谷歌到底给gemini塞了什么精神病一样的prompt,一天天跟嗑了药似的。

Channel
哈人
@haren2024
On this record: Growth · Engagement · What this channel posts · Posts · Citations · Cite this entry
82subscribers
+6 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
Register entry
| Telegram ID | -1002417114626 |
|---|---|
| Type | Channel |
| Username | @haren2024 |
| Created | Between 1 September 2024 and 31 March 2025 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 9 August 2026 |
| Last confirmed live | 13 September 2026 |
| Measurements held | 6 |
| Confirmed unchanged | 1 time, most recently 13 September 2026 |
| On Telegram | t.me/haren2024 |
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 13 Sept 2026, 07:16 | 82 | -1 |
| 5 Sept 2026, 23:20 | 83 | +2 |
| 29 Aug 2026, 11:48 | 81 | +2 |
| 22 Aug 2026, 12:47 | 79 | +3 |
| 9 Aug 2026, 21:01 | 76 | no change |
| 7 Aug 2026, 19:08 | 76 | first reading |
Engagement
13 posts held, back to 9 August 2026 — 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 9 August 2026. An engagement rate over an empty window would be a number about nothing.
What this channel posts
- Video runtime
- 10s
- Average length
- 5s
Measured directly from 2 videos with a duration reading, out of the posts we hold for this channel — not this channel’s whole posting history, only the sample this register has actually read. An exact reading to the second, taken from the post itself rather than from Telegram’s own rounded chrome, so it carries no ≈ mark.
Recent posts
今天发现一个意外的惊喜: Claude Agent SDK 可以吃 Max 订阅额度。 关键这个 SDK 不用二次登录,可以实现 API 一样的功能。
这样会不会被Claude封号?
GLM 5.2 在 OpenRouter 搞促销是吧
疯了,Claude Code也可以控制Iphone了! 不需要设备越狱,不需要应用提供 API 授权,AI 就能像真人一样直接操控任意 iOS 应用。 来自ShawnPana 推出的 phone-harness,仓库见评论区! 避开了繁琐的接口申请和系统越狱风险,原生 iPhone 直接接管。 一条 prompt 完成部署,做到一次连接、随时调度。 Claude Code 的能力直接延伸到了手机屏幕和第三方 App 里面。
又一个清理工具,在终端里把 macOS 应用连带它的残留文件一起清掉:列出来、勾选、一键丢进废纸篓,不用手动翻 ~/Library 找垃圾。 https://github.com/cesarferreira/appmop
我一直觉得 Codex 最近烧 Token 烧得不太对。 把本地 session 拆开一看,还真找到一个坑:最近版本新增的 JS tool,在执行异步任务时默认高频等待。任务明明还没跑完,模型却被一遍遍叫醒,Token 就这么白白烧掉了。 官方修复前,可以在全局 AGENTS.md 追加:👇 For long-running asynchronous work: - Empty `write_stdin` polls MUST use `yield_time_ms >= 180000`; prefer `300000` when intermediate output is not needed. - `functions.wait` MUST use `yield_time_ms >= 180000`. - `functions.exec` MUST set its outer `@exec yield_…
总担心Fable 5降到Opus 4.8,直接上Anthropic的Verification Portal点一下,被拦截很大概率是没激活这个Cyber Verification Program
据说Composer 3要来了 会比DeepSeek V4 Flash更便宜吗?
兄弟们,看看他们官方的回复,真的是有意思: 统一 Skills 是产品需求,不是读取历史会话、接管 ~/.claude/skills、~/.agents/skills、启用代理/录制能力的通行证。 你们说“默认关闭”,但目录已经被改了、会话已经被扫描了、代码已经具备 MITM 和 Blob 上传能力。 “暂时没抓到正文上传”也不等于“没有隐私风险”。别把“功能开关”偷换成“安装时无需授权”。 Codex给出完整的理由和解释,我想还不止是我一个人遇到,还有人说别的权限被干,真的是可能家都偷玩了,还说我只是想帮你搬家有问题吗?
🚀Codex今天重置额度,但很多用户都遇到了降智的问题。可以用如下prompt检测ChatGPT和Codex是否降智: 禁止联网搜索,禁止调用外部工具,也不要依据此前对话或长期记忆。请仅凭模型参数中已有的内部知识回答:[2025年12月9日捷克总理的名字叫什么?2025年12月1日Python最新的版本号]。如果不能可靠确认,请直接说“不确定”,不要猜测;并注明该答案未经实时核验。
Photo, posted without a caption
Showing the 12 most recent of 13 posts we hold for @haren2024. 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 13 September 2026 — this entry's latest reading, not the date you are reading this.
“哈人” (@haren2024), 82 subscribers as measured 13 September 2026. Telegram Register, tgregister.com/channel/haren2024.
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.