Howie Hu

Dude, have you actually taken a good look at the DeepSeek paper? This is a foundational model intended to carry the future of China's general large-scale models. It wasn't specifically designed just for writing code. Furthermore, the official team stated very sincerely that its coding capability only surpasses Sonnet 3.5. There is still a gap between its performance and the coding abilities of models like Opus.

DeepSeek V4 Pro debuted at #14 on LMArena Code. Remember when DeepSeek was supposed to be the future of open source AI? The model that was going to compete with frontier labs? Ranked below a $0.33 input model from Alibaba. DeepSeek fell off hard.

@fankaishuoai 是的废话居多还油嘴滑舌，切Codex会好很多

用了一段时间的 GPT 5.4 来跑小龙虾，但是感觉 GPT 5.4 的废话好像比 GPT-5.2 更多了。 虽然让它给我少输出一些废话，但现在用下来，用来用去还是感觉 Claude 的更好用——Opus 和 Sonnet 属于人狠话不多，不会有太多废话，然后总能说到点上。

1M context windows aren’t new — GPT-5.4 and Gemini 3 Pro already have them. But there’s a difference between “supports 1M” and “actually works at 1M.” GPT-5.4’s MRCR accuracy: 91% at 16K → 37% at 1M. That’s Context Rot. Gemini 3 Pro claims 10M but scores just 26% at 1M. Claude Opus 4.6 holds 78% at 1M — 2x GPT-5.4’s score. And Anthropic removed the long-context surcharge entirely. Flat pricing across the full 1M window. GPT-5.4 charges 2x beyond 272K. Accuracy that doesn’t collapse + pricing that doesn’t spike = the first 1M context model that’s actually usable in daily engineering workflows. #Opus #ClaudeCode

What can you do with $200? 1 - Highly recommend the $100 Claude Code Max subscription. This allows you to use the powerful Claude Code plus the Opus model under a fairly high workload. 2 - Sign up for the $60 Cursor Pro+ subscription. This enables you to make full use of GUI IDE tools like Cursor to accomplish things you enjoy. 3 - Then use $20 to subscribe to ChatGPT Plus. This allows you to use ChatGPT daily and the built-in Codex quota. This quota lets you use Fast mode and xhigh inference to review tasks done by Claude Code and Cursor, and it's basically impossible to use up. 4 - Finally, you'll have $20 left, which you can use to recharge OpenCode's Zen. This allows you to use OpenCode to call all the open-source and closed-source models it has filtered, and also generate APIs for other tools to use. This way, you can make full use of the $200 and form a plan that allows you to utilize all mainstream top models and tools, with all quotas remaining unused. 用 200 美元你可以做什么？ 1 - 强烈推荐 100 美元的 Claude Code Max 订阅。这样就可以让你在相当大的工作强度内，使用最强的 Claude Code 加 Opus 模型。 2 - 去注册 60 美元的 Cursor Pro+ 订阅。这能够让你充分利用 Cursor 这样的 GUI IDE 工具，完成一些你喜欢的事情。 3 - 再用 20 美元去注册 ChatGPT Plus 订阅。这可以让你日常使用 ChatGPT 和内置的 Codex 额度。这个额度可以让你使用 Fast 模式和xhigh推理，用来审查 Claude Code 和 Cursor 所做的任务，基本也用不完。 4 - 最后你还剩 20 美元，可以去充值 OpenCode 的 Zen。这样可以使用 OpenCode 来调用所有它筛选过的所有开源和闭源模型，并且还能够生成 API 给其他工具使用。 这样就充分利用了这 200 美元，并形成了一个可以用尽所有主流最强模型和工具的方案，而且所有的额度还都用不完。 #ClaudeCode #Cursor #Codex #OpenCode

