光年） 与显微镜座AU（AU Microscopii，32.3光年）来看，这些讯号的可侦测程度。分析显示，机场用来监控飞机的雷达系统，合计产生约 2×10¹⁵瓦特的功率，这样的能量输出足以让如绿堤望远镜（Green Bank Telescope）等级的电波望远镜在 200 光年外仍能侦测到讯号。军事雷达系统具有更高的指向性，形成如同灯塔光束扫过天空般的独特模式。

域名系统（DNS）的原始设计不包含任何安全细节，域名系统安全扩展（DNSSEC）尝试在其中添加安全性，同时仍保持向后兼容性。DNSSEC 能阻止 DNS 缓存污染等攻击，它的 RFC 是在 28 年前发布的，根据 Internet Society 的数据，DNSSEC 普及率仅为 34%，相比下 HTTPS 的开发时间线与 DNSSEC 基本相同——在 Top 1000 网站中，HTTPS 的普及率为 96%，HTTP/3 仅发布四年时间普及率就达到了 25%。大约三成的国家域名尚未实现 DNSSEC。

挪威经济学家 Martin Bech Holte 在新书《The Country That Became Too Rich》中将矛头对准自己的国家，认为挪威太富裕而致使其经济健康受损。挪威的主权财富基金高达 2 万亿美元，相当于人均 34 万美元，过去二十年挪威的生产力增长在富裕国家中最低，而挪威人每年请的病假天数多达 27.5 天，在经合组织中最多。挪威人均教育经费为 2 万美元，经合组织的平均水平为 1.4 万美元，但自 2015 年以来挪威学生的考试成绩持续下降，目前低于经合组织平均水平。挪威从主权基金中提取的资金占到了国家年度预算的五分之一以上，而二十年前不到十分之一。

两年前，中国的大学警告学生不要在作业中使用 AI。今天的大学逆转了立场，鼓励学生使用 AI，只要他们遵守最佳实践（best practices）。根据麦可思研究院(MyCOS Institute)的调查，生成式 AI 已基本普及，只有 1% 的师生表示从未在学习或工作中使用 AI，近六成被调查者表示每天或每周数次使用 AI。随着 DeepSeek 的流行，人们日益将生成式 AI 视为国家骄傲的来源。高校的讨论重心逐渐从担忧 AI 对学术诚信的影响转向鼓励学生提高素养、提高生产力和保持领先。斯坦福大学 Institute for Human-Centered Artificial Intelligence (HAI)的调查发现，中国对 AI 热情领先于世界其它国家，八成的人对 AI 感到兴奋，相比下美国和英国仅为 35% 和 38%。MIT Technology Review 对 46 所中国顶尖大学 AI 战略的调查发现，几乎所有学校过去一年引入了跨学科的 AI 通识教育课和 AI 相关学位。清华大学、人民大学、南京大学和复旦大学等推出了 AI 素养课程和学位，面向所有学生而不只是计算机科学专业的学生。教育部于 2025 年 4 月发布了国家“AI +教育”指南，呼吁进行全面改革。

秦始皇帝陵博物院兵马俑研究考古人员通过超景深显微镜捕捉到了 2000 多年前清晰的指纹印记，提取了指纹100多枚。研究显示兵马俑的塑造者中有未成年人。秦始皇帝陵博物院馆员李晓溪介绍，工作人员在已经修复的 40 多件陶俑身上，提取了指纹100多枚。通过对指纹进行分析比对， 获取了陶工的年龄构成， 和性别比例等信息。初步分析显示，绝大多数指纹属于成年男性，与传统认知相符，同时也发现存在少量未成年人指纹。至于在整个制作过程中 ，他们都参与了什么样的环节，存在怎样的分工差异还需要进一步分析研究。

北京谋智火狐信息技术有限公司（北京火狐）宣布，2025 年 5 月 8 日，Mozilla 与北京火狐达成一致，北京火狐将不再运营 Firefox 浏览器及任何与 Firefox 有关的中国大陆业务。自 2025 年 9 月 29 日晚 24:00 起，Firefox 火狐中文官方网站（firefox.com.cn）、Firefox 火狐社区网站（mozilla.com.cn）、Firefox 火狐通行证账户服务（accounts.firefox.com.cn）及 Firefox 火狐主页（home.firefoxchina.cn）将正式停止运营，所有相关功能将终止。自即日起，Firefox 火狐中文官方网站 www.firefox.com.cn 将不再提供 Firefox 浏览器相关产品的下载。中国火狐用户需要在 2025 年 9 月 29 日前将北京火狐服务器上的数据同步到本地，在这之后所有数据都将删除。Mozilla Firefox 用户不受任何影响。

仙女座大星系近旁发现被称为 SDSO1 的星云。根据一篇预印本，SDSO1 可能并非来自仙女座，而是位于银河系内的一个古老行星状星云，被命名为「幽灵行星状星云」（Ghost Planetary Nebula, GPN）。这项研究由多位业余天文摄影师联合完成。研究团队透过影像显示的弓形震波与尾迹结构，并比对银河系内，距离地球约 600 光年的共生双星 EG Andromedae（仙女座EG）的位置与特性，推论这片云气正是由该双星系统在数十万年前抛出的壳层所形成，进而成为行星状星云。分析显示，仙女座EG 以每秒约 107 公里的速度穿越星际介质，因而产生壮观的弓形结构与长达 45 光年的尾迹。这类行星状星云在演化后期已极度稀薄而黯淡，但因与周围介质的高速交互作用才显现，SDSO1 也因此成为已知首个被提出的幽灵行星状星云案例。研究团队还辨识出银河系内另有 7 个具有类似特征的幽灵行星状星云候选天体，显示这类古老天体可能比我们以往认为的更为普遍。

根据发表在《Nature Medicine》期刊上的一项研究，教育并不能延缓认知衰退。对 170,795 名 50 岁以上参与者的 407,356 份情景记忆评分和 6,472 人的 15,157 次脑部磁共振成像(MRI)扫描数据分析发现，教育程度与更好的记忆功能、更大的颅内体积相关，但并不能阻挡岁月对大脑的侵蚀。无论学历高低，大脑都会以相似的节奏慢慢萎缩，认知能力也会同步下滑。教育给了你一个更好的起跑线，但并不能改变衰老这场马拉松的节奏。虽然读书不能让你永葆青春，但至少能让你在变老的路上保持更清晰的头脑。