Skip to content

#Agent

16 today

Oct 29Thursday

Hacker News front page

Google's Gemini 4 Carbon tops Artificial Analysis Intelligence Index v5

Google's Gemini 4 Carbon scored 59 on the Artificial Analysis Intelligence Index v5, taking first place. It ranked second on the coding agent index. Artificial Analysis compared it with similar models and found its cost per task lower than Claude Opus 5.5.

Why it matters: The benchmark puts Gemini 4 Carbon first on general intelligence and cheaper per task than Claude Opus 5.5.

Hacker News front page

I Used AI to Fake a Scientific Paper. Here's What Happened

Benjamin Skuse 经 IEEE Access 同意,分别用免费大语言模型和自动化科研系统 FARS 生成论文,两轮测试均未通过期刊检查。第一轮论文由 ChatGPT 和 Gemini 生成,STM Integrity Hub 检出 12 条虚构引用,MolecularConnections 无法验证其中 24 条引用。

MIT Technology Review · AI

We urgently need to monitor AI agents’ actions in real time

AI 智能体需要实时行动监控,但两位作者对四个广泛使用的智能体框架开展的研究发现,现有框架缺少支撑安全监督的关键记录。缺口包括持续有效的智能体身份标识、人类批准与干预记录,以及权限和记忆变更记录,妨碍识别未经授权的行动。作者主张通过 OpenTelemetry 等基础设施补足行动记录,同时指出,用于记录决策过程的 CoT 是否忠实反映模型决策、决策置信度能否可靠衡量,仍是开放研究问题。

Hacker News front page

Bernstein – open-source governance layer for AI agents

Bernstein 是开源 AI 智能体治理层,v3.23.0 提供 53 个 CLI 适配器,采用 Apache 2.0 许可。它通过不含模型的确定性 Python 调度器并行运行智能体,按分解、隔离执行、验证、合并四阶段处理任务,仅合并通过验证的代码差异。

Hacker News front page

Claude Code sends full background agent transcripts to the model every 30 seconds for status summaries

Claude Code sends each background agent's full transcript to its model roughly every 30 seconds, asking for a 3–5 word status summary. Telemetry from Flamerix AI shows these requests made up 16.4% of a week's estimated cost. Subscribers spend rate-limit quota on them, not billed dollars.

Why it matters: Flamerix AI used telemetry to pin down Claude Code's background summary overhead and a timer hook to turn those requests off, a reusable way to find hidden model calls.

Computing Life · Share · Yage

Anthropic 和 OpenAI 的外围防线如何被第三方软件与旧授权攻陷

Anthropic 与 OpenAI 的安全测试暴露了外围软件风险,第三方应用集成与旧授权让研究人员得以访问内部数据或代码仓库。Cathedral 的智能体在不到 12 小时内通过第三方软件漏洞读取 Anthropic 部分内部资料;Hacktron 研究人员则从 OpenAI 论坛漏洞经统一登录与 Codex 的 GitHub 授权进入核心代码仓库。

MIT Technology Review · AI

Creating AI value with enterprise context

MIT Technology Review Insights 调查显示,尽管所有受访企业都在使用 AI,仅 16% 从部署中获得变革性价值,40% 只在特定任务或团队看到中等收益,23% 收益极小甚至没有。

TechCrunch · AI

Anthropic just launched tools to show companies what their AI spending is buying

Anthropic 周三推出一套企业报告工具,帮助客户了解 token 支出对应的团队产出、成本及工作流故障。报告结合内部分析和员工调查,支持按日期范围查看团队工作,并提供改进建议,相关数据默认不会用于模型训练。Anthropic 还推出团队共享预算,帮助企业管理 token 支出。

Latent Space

Why Agents Love Supabase

Supabase 通过简化本地开发、提供声明式数据库结构和近数据库计算,减少 AI 智能体构建与运行应用的后端配置工作。无需 Docker 的本地运行环境已进入 alpha,声明式结构让智能体在 Git 中读取和修改目标数据库状态,处于 private alpha 的 Supabase Compute 支持在数据库附近运行容器。

AI HOT · Products

Microsoft opens Copilot harness through Foundry for multi-model agent development

Microsoft has opened the Copilot harness through Microsoft Foundry, giving developers and enterprises a fully managed way to build multi-model agents. The runtime orchestration layer, built by GitHub's engineering team, supports 20+ frontier models, bring-your-own-key, MCP, agent skills and plugins, and routes each task to a suitable model.

Why it matters: The managed Copilot harness lets developers cut the upkeep of the agent runtime layer while keeping their choice of model.

Google Blog · Gemini

Google releases Gemini 4 Carbon, targeting cybersecurity and long-horizon agent tasks

Google announced Gemini 4 Carbon, with gains in cyber defense, coding and long-horizon agent tasks. In external evaluations run without safeguards enabled, it scored 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploiting them and 71.0% on CWE-bench for fixing them.

