thank you !

We've added tool use support to the Workbench in the Anthropic Console so you can now test prompts that use tools.



Windsurf is on another level 🌊

Tweet Image 1

kw Reposted

We've added a Claude-powered prompt improver to the Anthropic Console. Take any prompt, run it through the improver, and get an optimized prompt in return. Here's how it works:

Tweet Image 1

!!!

We’ve added a new prompt improver to the Anthropic Console. Take an existing prompt and Claude will automatically refine it with prompt engineering techniques like chain-of-thought reasoning.



kw Reposted

对于大语言模型来说,它是没有记忆功能的,也就是每一次你必须发送给它所有的历史会话内容,也就是每次发新消息都会把历史消息一起发送过去。但是这样一直累加就会超出最大上下文窗口长度,并且会让会话的成本急剧上升,毕竟内容越多,需要消耗的算力越大。 所以对于 AI…

Tweet Image 1

The Context Window in AI chat apps is like a sliding memory buffer: it keeps recent messages but summarizes older ones to save space. That's why AI might "forget" earlier chats - it's not storing the full history, just a condensed version plus recent exchanges!

Tweet Image 1


是的 这样的傻逼真的很多

在互联网上真有一群傻逼,每看到别人用个mac,就反复问别人, “你用mac是不是装逼?”、“你们用mac除了装逼还有别的什么用?”、“你们mac用户为什么这么喜欢装逼?” 至少证明了一件事: 这世界上真的存在“自己买不起mac,还觉得别人用mac是纯粹装逼,看别人买得起mac比杀了自己亲妈还难受”的大傻逼。

Tweet Image 1


kw Reposted

强烈推荐这篇 prompt 大神李继刚的采访,非常非常有共鸣!几乎是把我这半年来用 prompt 的微妙感受,做了一个高度的提炼(压缩),佩服佩服!! 1.…


通过语言和文字的表达可以判断出一个人是否聪明,我一直都这么认为

有个观点我憋了好多年,正好借姜萍事件落幕说一下(如果伤到一些人提前说声抱歉): 天才们真的是木讷而不善言辞的吗?错,大错特错…



I used to write code to recognize images in PDFs, but now this step is no longer necessary. It’s so convenient!!

Claude can now view images within a PDF, in addition to text. This helps Claude 3.5 Sonnet more accurately understand complex documents, such as those laden with charts or graphics. Enable the feature preview: claude.ai/new?fp=1.



If you like more beautiful text, I can tell you clearly that the linguistic charm of opus far surpasses that of the sonnet. If you use them frequently and make comparisons, you will definitely think so.


kw Reposted

Build and deploy RAG-as-a-service in production for your own data using Claude Sonnet 3.5 in less than 50 lines of Python Code (step-by-step instructions):


Ending is better than mending, anytime.


Claude is the type who is tough and doesn’t say much. After experiencing computer use, I feel that this kind of change will only accelerate.

Computer use is the first step toward a completely new form of human-computer interaction. In just a few years, the way we interface with computers will be completely different from today. Let me explain:

Tweet Image 1


kw Reposted

纠结东北雨姐的木薯粉条里的木薯有没有毒,不看看自己农村老家大集上的腌鱼烂肉和防腐剂, 天天盯着肯德基豆油低于0.00001%的转基因蛋白质,不去看看煤油含量高于5%的市场食用油, 吃一锅老火锅,能喝半锅反式脂肪酸牛油加口水,每天还在关心锅底的三花淡奶、鱼丸里的淀粉量, 洼地人确实太傻逼了。


Start using immediately!

Introducing an upgraded Claude 3.5 Sonnet, and a new model, Claude 3.5 Haiku. We’re also introducing a new capability in beta: computer use. Developers can now direct Claude to use computers the way people do—by looking at a screen, moving a cursor, clicking, and typing text.

Tweet Image 1


kw Reposted

Sweet. You can now choose between full or concise responses in @AnthropicAI's #Claude 🔥

Tweet Image 1

kw Reposted

太强了,站在提示词颠覆的男人李继刚汉字新解后继有人,Claude 提示词 prompt 后已经进化到下边图例这种程度了! 由网友zephyr 空格发布的完整提示词已经开源: ;; 提示词:动物的一生 ;; 作者:空格 zephyr (defun 动物生命周期 ()   "生成动物的生命周期SVG图表和描述"   (lambda (主题)…

Tweet Image 1
Tweet Image 2
Tweet Image 3
Tweet Image 4

“I can’t wait any longer.”

LETS GO, Opus 3.5 next week Tuesday, October 22! Finally, I'm so excited!



kw Reposted

Don't copy and paste answers from ChatGPT. ChatGPT writing is easily detectable. Here's a secret hack to humanize your text:

Tweet Image 1

kw Reposted

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

Tweet Image 1

United States Trends
Loading...

Something went wrong.


Something went wrong.