AI 新闻 · V2

最新：Anthropic 最新经济报告警告，程序员可能需要去学修马桶。

突发：据《The Prospect》报道，Anthropic 据称正在建设一套广泛的监控与情报系统，用于监视反对人工智能的活动人士和抗议活动。

他确实在那里工作过，但只待了几个月。

前 Anthropic 员工 Jacob Coxon 称 AI 行业是在“拿我们的生命赌博”。他对安德森说，最可怕的是“AI 被用来让自己变得更智能”，并警告这些公司“被迫竞相打造致命技术”。

Jacob 是今年5月加入 Anthropic 的资深研究员。我和同事们约两年时间都在争取招他，因为他在 OpenAI 表现很强。离开前我曾劝他留下加入我的团队，他决定走我很遗憾，很多同事也一样。我完全同意 AI 对社会有严重风险，也很高兴他站出来说话。

推出 DeepSeek-V4.1-Flash：更智能、更快、更高效。介绍我们新架构家族中的最小模型，具备原生视觉理解；旨在更强能力、更快推理、更高吞吐，并面向更大规模模型扩展。1/6

明天我会拆解 Jacob Coxon 在 CNN 的露面。但先别再搞“只干了六周/入门级”那套胡扯和人身攻击了。我最可信的消息源说他大约五月底入职，不是某些一本正经胡说八道的 AI 网站（以及一群本不该轻信 AI 的人）声称的七月。所谓“几周”据我所知根本是假的。“入门级”也是胡扯（他在 OpenAI 干了两年多，Anthropic 长期挖他）。别搞人身攻击，把焦点放回他观点的优劣上。

嗯，眼下中国实验室的公开与开放程度比美国实验室高出一百倍。

Gemini 3.8 Cyber 在多项网络防御基准和真实场景中比 Mythos 更强。它已在 Google 内部被 Chrome、Wiz 和 Cloud 广泛使用（很快也会对外扩展）。https://deepmind.google/models/gemini/cyber/

抛开关于存在性风险的政策不论，值得注意的是：即便今天就停止 AI 研发、只保留现有模型，随着工具链完善与用途扩散，工作、教育和社会生活的大部分领域仍将至少经历十年剧烈变革。

而且 @Grok @Bot 几乎每天都在变得更好。

Self-supervised speech foundation models are now used in a wide array of downstream applications, including traditional speech recognition and as the basis for tokens in speech-aware language models. Attempts to understand their usefulness have largely focused on probing their representations' ability to discriminate phonemes and words. However, discriminative ability for words need not imply spec

Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and regulatory concerns. Machine unlearning offers a practical alternative to full retraining, but many existing methods apply broad or fixed parameter updates that can degrade utility and remain brittle under deployment changes such as post-training

While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context limits. To address this, sequential approaches like MemAgent extend the effective context by reading text in segments and iteratively updating a fixed-size memory. However, this sequential paradigm suffers from high latency and requires costly reinforc

Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: models primarily reason in English regardless of the language they are prompted in. This is inaccessible for non-English-speaking users, risks losing the intent of the original question, and forgoes knowledge more readily expressed in the target lang

Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance of shared state, and coordination across heterogeneous environments. However, existing GUI benchmarks overwhelmingly evaluate agents on single-device, statically defined tasks, thus leaving such cross-device capabilities largely unexamined, result

Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning, but their capability to learn physics and generate physically realistic dynamics remains hitherto untested. In this work, we introduce SemiGroup-JEPA (SG-JEPA), which extends the LeWorldModel framework by supplying the parameter governing the physics

More Electric Aircraft require fast and reliable monitoring of high-frequency electrical networks, yet most power quality disturbance and fault diagnosis methods are developed for conventional 50 or 60 Hz grids. This work presents a hardware-aware deep learning framework for multiclass detection of electrical faults and power quality disturbances in a 400 Hz aerospace power system. A high-fidelity

