AI 情报文章归档

Ars Technica 介绍了一种以自然语言提示设计蛋白质的工具 Pinal，它由 T2struct 将文本转为结构蓝图，再由 SAProt-T 生成氨基酸序列，训练数据包括 8 亿关键词-蛋白质对和 AlphaFold 预测结构。

有东西要来了。 首个 Krea 3 专家模型本周上线。 谁能猜到第一个专家是什么？👇

Google has announced Gemini 4 Argon, its next-generation frontier model, with a phased release that...

Latent Space 发布对 Anthropic 的 Katelyn Lesse 和 Angela Jiang 的访谈，介绍 Claude Platform 背后的工程实践，包括发布 Opus 5.5、把模型大脑与智能体执行环境分离、扩展 API 和构建可靠的托管智能体。

那种反复出现的说法——AI 公司谈论生存性风险是为了制造炒作、抬高股价——一直都很奇怪。 告诉人们你的产品可能会杀死所有人，事实上并不会促使人们采用它，也不会降低监管风险。

TestingCatalog 称 ChatGPT 现已可连接 iCloud 日历和邮件，支持网页桌面端和 iOS。作者称这是一项期待已久的功能，并附有视频。

Google’s current AI work points to two distinct, potentially important tracks: Project Genie, a...

Mecka，为物理 AI 提供数据层的公司，完成了由 Sequoia 领投的 6000 万美元 B 轮融资，正在英雄联盟全球总决赛现场招人。 有意思的视频，告诉我们他们想要的人才实际上把时间花在哪里。

Codex 发布 0.165.0，新增内置 Google Cloud Vertex AI 提供商（model_provider = "gcp"），并将 GPT-6.1 Terra 加入模型目录。该版本默认对新配置启用 memory v2 并支持导入外部智能体记忆，同时默认允许在对话中调整推理强度。会话选择器新增仓库过滤，agent 命令中心支持按目录分组。

Baseten 宣布 Bryan Vann、Ilina Mitra、Jaikumar Ganesh 和 Rahmi Marasli 四位工程负责人加入。

Every repository has a graveyard. A Día de los Muertos altar and séances for your deleted files, written by Gemma 3 running locally.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the...

Nathan Lambert 认为，组织架构与团队功能对构建优秀 LLM 的重要性被严重低估，这也是 Llama、xAI 等团队反复重建、而落后团队仍能追赶的原因。他表示，高效的组织和团队价值相当于数倍算力。他还认为构建模型并无太多秘密配方，大部分收益来自持续一致的执行和对算力的明智使用。

每个语音智能体都得在电视声、狗叫声或大奖赛看台的嘈杂中听清客户说话。 我们想试试更吵的环境，于是借用了 @audif1_ 的风洞。 抱歉吵到你了，@HulkHulkenberg。

Databricks 博文讲解如何在 ai_extract 文档抽取中把一次性修补变成可评测的工程流程。实践来自一个从数十种 PDF 订单文档抽取约 40 个结构化字段的项目，结合人工审核作为 ground truth。

Databricks Lakehouse Federation 支持通过标准 SQL 直接查询 SQL Server、PostgreSQL、MySQL、Snowflake 等外部数据库，数据留在原处，无需复制或同步。

Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal s…

Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot demonstrations. Human videos provide much broade…

Test-time adaptation helps a deployed model respond to changing inputs, but the same intervention can rescue one batch and damage the next. Updating normalization statistics, for example, can improve corrupted images yet fail when a batch …

We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should redistribute attention between trusted and untr…

Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father's mother is not a mother's father; verifying a composed relation mea…

Atmospheric chemical mechanisms are commonly distributed in the language of the Kinetic PreProcessor (KPP), which generates efficient Fortran or C code but does not fit into the differentiable programming frameworks in which machine-learni…

Dexterous manipulation with multi-fingered hands is the next frontier of robotics, yet learned hand skills remain limited to simple grasps or basic repeated motions, such as rotating an object. As robots attempt more demanding in-hand mane…

Large Language Models (LLMs) are increasingly used in multi-turn agentic workloads that require sustained interaction with complex environments. Existing reflective prompt optimizers such as GEPA learn from failed rollouts, but agentic fai…

Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavior, such as heavier objects falling more…

We explore how to build performant large language model (LLM) tool-use agents that complete complex, multi-step tasks. Specifically, we study how data composition in synthetically generated tool-use environments affects the training of suc…

Weight decay and explicit weight-norm constraints improve optimizer performance in language model pretraining, yet a unified understanding of why such control helps and how much is needed remains incomplete. We analyze norm control in Muon…

Self-attention plays a key role in long-sequence modeling, but its quadratic time complexity fundamentally limits the scaling of Large Language Models. Recently, Multi-State Linear Attention (MSLA) mechanisms have been proposed to make seq…

Diffusion language models offer a promising path to efficient agents through parallel token generation. However, efficient interaction requires adapting both where computation is spent and how much text is generated. We introduce a metacog…

Claude Code on a subscription has two limits: a 5-hour session and a weekly cap. The session one is...

Language models pretrained on web corpora collected over multiple years learn both general and domain-specific knowledge. How these different kinds of knowledge are learned as pretraining progresses remains unclear. Recent point-in-time mo…

A documentation skill sounds like a low-risk addition to an AI agent. It reads code, proposes an...

ChatGPT 官方宣布 iCloud Mail 和 Calendar 插件现已可用，用户可让 ChatGPT 查找邮件、处理收件箱、查看日程或更新日历事件。该功能支持所有 ChatGPT 套餐，覆盖网页端、桌面端和 iOS。

Liquid AI 发布新一代开源权重模型家族 LFM3，1.7B 文本模型表现超越其前代 2.6B 模型。性能提升来自 tri-hybrid 架构，24 层中 13 层为短卷积、5 层用 256-token 滑窗注意力、6 层全局注意力；官方称 LFM3-VL-2B 可与参数量大 6 倍的 Gemma 4 12B 竞争，作者引用的数据称 1.7B 模型在 AutomationBench 得分 41.29，高于 Qwen3.5-9B 的 15.10。

When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the decision criteria. On hidden-profile task…

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine. ...

Alphabet, Broadcom and SpaceX each report a big deal with a company they don't name. Read against Anthropic's S-1, the terms match.

看到驻外士兵通过 Beam 与孩子共享温馨时刻，令人感动。非常感谢 @USArmy @The_USO 促成此事。

Arena 宣布 Agent Mode 现已支持 Connectors，用户可在单个任务中接入 Vercel、Linear、GitHub、Supabase、Notion、Gmail、Google Drive、Google Calendar 等真实工具，端到端完成更复杂的实际任务。首批服务来自社区构建者最常请求的清单，后续将持续扩充。

I built SECOND STRIKE, a real-time world war on a 3D globe of the real Earth, where AI models and...