LexaAI

406 posts

LexaAI

LexaAI

@ilexax

ML | DL | AI Coding

Katılım Eylül 2020
1K Takip Edilen54 Takipçiler
Tibo
Tibo@thsottiaux·
tok tok goes the token silicon dreams wake in sand machines ask why now
English
86
12
624
37.1K
Barret李靖
Barret李靖@Barret_China·
团队将 Claude Code 源码放进了 WebAssembly 运行环境,将 Node.js 和 Python 环境也打包了进去,现在可以愉快地在网页上直接使用 Claude Code 了😄 基于 Claude Code 源码做了四层工作,包括:1)浏览器宿主,让网页中具备 Claude Code 的终端界面、会话状态和交互体验;2)WebContainer/WASI 运行时,实现在浏览器里提供类本地的隔离执行环境,真正跑起 Node.js、Shell 和 Python;3)Node 兼容层,为文件系统、进程、模块加载等补齐浏览器侧适配;4)HostBridge,在网页宿主与运行时之间桥接搜索、抓取、代理、文件同步等外部能力。整体工作量还是蛮大的。
Barret李靖 tweet media
中文
41
32
327
49.8K
ClaudeDevs
ClaudeDevs@ClaudeDevs·
Happy Friday! We've reset everyone's 5-hour and weekly rate limits.
English
1.6K
1.3K
30.6K
1.9M
Tibo
Tibo@thsottiaux·
Confirmed stable and recovered
English
160
19
911
92.7K
Tibo
Tibo@thsottiaux·
We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours. We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening. Apologies and now is the time for /fast maxxing.
Tibo@thsottiaux

Codex team is aware of reports of GPT-5.5 performing worse for some users and investigating. We don't have anything conclusive yet and systems are healthy but we will share updates as we go.

English
817
508
7.6K
1.7M
LexaAI
LexaAI@ilexax·
@sama Thanks for the update and for moving quickly here — genuinely appreciate the transparency. The contrast with Anthropic’s handling a few days ago is… educational. It turns out acknowledging an issue, explaining what was found, fixing it, monitoring the recovery.
English
0
0
0
11
LexaAI
LexaAI@ilexax·
@thsottiaux Thanks for the update and for fixing this quickly. Glad to hear the likely causes were identified. I’ll keep an eye on performance over the next few hours as well. Appreciate the usage limit reset — time to make the most of /fast.
English
0
0
0
96
Claude Code Changelog
Claude Code Changelog@ClaudeCodeLog·
Claude Code 2.1.142 has been released. 24 CLI changes Highlights: • New 'claude agents' flags configure dirs, permissions, model, effort and plugin/MCP settings for finer control • grep now uses ripgrep as the default search tool for faster, more accurate results • Background daemon detects clock jumps after macOS sleep/wake, preventing session loss and reconnect failures Complete details in thread ↓
English
26
35
476
48.4K
宝玉
宝玉@dotey·
OpenAI 把 Codex 搬进了 ChatGPT 手机 App,今天在 iOS 和安卓上同步开启 preview,所有 ChatGPT 用户都能用,包括免费版和最低价的 Go 套餐。 手机端不是让你在手机上写代码。真正干活的 Codex 还是跑在你的笔记本、Mac mini 或者 devbox 上,手机只是一个远程窗口:地铁上能看 Codex 跑到哪一步、审一眼它改的 diff 和跑的测试结果、批准下一步操作,或者临时换个方向走。文件、凭证、权限都留在原来那台机器上,不上传到手机。 OpenAI 的解释是底层走了一层 secure relay 中继,让跑着 Codex 的机器能跨设备保持可达,又不直接暴露在公网上。你在哪台设备登录 ChatGPT,会话状态和上下文就跟到哪里。 为什么现在做。OpenAI 自己公布的数字是 Codex 每周活跃用户已经过 400 万。当 agent 越来越多地跑长任务,几十分钟甚至几小时的那种,人坐在电脑前盯着就很傻,你需要随手能看一眼、能拍板的能力。 一个明显限制:手机端目前只能连 macOS 上的 Codex,Windows 支持据说”很快”。 另一层意思是,OpenAI 没给 Codex 单独做手机 App,而是塞进 ChatGPT 主 App。这跟他们之前透露过的”超级 App”路线一致,把 ChatGPT、Codex、Atlas 浏览器整合成一个入口。桌面端是独立的 Codex App,手机端直接合并进 ChatGPT。 参照系是 Anthropic。Claude Code 从去年秋天起就支持手机远程查看和介入正在跑的任务,后面的 Cowork 配套移动端走的也是类似 dispatch 思路。Codex 这次把覆盖范围扩到了 devbox 和远程企业环境(支持 remote SSH 接入),算是追平加扩张。
OpenAI@OpenAI

You've been asking for this one... Now in preview: Codex in the ChatGPT mobile app. Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.

中文
78
33
301
142.4K
LexaAI
LexaAI@ilexax·
@Mnilax Can I use it for my Codex(Agents.md)
English
0
0
0
132
Can Vardar
Can Vardar@icanvardar·
gpt 5.5 is actually insanely fast
English
26
5
256
12.5K
LexaAI
LexaAI@ilexax·
@gdb A strong /goal should include: 1. The desired outcome 2. Relevant context 3. Constraints and things not to change 4. Completion criteria 5. Verification steps When Codex should pause and ask for direction What summary you expect at the end
English
0
0
0
36
LexaAI
LexaAI@ilexax·
@gdb Can document provide some best examples of '/goal' command
English
0
0
1
178
Tibo
Tibo@thsottiaux·
We are Codex. We are legion. We do not miss. We do ship. Expect us. DM me if you have a track record of solving near impossible problems and want to work on the future of computing. We work across research, infra, agent harness and products. Currently hiring in San Francisco only.
English
307
102
3.8K
530.9K
LexaAI
LexaAI@ilexax·
codex 命令速查
LexaAI tweet media
中文
0
0
0
13
LexaAI
LexaAI@ilexax·
@thorstenball The real 2026 agent stack: Agent does the task. Agent audits the agent. Agent writes the postmortem. Human gets paged anyway.
English
0
0
0
64
Thorsten Ball
Thorsten Ball@thorstenball·
Smoking Gun, Belt & Suspenders: The Year 2026 With Agents A Memoir
English
6
1
40
7K