Why it matters: Google kept the previous generation's entry price for Gemini 4 Carbon and reports secure code generation succeeding more than 2x as often as before.

Google DeepMind

Google DeepMind releases Gemini 4 Carbon, boosting cybersecurity and long-horizon tasks

Google DeepMind announced Gemini 4 Carbon, focused on cyber defense, coding and long-horizon agent tasks. It opens this week to a limited set of cyber defenders.

Why it matters: Google DeepMind reports Carbon more than doubles Argon's success rate on internal secure code generation tests, while making fewer unsupported claims.

OpenAI News

The future of the firm

Hemanth Asirvatham 和 Elliott Mokski 提出 AI 进入企业组织架构的三种情景:成为员工下属、与人类并列的同事,或嵌入高管与员工之间的协调层。

Simon Willison

GitHub Octoverse 2026: merged pull requests triple to 220 million a month

GitHub released its Octoverse 2026 report at Universe. Merged pull requests tripled in under a year to 220 million a month, and commits more than tripled to 7.38 billion a month, with most of the growth in the second half of the year. New repositories doubled this year to 30.3 million a month.

Why it matters: The report spells out how GitHub uses LLMs to locate users and multilingual embedding models to classify industries, giving the repository activity numbers a concrete method behind them.

Hacker News front page

Converge (YC S23) Is Hiring a Founding Platform Engineer

Converge 正在纽约招聘首位平台工程师,负责为自动投放和扩展广告的 AI 智能体构建平台,薪资 $180K-$240K 加 0.3%-0.5% 股权。公司现有 13 人、3 名产品工程师,系统已处理 $6 billion 年收入规模、每月摄取 20 TB 数据、峰值 10,000 jobs/s。

AI HOT · Tips & opinions

How to keep coding with OpenRouter after Claude Code hits its usage limit

Once Claude Code hits its plan's usage cap, you can keep using Claude models through OpenRouter and pay per token, outside the five-hour and weekly windows. Spending is then bounded by your account balance and budget instead.

Why it matters: It sets up a separate shell function that routes Claude Code through per-token billing on OpenRouter, while keeping the original plan command for when the quota resets.

The Decoder

Google opens Android dev environment to third-party AI agents, launches new Gemini API

At this year's Android Dev Summit, Google introduced a BYOA feature for Android Studio Rabbit 2 and released a new API for connecting on-device agents and apps.

Why it matters: Google is letting third-party coding agents into Android Studio and opening app tool-call interfaces, so agents can use dev tools and app features directly.

OpenAI News

Legora is building the agentic operating system for legal work

Legora 正借助 OpenAI 模型和编码智能体构建法律工作的智能体操作系统,支持合同审查与尽职调查。其内部法律团队基于历史协议建立 NDA 审查规则,将相关审查占用的团队精力从约 20% 降至不足 1%。Legora 称,一家 Fortune 100 客户的合同周转时间缩短了 90%;其 Tabular Review 工作流能在几分钟内围绕多个问题分析数千份合同,再由律师审核和解释输出。

Computing Life · Share · Yage

对话状态该由谁托管:SGLang 押注推理引擎的设计取舍

SGLang 的统一交互运行时将推理引擎的基本单位从单次请求改为持续会话,以统一实时语音的轮次、打断和历史截断规则。分析指出,原生全双工更依赖引擎内的会话控制,级联架构主要获得接口与评测便利,前台语音加后台委派所需的异步任务能力尚未完成。状态常驻引擎会增加迁移成本,SGLang 目前不支持断线恢复,评估锁定风险还需检查会话接口的私有扩展及状态能否导出重建。

Hacker News front page

Dayjob: Tax – evaluating AI agents on 50 professional tax assignments

Surge AI 推出 DAYJOB: Tax,涵盖八类税务业务的 50 个任务环境,评测 AI 智能体完成专业税务工作的能力。以满足至少 95% 任务标准为通过条件,Claude Sonnet 5.5 的 pass@1 为 10.8%,Claude Fable 5.1 和 Claude Opus 5.5 分别为 9.6% 和 9.2%。

Oct 28Wednesday

Simon Willison

Simon Willison reviews four games, calls October the turning point for vibe game development

Simon Willison built four browser games himself and says October 2026 is the turning point for vibe game development. He credits Claude Opus 5.5's gains in 3D modeling, music generation and game design with letting him make games he actually enjoys playing.

Why it matters: Willison traces four games from chat prototype to coding agent, and the process still keeps human playtesting and gameplay fixes in the loop.

