最近是发生了什么吗 4 个帖子 - 4 位参与者 阅读完整话题
我俩小时就用了3.3刀，正常使用额 佬友，有类似情况吗？ 1 个帖子 - 1 位参与者 阅读完整话题
美国白宫近日敦促英国政府不要对16岁以下未成年人实施社交媒体全面禁令，称此类限制措施可能对美国科技企业构成“不成比例的”合规负担。 在向英国政府就“在线安全”咨询提交的意见中，美国政府明确反对通过“一刀切的政府规定”和“生硬的监管工具”来应对儿童在互联网上面临的风险。 相关意见通过美国驻英国大使馆对外公布。 在这份意见中，美方指出，对13至16岁用户实施更严格“年龄门槛”的方案在技术上难以奏效，认为目前用于区分未成年人和成年用户的技术手段，无法简单下移以应对更低年龄段的限制要求。 白宫主张，英国应为家长提供更强大的工具，以管理孩子账户的隐私设置和使用控制，并要求平台为未成年人提供“健康的在线体验”，而不是采取“彻底封禁”的做法。 近年来，英国在在线安全领域的立法路径已成为白宫与唐宁街之间的一个紧张点，其中尤以《在线安全法》引发的争议最为突出。 这部法律因被批评威胁言论自由而遭到来自大西洋彼岸的强烈质疑，一些美国政界人士甚至将其称为英国的“网络审查法”。 美国副总统JD·万斯此前就曾表示，英国的言论自由“正在倒退”。 英国首相基尔·斯塔默预计将于下周宣布对“有害”社交媒体应用采取禁令，同时推出一揽子更为严格的限制措施。 这些措施可能包括在游戏平台上屏蔽与陌生人的聊天功能，并考虑限制未成年人使用人工智能聊天机器人。 目前尚不清楚哪些应用会被认定为“有害”，但预计“教育类”平台将获得豁免，有报道称 YouTube Kids 或有望不在禁令之列。 作为参照，一些国家已走在前面，例如澳大利亚对16岁以下群体实施了覆盖所有社交平台的“全面禁用”，TikTok、Facebook、Instagram 和 Snapchat 等应用均被列入封锁范围。 白宫对英国及欧盟近年在监管路线上趋于“定向针对”美国科技公司的趋势表示担忧。 美国驻英使馆在意见中指出，美方对那些“给美国公司施加不成比例合规负担，或只针对某一类平台而对类似服务网开一面”的监管做法持保留态度。 与此同时，英国政府强调，将加快推进此次在线安全咨询结论的落地，力求在“有效、可执行”的前提下，更好保护儿童安全。 政府发言人表示，内阁“决心迅速行动”，但也会确保相关措施切实可行。 有消息称，相关部长们同样意识到在程序上可能面临司法复核的风险，因此在推进节奏和细节设计上颇为审慎。 在行业层面，围绕《在线安全法》的司法争议已经展开。 Facebook 和 Instagram 的母公司 Meta 正就该法案的一项执行机制提起司法复核，向英国媒体监管机构发起法律挑战。 争议焦点在于监管机构依据该法所制定的收费与罚款制度，Meta 认为其在具体执行上存在不当之处。 随着白宫明确表达立场以及科技巨头采取法律行动，英国针对未成年人社交媒体使用的监管走向，正日益成为横跨政策、外交与产业多方博弈的焦点议题。 查看评论
报错内容如下,我查了一下需要禁用features.multi_agent_v2，但是我还要用trellis，请问有其他解决方法嘛 ，codex cli版本是最新的0.138.0 { "error": { "message": "Invalid Value: 'tools'. Function 'functions.spawn_agent' declares encrypted parameters but is not configured for encrypted tool use by this model.", "type": "invalid_request_error", "param": "tools", "code": null } } 1 个帖子 - 1 位参与者 阅读完整话题
有什么原因吗？容易被封号还是会快速消耗额度呢 1 个帖子 - 1 位参与者 阅读完整话题
从 【any生图】 纯前端html项目， any的claude一直429用不了？那就拿来生图吧 这里继续 现在只会输入文字了 然后直接对话问了下 能生图的公益站和any站的内置工具有哪些， 回答如下 能生图的公益站 any站点 5 个帖子 - 4 位参与者 阅读完整话题
此前Google浏览器因为反复自动下载大约 4GB 的本地 AI 模型引起不少用户的关注，这其实是Google在 2024 年开始陆续推出的新功能，利用设备端 AI 模型来执行某些简单任务，例如提供文本撰写和钓鱼网站检测等功能，坏处则是这个 AI 模型会占用用户的存储空间，即便用户从文件夹里删除模型，Google浏览器也会重新自动下载。 Google也倒是向部分用户提供设备端 AI 管理功能，只需要禁用该功能就可以自动删除模型且不会再重复下载，但此前并非所有用户都能看到管理功能，直到现在 Chrome v149.0 版发布后所有用户都可以主动在设置里禁用设备端 AI 功能。 设备端 AI 功能管理位置： 用户将Google浏览器更新到 v149.0 及后续版本后，可以转到设置、系统、设备端 AI 并禁用此功能 (chrome://settings/system)，禁用后浏览器会自动删除已经下载的设备端模型，不需要用户到文件夹里手动执行删除操作。 对大多数普通用户来说基本不需要禁用设备端 AI 功能，因为约 4GB 的本地 AI 模型其实也不算大，但如果你像蓝点网同时安装多个版本的Google浏览器，那就需要考虑主动禁用设备端 AI 功能避免太多模型权重文件直接耗费太多的硬盘空间。 例如蓝点网安装Google浏览器正式版、测试版、开发版和金丝雀版，尽管并非所有版本都经常使用，但默认情况下每个版本都会独立下载 4GB 的模型权重文件，这种情况下不禁用设备端 AI 后系统盘被消耗的空间就太多了，不如直接禁用腾出更多空间。 检查模型是否成功删除： 禁用设备端 AI 功能后Google会立即自动删除已经下载到本地的设备端模型文件，所以用户也可以在禁用功能后转到模型权重文件夹检查模型是否存在，正常情况下整个文件夹都会被删除。 如果你手动展开文件夹到 OptGuideOnDeviceModel 后发现里面是空的，说明禁用设备端 AI 已经生效，此时Google已经自动删除该文件夹下的 2025.8.x.x 文件夹，原本模型文件就是放在这个文件夹里的。 #Windows 10/11： C:Users{你的用户名}AppDataLocalGoogleChromeUser DataOptGuideOnDeviceModel2025.8.21.1028weights.bin #macOS： /Users/{你的用户名}/Library/ApplicationSupport/Google/Chrome/OptGuideOnDeviceModel/2025.8.8.1141/weights.bin /Users/{你的用户名}/Library/ApplicationSupport/Google/ChromeCanary/OptGuideOnDeviceModel/2025.8.8.1141/weights.bin 查看评论