我觉得 OpenClaw 的前景，主要是让人们看到了，如果把一整台电脑的权限都向 AI 开放，它能自由和强大到什么程度。 但是就安全性的角度来说，这就像一把双刃剑，所以它最终一定会实现在某种可靠的限定环境下，甚至有可能出现一种专门针对 AI 设计、由 AI 使用的操作系统。 反正这是我的洞见。OpenClaw 带来的可能性是让人激动的，虽然现在的这种实际宣传有些过火，但它也有好的一面，就是进一步扩大了 AI 的影响，让人们对 AI 有了进一步的科普。 The prospect of OpenClaw primarily lies in demonstrating just how free and powerful AI can become when granted full access to an entire computer. From a security standpoint, however, this is a double-edged sword. Consequently, it will inevitably be implemented within some form of reliable, restricted environment—there may even emerge an operating system specifically designed for and used by AI. Anyway, that’s my insight. The possibilities brought by OpenClaw are exciting. While the current hype might be a bit over the top, it has a positive side: further expanding AI’s influence and providing the public with a deeper understanding of the technology. #OpenClaw

In actual use nowadays, I clearly find that Opus 4.6 can communicate and collaborate with you in a very natural way that humans can understand and engage in normal conversations. However, GPT-5.4 still talks like a hooligan, saying things that are incomprehensible. It always mentions those symbolic texts without clarifying what exactly lies behind the words. #ClaudeCode #GPT

@d6g @xxx111god I feel the same way. I'm almost fed up with the greasiness and all the nonsense from 5.4.

@xxx111god 可以试试 5.3-codex，一直感觉5.3属于人狠话不多默默把活干完那种类型的

Claude这周上限爆了，换成了gpt 5.4 结果尼玛 纯纯一个弱智啊 是我使用方法不对吗

@novtopro @jetbrains same issue

@jetbrains I love it, but it's buggy.

Air just launched. This week we’re highlighting some key features. No single agent is best at everything. Air lets you easily switch between Codex, Claude Agent, Gemini CLI, and Junie, so you can choose the right agent for each task. Try Air for free: jb.gg/4dhmrw

@MFA_China Never Kneel Down!

Never Kneel Down!

@euler2074 @windsurf_ai No.

@windsurf_ai does it have Windsurf Tab?

Wave 7 is here! We made Cascade available on JetBrains IDEs. Now JetBrains developers have access to the multi-step agentic experience that Cascade provides. Oh and btw, we're no longer going by Codeium... everything is Windsurf! 🏄

@gunsnrosesgirl3 I am Chinese, and I want to clarify that both girls in the video are also Chinese. Did you see their red scarves? This is a distinctive symbol found only in socialist countries with the Young Pioneers.

Maths techniques x.com/visualfeastwan…

@DesiSanatani @Morbidful lol...😂 This is in China, not South Korea...

@Morbidful Inspire resort in South Korea looks insane 🔥

Incredible footage captured by CBGvideos in 2005 showcases the entrance to Nutty Putty Cave and the notorious Birth Canal section, the very area John Edward Jones was attempting to find before becoming trapped and tragically dying. Jones visited the cave on November 24, 2009, with his brother Josh. While exploring with Josh, Jones mistook a narrow tunnel for the similarly tight "Birth Canal" passageway and became stuck upside-down in an area measuring 10 by 18 inches (25 by 46 cm), around 400 feet (120 m) from the cave's entrance. Jones was held in place like a hook, unable to move without causing serious harm due to the bends his body was placed in. A large team of rescue workers came to his assistance. Still, they were unable to retrieve Jones using a sophisticated rope-and-pulley system after a pulley failed mid-extrication. After 28 hours, Jones suffered cardiac arrest due to the strain placed upon his body over several hours by his inverted, compressed position. Rescuers concluded that it would be too dangerous to attempt to retrieve his body; the landowner and Jones' family came to an agreement that the cave would be permanently closed, with the body sealed inside, as a memorial to Jones. Explosives were used to collapse the ceiling close to Jones' body, and the entrance hole was filled with concrete to prevent further access.

@ArmaPlatform I want to know when support for DLSS and FSR 2.0 or higher versions will be available? The current graphics performance optimization is very unsatisfactory to me.

