https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase 少即是多? (正在试用 Pi update: 似乎相比 codex 没有明显的性能退化,但是完成任务的速度显著更快
Channel
Yifan's nonsense
@yifan_boardcast
On this record: Growth · Engagement · Reactions · Posts · Citations · Cite this entry
23subscribers
+1 since we began measuring on 8 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
Register entry
| Telegram ID | -1002184864008 |
|---|---|
| Type | Channel |
| Username | @yifan_boardcast |
| Created | 27 June 2024 — measured — dated from the channel’s first post |
| First recorded | 11 August 2026 |
| Last confirmed live | 18 September 2026 |
| Measurements held | 3 |
| Confirmed unchanged | 5 times, most recently 18 September 2026 |
| On Telegram | t.me/yifan_boardcast |
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 16 Aug 2026, 02:58 | 23 | +1 |
| 11 Aug 2026, 13:32 | 22 | no change |
| 8 Aug 2026, 09:00 | 22 | first reading |
Engagement
13 posts held, back to 27 June 2024 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 page of Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 13 posts for this entry, the most recent from 24 July 2026. An engagement rate over an empty window would be a number about nothing.
Reaction mix
4 reactions across 4 posts, in 3 distinct kinds. The most used accounts for 50.0% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 😁 | 2 | 50.0% | |
| 👍 | 1 | 25.0% | |
| 🤪 | 1 | 25.0% |
No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.
Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.
Coverage. Reactions were read on 4 of the 13 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 4 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 13 most recent posts we hold, published 27 June 2024 to 24 July 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
Recent posts
借鉴 zsh-kimi-cli 的思路,写了个小插件,在 zsh 中无缝切换 agent 模式(底层是codex),类似 warp 的体验。欢迎试用😆 https://github.com/gaoyifan/zsh-codex-mode
最近发现一个好用的 OpenSSH 替代品 tssh https://trzsz.github.io/tssh 它解决了长期以来困扰我的几个问题: 1. 在高延迟或高丢包的网络环境中,SSH 不稳定且交互延迟极高 2. 网络中断后,SSH 无法自动恢复 3. mosh 无法使用 tmux -CC 4. mosh 不支持 ssh-agent tssh 支持 UDP 模式(QUIC/KCP协议), 极大得缓解了高延迟或高丢包环境的性能问题,同时由于 UDP 的无状态性,能够实现类似 mosh 的网络漫游与透明的重连接能力。另外,tssh 是可靠数据流传输模型,兼容 tmux -CC。 也非常适合搭配 codex cli食用🙈
如果你回顾过去几百年的历史,会发现人类曾有几次意识到自己远没有原先想象的那么重要。 哥白尼让我们意识到地球不是宇宙中心;达尔文让我们明白人类也是动物;而现在,AI 让我们不得不接受:智慧并非生物体所独有,非生物体同样可以作为像我们一样的生命存在。 From https://www.youtube.com/watch?v=p7t1Q_p2gZs&t=1356s
Codex 有个机制,当 Quota 用尽时,它依然允许跑完最后一轮对话。 利用这一点,只要在配置里开启 [features] default_mode_request_user_input = true 并用 Prompt 诱导它不断调用该工具,就能把对话卡在同一个 turn_id 里无限套娃续航😂 因为调用工具并不算新的一轮对话,但 request_user_input 工具实质上提供了插入新 prompt 的能力 附送提示词: 总是在结束前调用 request_user_input 工具告知用户当前进展,接收用户的反馈。
🤪1
最近深度使用了一下 Codex(CLI), Cursor CLI, Github Copilot CLI, Antigravity CLI,做个小的总结: 终端交互体验: • GitHub Copilot CLI 全场最佳,打磨得相当完善(有点意外😂 • Codex CLI, Antigravity CLI 可用,但功能或提示有缺失,一些在UI上能实现的功能,CLI无法实现(比如 undo/redo/revert) • Cursor CLI 体验相当差,严重的性能问题,并且功能和提示相当不完备。如果不是还有 500次的 request-based plan,简直难以捏着鼻子用下去。 Agent 能力大家差不多,没有很显著的差距,值得注意的是: • Cursor CLI 的 Shell 似乎无法很好得实现交互式操作。导致模型会卡死在某些奇怪的地方(比如 apt install -y xxx 过程中弹出的交互提示) • Ant…
👍1
发现一个 LLM 对话式的 MBTI 评估,是个有趣的产品。感觉作者应该花了不少功夫打磨 prompt(挺准的😂 https://mbti.ax0x.ai
最近在用 Raycast AI,发现真的好方便呀。 可以捕获当前屏幕上选中的内容,可以捕获当前打开的浏览器页面全文,可以捕获剪贴板,可以自由定义触发的全局快捷键。 我实现了这么几个指令(快捷键),高频使用中: 1. 解释选中词语(文本)的含意 2. 总结当前网页 3. 总结视频。配合 MCP Subtitle,即便没有内嵌字幕,也能通过语音转录来提取 经过zzh的提醒,gemini 可以直接对YouTube视频进行多模态理解,且速度也更快,体验更好
腾讯 EdgeOne CDN 免费计划的兑换码,有需要的请自取(有效期7天) RQJ9L36AA46B 5PSQJZ9V42D4 MT0QJXFPU175 PT86VFRIOC98 DB1UIUO7U706 https://edgeone.ai/zh/redemption
推荐一下 Livekit,最近用它把 GPT-4o realtime 与电话系统(传统电话&SIP软电话)连起来了,开发体验和使用体验都还挺不错的。 只用写非常少量的代码,可以 python 编程, tool call 的开发也与 python 语言特性结合得很好。 同时支持 WebRTC 和 SIP,有比较成熟的 demo 可供参考。 SIP 可以实现与传统电话的结合,方便低门槛体验(比如家里的老人) BTW, Livekit 做的 GPT-4o realtime 的 playground 也比官方给出的示例代码要好使不少: https://playground.livekit.io/ (开源)
😁1
最初的问题是 SONY A7C2 拍摄的 HEIF 格式照片元信息格式有问题,导致 Photo 预览的时候竖拍的照片角度错误。 osxphotos 底层有两种方式操作 Photos Library 1. Apple Script。但 Photos 未实现 orientation 相关的 Apple Script 接口。 2. Photos.sqlite。直接操作 Photos 的内部数据库
😁1
osxphotos: macOS 上命令行(或程序化)操作 Apple 原生 Photo Library 的工具 一个很实用的功能是 osxphotos add-locations 可用于批量化添加 GPS 位置信息(通过复制附近时间段的照片) osxphotos add-locations --window "2 hr"
Showing the 12 most recent of 13 posts we hold for @yifan_boardcast. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Forward network
Republished by
Channels on the register that have forwarded this channel's posts into their own feed.
Built only from forwarded posts we have actually read, on both sides. Coverage is early and deliberately incomplete: a missing link means we have not read the post that would prove it, never that the relationship does not exist. Counts are distinct forwarded posts observed, so they only ever go up as we read more.
Cite this entry
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 16 August 2026 — this entry's latest reading, not the date you are reading this.
“Yifan's nonsense” (@yifan_boardcast), 23 subscribers as measured 16 August 2026. Telegram Register, tgregister.com/channel/yifan_boardcast.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.