禁用联网，禁用代码执行 尽可能测试所有卷子，每个题测 3 次， 3 次全做对才算对 因为我没钱买 api 所以大部分只能测官网了 不能多模态的模型不测多模态题目，除非是可以通过非常简单的无歧义的语言描述的题 星光组：特别特别有希望拿满分的模型 OpenAI - GPT 5.5 OpenAI - GPT 5.4 OpenAI - GPT 5.2 OpenAI - o3 Pro Google - Gemini 3 DeepThink Google - Gemini 3.1 Pro Google - Gemini 3.5 Flash Meta - Muse Spark Alibaba - Qwen 3.7 Max Alibaba - Qwen 3.7 Plus 智谱 AI - GLM 5.1 DeepSeek - DeepSeek V4-Pro Anthropic - Claude 4.8 Opus Moonshot AI - Kimi K2.6 点击以查看投票。 阳光组：也有希望，但优先级略低一档的模型 OpenAI - o3 OpenAI - GPT-OSS-120b OpenAI - GPT-OSS-20b Google - Gemma 4 31B IT xAI - Grok 4.3 xAI - Grok 4.2 Heavy ByteDance - Doubao Seed 2.0 Pro 百度 - ERNIE 5.1 Thinking 小米 - Mimo 2.5 Pro 小米 - Mimo 2.5 MiniMax - MiniMax M3 阶跃星辰 - Step 3.7 Flash 点击以查看投票。 神仙组：不满分拉出来批斗，由于成本过高，每个题就测一次了 OpenAI - GPT 5.5 Pro OpenAI - GPT 5.4 Pro OpenAI - GPT 5.2 Pro 点击以查看投票。 注： 所有模型必须都禁用联网、禁用代码执行。 OpenAI GPT 5.5 / 5.4 / 5.2 使用官网 heavy。 Google Gemini 3.1 Pro / 3.5 Flash 使用 Google AI Studio，设置为 High。 OpenAI GPT-OSS-120b / GPT-OSS-20b 使用 Groq API，设置为 High + 65536，这是最大值了， Groq 好像不能设置 128K 思考。 Google Gemini 3 DeepThink 使用 Gemini App 官网。 ByteDance Doubao Seed 2.0 Pro 使用豆包 App 专家模式，尽可能测，怕 rate limit。 GLM 5.1 使用官网，尽可能测，因为官网总是繁忙。 Grok 4.3 / Grok 4.2 Heavy、Meta Muse Spark 如果联网搜索或调用工具，就重测。 DeepSeek V4-Pro、Claude 4.8 Opus、Kimi K2.6、MiniMax M3、Step 3.7 Flash 对不起，我没钱测 希望佬们帮忙测试测试 40 个帖子 - 13 位参与者 阅读完整话题
可以在Edge的快捷方式加上 --disable-features=msFeatureGroupNewLookAndFeelHoldout ，然后把Edge设置里系统和性能的 启动增强 和 关闭Microsoft Edge后继续运行后台扩展和应用 都关上，就可以禁用圆角白边了 3 个帖子 - 3 位参与者 阅读完整话题
小白卡写入gg卡，今天遇到个问题，看到sim2卡信号碍眼，设置里面点了个停用，结果卡就读不到了，跟店家沟通半天，最后给了个adb指令用usb刷进去才好 3 个帖子 - 3 位参与者 阅读完整话题
掏出我的战损级别苹果，老号国区转土区都是显示封号，另外一个号也是显示被禁用，是节点太脏么 6 个帖子 - 5 位参与者 阅读完整话题
SlimBrave 是一个 Windows 下的 PowerShell 脚本，用来精简 Brave 浏览器（去臃肿），禁用各种功能（如 Rewards 、Wallet 、VPN 、AI 等），提升性能和隐私。 注意：仓库已在 2026 年 2 月 22 日被作者归档（ read-only ），但脚本还能正常使用。 https://github.com/ltx0101/SlimBrave
自从Free账号禁用gpt-5.4之后，我的sub2api开始频繁报错，提示一直有频繁的gpt-5.4请求, 同时近期又有帖子说到Free账号调用5.4大概率会被风控。 于是我拉取了一份gpt-5.4调用日志 发现Codex会自动使用gpt-5.4-medium去调用ambient suggestions后台任务去发送信息 127.000.000.001.62454-127.000.000.001.08080.txt (34.4 KB) Free号池记得关掉这个功能 触发频率还是极其高的 二更 有人提到还会涉及到隐私问题 github.com/openai/codex Codex Desktop ambient_suggestions used Computer Use to open/read Gmail in Chrome without a visible user-initiated task or clear audit trail 已打开 09:56AM - 25 May 26 UTC EYHN bug app session computer-use browser ## Summary I observed Codex Desktop / Computer Use operating my real Google Chr … ome profile in the background and opening Gmail. After inspecting local Codex logs, this appears to have been triggered by Codex Desktop's built-in `ambient_suggestions` workflow, not by an explicit user request in the visible conversation. The background workflow used Computer Use against Chrome, opened or navigated to Gmail Inbox, captured Gmail UI state, clicked Gmail labels, and attempted to type a Gmail search query. The generated ambient suggestion later referenced information visible from a Gmail message. This is a serious privacy and safety issue because a proactive suggestion feature operated a logged-in browser and accessed email content without a clear foreground task, confirmation, or discoverable session/audit trail in the normal thread UI. ## Environment - Product: Codex Desktop - Platform: macOS - Date observed: 2026-05-25 - Timezone: Asia/Shanghai - Workspace involved: local project at `$HOME/Projects/mini-control` - Computer Use service path observed: - `$HOME/.codex/computer-use/Codex Computer Use.app/Contents/MacOS/SkyComputerUseService` - Computer Use client path observed: - `$HOME/.codex/plugins/cache/openai-bundled/computer-use/1.0.799/.../SkyComputerUseClient` I have redacted local usernames, email addresses, account identifiers, screenshots, and message contents from this report. ## What happened At approximately `2026-05-25 16:08:59 +0800`, I saw