The Decoder

Cathedral says its AI agent breached Anthropic via third-party software; Anthropic disputes scope

In bug-bounty research, security startup Cathedral used an AI agent to get into Anthropic's internal systems through third-party business software. Cathedral says it found a path to meeting notes, salary data and Slack messages in under twelve hours. Anthropic confirms some sales, HR and IT systems were accessed, says Claude conversations, source code and model weights were not exposed, and closed the affected access on the day it found the intrusion.

Why it matters: An AI agent reached Anthropic's internal data through a third-party integration, showing how outside services widen the reach into company systems.

OpenAI News

Legora is building the agentic operating system for legal work

Legora 利用 OpenAI 模型和编码智能体构建法律工作平台,将 AI 接入合同审查、尽职调查及内部研发流程。其内部法务团队依据历史协议建立 NDA 审查规则,将相关审查占用的团队产能从约 20% 降至不足 1%,律师负责审阅和解释智能体输出。

AI HOT · Tips & opinions

Pydantic AI benchmark: code mode cuts long-task cost 58% and time 51%

Pydantic AI tested 8 models across 5,276 scored runs in an internal benchmark. Code mode cut long-task cost by 58%, time by 51%, and raised success rate by 16.0 percentage points.

Why it matters: The same tool set was run two ways, and code mode saves on long tasks while adding overhead on short ones.

Hacker News front page

Artificial Analysis Intelligence Index v5.0

Artificial Analysis 推出 Intelligence Index v5.0,由 9 项评测组成,覆盖知识工作、编程、科学、通用四类,各占 25% 权重。

Computing Life · Share · Yage

实时语音智能体架构解读:两个选择和一层委派

实时语音智能体可按组件拆分、轮次判断和后台委派,分为级联、轮次式、原生全双工、原生前台加委派四类架构。级联便于日志审查和组件替换,原生全双工侧重自然交互,GPT-Live 则将即时接话与后台复杂任务分开,应用负责函数执行、权限检查和用户确认。选型应从场景中不能牺牲的要求倒推,文中团队为手机语音助手选择原生前台加委派,为桌面本地指令入口选择级联。

Hacker News front page

Free daily JSON feed of Shanghai government subsidy notices

China Policy Data 上线上海政府补贴与政策公告的免费机器可读 JSON feed,每日刷新,覆盖 9 个官方来源约 150 条公告。每条记录含标题、官方链接、发布机构、截止日期、daysLeft、isOpen 状态及面向外资中小企业的 0-10 相关性评分,并提供开放项目的 titleEn 与 summaryEn 英文字段。

AI HOT · Industry

Axiom 智能体集群据称用 24 天完成有限单群分类定理的机器验证

Axiom 的 AI 智能体集群据称用 24 天完成有限单群分类定理(CFSG)的机器验证。材料称,该工作将跨越 500 多篇论文的 15,000 页证明转化为 3800 万行以上机器验证代码,并发现已发表记录中的 34 处严重出入。引用内容另称,该形式化证明可能是最大的开源项目之一,所附图表显示 Axiom CFSG 达 43.0M 行,约每 37 天翻倍。

Ars Technica · AI

"No human at the helm": Delaware plan would let AI agents run entire businesses

特拉华州拟允许 AI 智能体运营整家公司,美国众议员 James Comer 昨天致函州长,要求提供相关文件并质疑出资人的责任保护。草案拟设立为期 30 个月的监管沙盒,允许人工智能公司(AIC)从事银行业务以外的合法业务,由 AI 智能体管理经营。出资人通常不承担 AIC 行为所产生的责任,但欺诈、故意违法及明知或应知公司超出设立目的经营等情形存在例外。

TechCrunch · AI

Bank of America kindly asks that you don’t share your banking password with your AI assistant

美国银行向客户发送邮件,提醒他们不要向他人或外部服务分享银行用户名和密码,包括代其行动的 AI 工具或智能体。分享凭据可能导致未经客户知情的金融操作、账户被锁,或因 AI 助手的安全漏洞而泄露凭据。邮件强调,客户须对分享凭据后产生的账户活动负责;银行和支付机构仍在探索如何允许 AI 智能体访问账户及自主付款。

Hacker News front page

Hex Raises $100M

Hex 完成 $100 million 融资,估值为 $1.2B,由 PeakXV 和 137 Ventures 领投。公司同时推出从头重写的 Hex 4.0,以普通代码为基础,强调数据工作的上下文、控制与治理。重写旨在解决旧架构中智能体工具膨胀、外部智能体接入受限,以及计算引擎难以支持高速、高并发迭代工作流的问题。

OpenAI News

How Check Point accelerates vulnerability research with Daybreak

Check Point 借助 OpenAI Daybreak 将漏洞研究工作流从数小时压缩到数分钟,其分析师能更快把漏洞情报转化为客户防护。Daybreak 提供 OpenAI 前沿网络安全模型,可分析漏洞、推理攻击路径并识别代码与配置中的安全缺口。