We construct counterexamples to Rockafellar's sum conjecture in which two maximally monotone operators satisfy the interior-domain condition but their sum is not maximally monotone. We give one counterexample on $c_0$ and another on $\ell^1$ with its usual norm. We establish a general construction theorem that computes the entire monotone polar of a class of graphs, gives a necessary and sufficien

This feature article provides an overview of the theoretical foundations for coVariance neural networks (VNNs), i.e., graph neural networks (GNNs) operating on covariance matrices as graphs. Covariance matrices are ubiquitous across domains, and hence, the deployment of GNNs often leverages graphs of pairwise statistical dependencies. Existing theoretical contributions on GNNs consider abstract gr

Enterprises deploy systems, not checkpoints. Usable capability depends jointly on weights, serving route, precision, output contract, and harness, yet all 18 audited benchmarks score advertised model identifiers. We treat this as measurement error and give a protocol that makes it reportable. It has three parts. A gold-blind capability-binding preflight verifies that a route can execute the evalua

In real-time colonoscopy, ground-truth annotations are unavailable at inference, so polyp segmentation models can fail silently. We propose Referee-Based Quality Estimation (RBQE), a reference-free framework measuring agreement between a primary segmentation model and an independently trained referee on the same image. RBQE is evaluated on a standardized 1,223-image external benchmark drawn from f

Credit default prediction is a tabular classification problem in which modest gains in F1 translate directly into reduced financial exposure. We ask whether Instantaneous Quantum Polynomial-time (IQP) circuits can produce features that improve a classifier over both its raw classical baseline and Kernel PCA - the strongest unsupervised classical non-linear alternative - at an equal feature budget.

We determine the optimal sample complexity of low-rank quantum state tomography when each measurement may act jointly on at most $t$ samples. For sufficiently small $\varepsilon$, estimating an unknown state on $\mathbb{C}^d$ of rank at most $r$ to trace norm error $\varepsilon$ with constant success probability requires, and is achievable with, $$ Θ\left( \frac{dr}{\varepsilon^2} \max\left\

Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We present Show-Harness, an Embodied Harness that enables VLMs to "play" robots through a compact semantic interface linking intent to action. Show-Harness exposes discrete semantic action units that VLMs can naturally reason over, while emb

Language generation in the limit asks for valid unseen elements from every exhaustive positive presentation of an unknown infinite language. We characterize this task for arbitrary families over a countable universe. Generation is possible exactly when each target can be assigned a finite positive witness so that the targets activated by any finite sample have an infinite common intersection. The

We prove the gap-entropy conjecture for fixed-confidence best-arm identification with independent unit-variance Gaussian arms, means in $[0,1]$, and a unique optimal arm. For each suboptimal arm $i$, let $Δ_i=μ_*-μ_i$ be its gap from the optimal mean, and write $H=\sum_{i\ne *}Δ_i^{-2}$. Let $p_r$ be the fraction of $H$ contributed by arms with $2^{-(r+1)}<Δ_i\le2^{-r}$, and let $\mathrm{Ent}(I)=\

We present a simple decomposition of a neural-network-based normalizing flow that naturally uncovers a pivotal statistic (or something close) in the presence of nuisance parameters, based only on a sample generator from the distribution of interest. We show that the statistic is near-pivotal in the sense of minimum average KL-divergence of its $p$-values versus uniform and we argue that it can be

A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently specified for faithful implementation. We study the codification readiness of implementation-facing research-method specifications, defined by whether they provide sufficient methodological information for a competent implementer or coding agent to construct the intended method w

谷歌DeepMind开发新的AI搜索排名模型 - Search Engine Journal

GPT-6 Astra × V2Fun：当大模型开始“编排”三维生成，AI建模范式正在转变 - 36氪

权利中心发现：大语言模型可能抑制批判性思维 - Quantum Zeitgeist

人工智能与灵性智慧 - Catholic Stand

NASA与IBM科学家称，强大的新AI模型将以前所未有的细节绘制月球表面 - Live Science

人工智能担忧 - fox29.com