DooperD @dooper_d

低予算で作られた最高に面白いおもちゃ

Today we're introducing the new Obsidian Community site, the new developer dashboard, and a roadmap of things to come for plugins and themes.

Obsidian @obsdmd

2 months ago

x.com/i/article/2054…

45 207 2K 493K 2K

Bored? Sad about the current state of your country? Cheer up, make some arts and crafts. Make a cute bat 🦇

x.com/i/article/2074…

Hermes Agent v0.18.0 - The Judgement Release Changelog below:

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build. Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention. The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention! Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on. The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience. When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful. AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system. External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent. With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both! I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering). [Original text: The Batch]

AI builder: "Downloading Hermes and not using these features is like buying a Lambo and keeping it at 10mph." in 23 minutes, Jack breaks down every Hermes feature most people never touch worth more than a $500 AI automation course here's what he covers: > a memory system that recalls exactly what you said on any specific day > a "dreaming sequence" that plans your day before you wake up > running multiple research tasks in the background, simultaneously > connecting Hermes to your meetings, emails, and notes so it never forgets anything most people use Hermes like a basic chatbot the ones getting real value built it into a full personal operating system i wrote a guide on how to integrate Hermes Agent with Obsidian 👇

kepo @kepochnik

2 weeks ago

x.com/i/article/2071…

10 11 63 36K 116

“除了生理之外，你所感受到的痛苦，都是你的价值观带给你的，而非真实存在。” 痛苦源于「期待」与「现实」的落差......

x.com/i/article/2063…

x.com/i/article/2070…

x.com/i/article/2069…

x.com/i/article/2010…

🔥用 ChatGPT-Image2 画《导览式科普绘本》，硬核又趣味！ 复杂知识也能变成孩子看得懂的绘本✨ 1、小行星飞向地球，科学家怎么办？ 2、龙舟为什么能划得这么快？ 3、夏至那天，太阳发生了什么？ 4、城市为什么越来越热？ 每张图都有大场景、导览路线、知识站点和可爱小导览员 适合儿童科普启蒙、课程课件、亲子共学，把硬知识做成软内容！ 提示词在评论区👇

keyboard_arrow_left Previous keyboard_arrow_right Next

Larus Canus @MrLarus

2 months ago

有趣+实用！📚 🤯 用GPT-Image2生成《剖面科普图解绘本》，阅读感直接满分！ 我生成了四个主题：火山、潜水艇、心脏、霸王龙 全都能轻松做出外部形态 + 内部结构 + 功能分区 + 知识标注的完整图解页！ 配色舒服、细节丰富、孩子一看就入迷，完全是出版级质量！ Prompt放在评论区👇

keyboard_arrow_left Previous keyboard_arrow_right Next

32 145 706 160K 735

在投资自己时，千万不要犹豫。 🔺书籍 🔺健身 🔺优质食品 🔺心理健康 🔺个人发展 这些投资会带来长期的回报。你永远不会后悔！

Fun interactive science app ideas | Part 6 Made an app for exploring complex molecular structures Design & Code: Opus 4.8 More demos ↓

文字具象化 nano banana 2👇 --- A colossal hand gripping an enormous vintage fountain pen, captured in vertical portrait format (9:16), writing on endless textured paper that fills the frame. Where the ink flows, the story of [BOOK_NAME] bursts into vivid life — [iconic characters, key objects, and signature scenes from [BOOK_NAME] emerging as tiny miniature figures on the paper, each no larger than a fingernail, ultra-miniature scale]. The miniature world cascades downward across the page as the pen moves, characters frozen mid-story, ink still wet at the edges where they emerge. Extreme close-up of the enormous pen nib touching paper, ink bleeding into fiber, fingertips with visible skin texture. Warm amber and soft golden light raking across the paper surface, deep shadows, cinematic depth of field, magical realism, hyper-detailed, photorealistic, 8K, --ar 9:16

Koji：一个拒绝给答案的 AI 家教... 由来自麻省理工学院和哈佛大学的顶尖学习专家训练而成 号称全球第一个「图形化私教」 你给孩子一个答案，他就少思考一次；少思考一次，这个能力就少长一点。 Koji 反着来，不给答案,而是逼你自己想 它能看到你看到的，甚至能高亮、批注屏幕内容，实时指导你... 几个特点： 1、它不像 ChatGPT 那样只甩给我一串步骤清单，剥夺了学习机会还养出对AI依赖。Koji 反过来，问你、引导你，逼你自己把这步想出来。 2、它能看见你的屏幕你不用把题目描述给它。Koji 本来就趴在你旁边，看着你做题，知道你哪一步拖错了、在哪儿停了三秒。 它清楚你为什么卡住，因为它看得见。 3、「图形化」是关键普通 AI 只能跟你打字聊。Koji 能直接伸手改你的题：高亮一块区域、给图加批注、临时塞一道小题给你。 学导数时，它就在你那条切线上跟你一起画，而不是在另一个窗口回你一段文字。 4、它先开口，老师在你求助之前先开口，会大大降低你张嘴提问的门槛。所以每进一页 Koji 都先说一句：这题和上一道有什么不一样，动手前该注意什么。 视频里两个场景： 几何题：孩子在画布上挪圆挪错了。Koji 没说"该往哪边挪"，而是画了几个测试点反问"哪些符合圆的方程？" 逼孩子自己推出 y=0 时 x=6。 Python 课：Koji 直接不教 Hello World 那套，因为"代码现在都是 AI 写的"，孩子要学的是看懂代码 + 抓 AI 的错。卡死循环？它不告诉答案，只提醒"你在死循环里"，剩下你自己找。

Dragon Ball