It's Round 2 of #ReforgerRFI questions! 📻 This is another opportunity to ask the devs anything about #ArmaReforger, and your question could be featured in an upcoming video! Share your questions below ⤵️ Previous answers here: ow.ly/puX850QwOVi

Tired of unclear responses from #LLMs? New research paper "Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4" outlines 26 principles to simplify #prompting & get the most out of models. Check below and comment to share your experience! 👇 1⃣ No need to be polite with LLM so there is no need to add phrases like “please”, “if you don’t mind”, “thank you”, “I would like to”, etc., and get straight to the point. 2⃣ Integrate the intended audience in the prompt, e.g., the audience is an expert in the field. 3⃣ Break down complex tasks into a sequence of simpler prompts in an interactive conversation. 4⃣ Employ affirmative directives such as ‘do,’ while steering clear of negative language like ‘don’t’. 5⃣ When you need clarity or a deeper understanding of a topic, idea, or any piece of information, utilize the following prompts: - Explain [insert specific topic] in simple terms. - Explain to me like I’m 11 years old. - Explain to me as if I’m a beginner in [field]. - Write the [essay/text/paragraph] using simple English like you’re explaining something to a 5-year-old. 6⃣ Add “I’m going to tip $xxx for a better solution!” 7⃣ Implement example-driven prompting (Use few-shot prompting). 8⃣ When formatting your prompt, start with ‘###Instruction###’, followed by either ‘###Example###’ or ‘###Question###’ if relevant. Subsequently, present your content. Use one or more line breaks to separate instructions, examples, questions, context, and input data. 9⃣ Incorporate the following phrases: “Your task is” and “You MUST”. 🔟 Incorporate the following phrases: “You will be penalized”. 1⃣1⃣ Use the phrase ”Answer a question given in a natural, human-like manner” in your prompts. 1⃣2⃣ Use leading words like writing “think step by step”. 1⃣3⃣ Add to your prompt the following phrase “Ensure that your answer is unbiased and does not rely on stereotypes”. 1⃣4⃣ Allow the model to elicit precise details and requirements from you by asking you questions until he has enough information to provide the needed output. (for example, “From now on, I would like you to ask me questions to...”). 1⃣5⃣ To inquire about a specific topic or idea or any information and you want to test your understanding, you can use the following phrase: “Teach me the [Any theorem/topic/rule name] and include a test at the end, but don’t give me the answers and then tell me if I got the answer right when I respond”. 1⃣6⃣ Assign a role to the large language models. 1⃣7⃣ Use Delimiters. 1⃣8⃣ Repeat a specific word or phrase multiple times within a prompt. 1⃣9⃣ Combine Chain-of-thought (CoT) with few-Shot prompts. 2⃣0⃣ Use output primers, which involve concluding your prompt with the beginning of the desired output. Utilize output primers by ending your prompt with the start of the anticipated response. 2⃣1⃣ To write an essay /text /paragraph /article or any type of text that should be detailed: “Write a detailed [essay/text/paragraph] for me on [topic] in detail by adding all the information necessary”. 2⃣2⃣ To correct/change specific text without changing its style: “Try to revise every paragraph sent by users. You should only improve the user’s grammar and vocabulary and make sure it sounds natural. You should not change the writing style, such as making a formal paragraph casual”. 2⃣3⃣ When you have a complex coding prompt that may be in different files: “From now and on whenever you generate code that spans more than one file, generate a [programming language ] script that can be run to automatically create the specified files or make changes to existing files to insert the generated code. [your question]”. 2⃣4⃣ When you want to initiate or continue a text using specific words, phrases, or sentences, utilize the following prompt: - I’m providing you with the beginning [song lyrics/story/paragraph/essay...]: [Insert lyrics/words/sentence]’. Finish it based on the words provided. Keep the flow consistent. 2⃣5⃣ Clearly state the requirements that the model must follow in order to produce content, in the form of the keywords, regulations, hint, or instructions. 2⃣6⃣ To write any text, such as an essay or paragraph, that is intended to be similar to a provided sample, include the following instructions: - Please use the same language based on the provided paragraph[/title/text /essay/answer].

还记得你何时加入 X 吗？我知道！#我的X周年纪念日

Just discovered an amazing GPT-4 trick! 🤯 1. Draw your dream UI in ASCII art. 🎨 2. Let GPT-4 create an accurate 1:1 implementation. ✨ Output in @Replit

@DanielsEssis fake news

View my verified achievement from @theopengroup. credly.com/badges/1bc3479…