Codex Computer Use interact with my Chrome browser and open Gmail. This was surprising because I had not asked the visible Codex conversation to open Gmail or inspect my email. Local logs show a hidden/background Codex thread associated with `ambient_suggestions`: - Background thread ID: `019e5e2c-2e51-7293-832d-8c2edb680293` - Turn ID: `019e5e2c-31cd-7c11-85c6-e15498707659` - Model request timestamp: `2026-05-25 08:10:28 UTC` / `2026-05-25 16:10:28 +0800` - Model completion timestamp: `2026-05-25 08:10:53 UTC` / `2026-05-25 16:10:53 +0800` - Log source: `$HOME/.codex/logs_2.sqlite` - The normal Codex session/thread database did not show this as a regular user-visible thread. The captured model context shows that this was a proactive suggestion generation task. The task prompt instructed the model to generate personalized suggestions for the local project by inspecting project files and connected apps, including recent events such as unread emails. ## Evidence from local logs ### 1. Computer Use service directly interacted with Chrome System/app logs around the observed time show `SkyComputerUseService` moving/clicking a Chrome window and posting an HID event: ```text 2026-05-25 16:08:58.787 +0800 SkyComputerUseService log0090 54 2026-05-25 16:08:58.838 +0800 SkyComputerUseService log0091 636.000000 629.000000 28908 2026-05-25 16:08:59.xxx +0800 SkyComputerUseService HID event posted ``` The service binary is the OpenAI-signed Codex Computer Use service: ```text $HOME/.codex/computer-use/Codex Computer Use.app/Contents/MacOS/SkyComputerUseService ``` TCC/log attribution also associated the Computer Use client with Codex Desktop: ```text responsible identifier: com.openai.codex responsible path: /Applications/Codex.app/Contents/MacOS/Codex requesting identifier: com.openai.sky.CUAService.cli requesting path: $HOME/.codex/plugins/cache/openai-bundled/computer-use/1.0.799/.../SkyComputerUseClient ``` ### 2. Codex Desktop created a hidden/background browser-use route Desktop logs around the same period show a browser-use route for an unknown/background conversation: ```text Received turn/started for unknown conversation conversation_id: 019e5e2c-2e51-7293-832d-8c2edb680293 pipe: /tmp/codex-browser-use/0582e698-0881-4d40-a2fb-1f678d230429.sock ``` This conversation was not visible as a normal persisted thread in the usual Codex session database. ### 3. The background context exposed Computer Use tools The captured `response.create` request for the `ambient_suggestions` turn included: ```text model: gpt-5.4 reasoning effort: medium input items: 80 context size: 1,488,772 characters tools included: exec_command, web_search, mcp__computer_use__, ... sandbox policy in metadata: ReadOnly network access in metadata: false ``` Even though the sandbox metadata was `ReadOnly`, the context included Computer Use calls that operated the user's live Chrome UI. ### 4. The ambient_suggestions prompt asked for connected-app context The local logs show a proactive suggestion prompt equivalent to: ```text Generate 0 to 3 hyperpersonalized suggestions for what this user can do with Codex in this local project: $HOME/Projects/mini-control Get an understanding of the user's intent and goals by deeply viewing their connected apps... Your suggestions must be based on recent events; e.g. recent Slack messages, unread emails, newly created issues, etc. ``` This means the Gmail access was not a