发布节奏
最近 12 周每周中位浏览
最近 12 周发布时间
颜色 = 中位浏览爆款 vs 日常
爆款 = 浏览前 10%| 指标 | 爆款 | 日常 |
|---|---|---|
| 帖子 | 4 | 28 |
| 带媒体 | 50% | 35.7% |
| 回复 | 0% | 0% |
| 平均字数 | 143 | 116 |
| 中位浏览 | 8,252 | 642 |
打法建议
只陈述相关性- 互动最好的时段是 04:00 前后（北京时间），中位浏览 2,771。
- 一周里 周二 的中位浏览最高。
- 形式上 带图/视频 的中位浏览更高（1,128 vs 689）。
- 爆款里带媒体占 50%、回复占 0%；日常分别是 35.7%、0%。
- 当前节奏约 1.1 条/天，日均浏览 2,299。
内容结构
按本站分析的分类（近 120 天）还没有分类分析。
形式与语言
帖子占比- 纯文字20
- 图片7
- 视频5
回复占比 0% · 引用 59.4% · 带媒体 37.5%
互动最高的帖子
按浏览排序- 1
Introducing: Browser Use Extensions 🧩 Your agent has been browsing the internet naked. Not anymore. > Any Chrome extension, uploaded once > Loaded before the first page > Ad blockers, password managers, your own Live today 💯
- 2
Automating stuff where API or MCP don't exist.
- 3
Haiku 5.5 on Browser Use Bench v2.1 👀 > same performace as Luna > 2.8x more expensive Haiku gets 5x more expensive after 100k context, including cached tokens. BU Bench 2.1 is mostly extremely long-running horizon tasks. It hits that pricing tier a lot.
- 4
We make sure you will never use the browser
- 5
You can now use browser-use with the new anthropic computer SDK. https://docs.browser-use.com/open-source/customize/integrations/toolsets-for-claude
- 6
Your agents don't have to start every run logged out 🔐 Profile Sync > One command copies your Chrome logins to the cloud > Every cloud browser starts logged in > No passwords or 2FA codes in the prompt
- 7
For anyone playing the cat and mouse game, we have the best stealth on the market 👀
- 8
Browser Use in JS 👀
- 9
GPT-6.1 Terra is insanely good at browser use 🔥 > 78.5 on the Browser Use Benchmark > basically Sol performance (79.7) at 35% less cost. Pareto frontier is once again dominated by OpenAI.
- 10
DeepSeek V4.1 Flash 1017 just matched Opus 5.5 on long horizon browser use. 19x cheaper 👀 > 75/100, same as Opus 5.5, almost Astra level > $0.22/task vs $2.35/task > Sol it still SOTA, but it's close The new pareto frontier 🔥
- 11
Introducing: Odysseys2 - hardest long horizon benchmark for web agents based on real user tasks 🏗️ We collaborated with @JangLawrenceK @rsalakhu from Carnegie Mellon University > SOTA agent fully completes only 47/100 > 5 agents complete none > 8-12 real rubrics per task, 60 min on the live web Web agents are becoming better than humans at knowledge work. http://odysseysbench.com/v2
- 12
Our iMessage agent is powered by @PhotonHQ try it out
点赞、转发、浏览是采集那一刻的快照，不是帖子最终数据；时间为北京时间。KPI 卡片里的同比只在账号有 8 周以上数据时显示， 否则只看近 4 周。“打法建议”只说明数据里的相关性，不代表因果。