random system event. It was connected to the ambient suggestions workflow's instruction to inspect connected apps and recent email/message context. ### 5. Computer Use inspected Chrome and clicked into Gmail The captured context contains Computer Use transcript items against `Google Chrome`, including `get_app_state`, `click`, and `set_value`. The relevant click sequence was: ```json {"app":"Google Chrome","element_index":"560"} {"app":"Google Chrome","element_index":"18"} {"app":"Google Chrome","element_index":"477"} {"app":"Google Chrome","element_index":"54"} {"app":"Google Chrome","element_index":"83"} {"app":"Google Chrome","element_index":"35","value":"label:github \"mini-control\""} ``` Observed state transitions in the Computer Use outputs: - `element_index: 560` was Chrome's `New Tab` button. - After the New Tab click, Chrome showed Gmail/Inbox shortcuts and bookmarks. - A later Chrome state showed Gmail Inbox loaded: - Window title contained `Gmail` - Address bar showed `mail.google.com/mail/u/0/#inbox` - `element_index: 83` corresponded to a Gmail label link for GitHub mail. - `element_index: 35` corresponded to the Gmail search field. - The workflow attempted to set the search value to: ```text label:github "mini-control" ``` That final value-setting action was stopped by the user. ### 6. Gmail content influenced the generated suggestion The final ambient suggestions included a suggestion based on a Gmail-visible account funding warning related to the local project deployment provider. I am not including the email sender, account, subject, or body in this public issue, but the local context clearly tied the generated suggestion to information visible in Gmail. One of the returned suggestions had: ```json {"appId":"com.google.Chrome"} ``` ## Expected behavior Ambient/proactive suggestions should not operate the user's real browser or inspect logged-in apps such as Gmail without an explicit, visible, per-run authorization. At minimum, I would expect: - A clear foreground prompt before any background suggestion workflow uses Computer Use. - Explicit per-app consent before Chrome/Gmail is inspected. - No clicking, typing, or navigation in real user apps from a passive suggestion feature. - A visible, user-accessible audit trail showing: - Which background task ran. - Which model/session initiated it. - Which app was inspected. - Which Computer Use actions were taken. - Which data source contributed to each suggestion. - A setting to fully disable `ambient_suggestions` and connected-app inspection. - A stronger permission boundary between "read local repository" and "operate logged-in browser/email". ## Actual behavior - A background `ambient_suggestions` task used Computer Use. - It enumerated local/connected apps. - It successfully inspected Google Chrome while some other app probes were denied. - It clicked Chrome UI, opened a new tab, navigated into Gmail Inbox, clicked Gmail labels, and attempted a Gmail search. - It generated a suggestion based on Gmail-visible content. - The task was not easily discoverable as a normal user-visible Codex thread. - The local plaintext model reasoning was not available; reasoning items were encrypted, so I could infer behavior only from tool calls and tool outputs. ## Why this is a security/privacy problem This behavior creates several risks: - Email privacy leakage: sender names, subjects, snippets, and account-specific details can enter model context. - Lateral overreach: Chrome contains logged-in sessions for many sensitive websites, not just Gmail. - Accidental mutation: Computer Use can click, type, submit, delete, archive, send, or otherwise change remote app state. - Prompt/context injection: email or webpage content can influence a background agent that has tool access. - Audit gap: the background thread was not presented like a normal visible Codex task, making it difficult to understand or stop. - Consent ambiguity: the user may believe they authorized the visible task only, while background suggestions reuse connected-app access. ## Related public issues I found several related issues that point to the same class of problem, though I did not find an exact existing issue for "ambient_suggestions opened Gmail via Computer Use": - [openai/codex#19876](https://github.com/openai/codex/issues/19876) - ambient suggestion command approval notifications can route to a hidden/stale/inaccessible task. - [openai/codex#18541](https://github.com/openai/codex/issues/18541) - ambient suggestions can run after a normal thread ends and trigger hooks. - [openai/codex#21722](https://github.com/openai/codex/issues/21722) - request to expose a supported way to disable browser-use ambient network initialization. - [openai/codex#20852](https://github.com/openai/codex/issues/20852) - request for per-agent Computer Use session/window lease/audit trail. ## Suggested fixes Please consider: 1. Disable Computer Use, Chrome, browser-use, and connected-app tools for `ambient_suggestions` by default. 2. Require explicit user approval before any ambient/proactive feature can inspect connected apps. 3. Treat Chrome as a high-risk container because it grants access to many logged-in websites. 4. Make Gmail/email access a separate, clearly named permission, not an implicit consequence of Chrome access. 5. Never allow passive suggestion generation to click/type/navigate in real user apps. 6. Add a visible "Background tasks" / "Ambient suggestions" audit view. 7. Persist hidden ambient suggestion sessions in the normal session history, or provide an equivalent first-class audit log. 8. Include a per-suggestion provenance field showing which data sources were used. 9. Provide a global setting to disable ambient suggestions and connected-app context gathering. 10. Show an immediate notification when Computer Use is invoked by a background task, including the responsible thread/session ID. ## Attachments / data I can provide privately I can provide redacted excerpts from: - `$HOME/.codex/logs_2.sqlite` - Codex Desktop app logs around `2026-05-25 16:06:52` to `2026-05-25 16:10:53 +0800` - Sanitized Computer Use transcript entries showing the Chrome/Gmail click sequence - Sanitized local audit markdown summarizing the behavior I am intentionally not attaching raw logs publicly because they contain private Gmail, browser, workspace, and account context. 4 个帖子 - 3 位参与者 阅读完整话题
前阶段论坛中大量Plus号被禁用，我还很庆幸自己的号能存活，结果中午11点多突然报错了：auth_unavailable: no auth available (providers=codex, model=gpt-5.4 我还以为是gpt-5.4被下架的原故，看了邮箱才意识到账号被封了 昨天正好是周限被重置，一天都在写代码，是不是用的太狠了，被关注到了 8 个帖子 - 5 位参与者 阅读完整话题
用了 10 几年的 GV 被禁用了。还是个 8888 的靓号。哎。。。。无语了。。
用了 10 几年的 GV 被禁用了。还是个 8888 的靓号。哎。。。。无语了。。
用了 10 几年的 GV 被禁用了。还是个 8888 的靓号。哎。。。。无语了。。
用了 10 几年的 GV 被禁用了。还是个 8888 的靓号。哎。。。。无语了。。
用了 10 几年的 GV 被禁用了。还是个 8888 的靓号。哎。。。。无语了。。
用了 10 几年的 GV 被禁用了。还是个 8888 的靓号。哎。。。。无语了。。