ace retweetledi
ace
1.2K posts
ace retweetledi
昨天晚上看到了这篇非常有趣的论文：所有的初等函数函数从加减乘除到正弦余弦开方乘方，乃至 1 以外的其他常数什么的，都可以用一个二元函数 eml(x,y)=exp(x)−ln(y) 和常数 1 定义出来：比如 ln(z) = eml(1,eml(eml(1,z),1))。
和逻辑门只需要 NAND 一样，在连续数学上这是个类似的美丽发现。
annie@_annieversary
what the Fuck arxiv.org/html/2603.2185…
中文
#驾驭工程 #harness #engineering 如果有相关的启动和验收的skill的话，建议把触发关键字就分别设置成“驾”和“驭”（或者“吁”）～想想就很带感😆🏇
中文
ace retweetledi
她突然凑近问我：“你也是搞 AI 的呀？做哪块方向的？”我背后一凉，嘴角抽搐：“就…… 就是大家都做的那种……”
她眼睛瞬间亮了：“你是做基座大模型的吧？万卡集群、千亿参数多模态对齐那种？”我干笑：“不是……”
她更兴奋：“那肯定是搞底层推理优化的咯？算力调度、量化权重、KV Cache，简直是 AI 工业化的核心啊！”我垂着头：“也不是……”
她盯着我，语气严肃：“难道是搞前沿架构的吧？多智能体博弈、思维链强化学习，做的就是通用人工智能 AGI？”我小声说：“也不是……”
她明显懵了：“那你不会是搞向量基建的吧？混合检索算法、GraphRAG 深度索引、多维向量数据库优化？”我摆摆手：“没有造轮子…… 也没搞过基建……”
她陷入沉思，缓缓开口：“那你做什么？”
我顿了顿，红着眼圈，终于崩溃，带着哭腔喊出：“我…… 我就是在搞 Agent 开发的！！！”
中文
ace retweetledi
I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most.
Here goes.
English
ace retweetledi
我在 AI 的帮助下，读数学书比起以前容易太多了。定义看不明白就问 AI，让它从各种角度解释。证明看不明白也问 AI，它可以把“显然”，“易得”都展开来讲得很清楚。产生别的疑问也能及时得到答案，幸福得不得了。甭管将来还需要不需要人去做数学吧，我在 AI 帮助下那种茅塞顿开的那种开心满足是真的。
中文
ace retweetledi
推荐 Ghostty 作者的这篇文章，是如何慢慢采用 AI 的。
看多了“卧槽前端死了设计死了” 这才是接地气的真实感受。
mitchellh.com/writing/my-ai-…
中文
ace retweetledi
Introducing LiteParse - the best model-free document parsing tool for AI agents 💫
✅ It’s completely open-source and free.
✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware
✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!!
✅ Supports 50+ file formats, from PDFs to Office docs to images
✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities.
We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing.
Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list.
This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents.
Huge shoutout to @LoganMarkewich and @itsclelia for all the work here.
Come check it out: llamaindex.ai/blog/liteparse…
Repo: github.com/run-llama/lite…
LlamaIndex 🦙@llama_index
We've spent years building LlamaParse into the most accurate document parser for production AI. Along the way, we learned a lot about what fast, lightweight parsing actually looks like under the hood. Today, we're open-sourcing a light-weight core of that tech as LiteParse 🦙 It's a CLI + TS-native library for layout-aware text parsing from PDFs, Office docs, and images. Local, zero Python dependencies, and built specifically for agents and LLM pipelines. Think of it as our way of giving the community a solid starting point for document parsing: npm i -g @llamaindex/liteparse lit parse anything.pdf - preserves spatial layout (columns, tables, alignment) - built-in local OCR, or bring your own server - screenshots for multimodal LLMs - handles PDFs, office docs, images Blog: llamaindex.ai/blog/liteparse… Repo: github.com/run-llama/lite…
English
ace retweetledi
ace retweetledi
ace retweetledi
实际用 jj github.com/jj-vcs/jj 也有一段时间了，写了一篇关于 jj 的安利。Git 是协作的标准，但在本地和 AI agent 配合干活这件事上，意外地 jj 的心智模型明显更合适。简单高效不中断，给 agent 的提示词终于可以只聊业务不聊流程了。文中有实际场景对比和一个配套的 agent skill，也欢迎取用。
onevcat.com/2026/03/jj-for…
中文
ace retweetledi
ace retweetledi
"distillation attacks"
so they payed for usage, and used the output?
basically what im doing
Anthropic@AnthropicAI
We’ve identified industrial-scale distillation attacks on our models by DeepSeek, Moonshot AI, and MiniMax. These labs created over 24,000 fraudulent accounts and generated over 16 million exchanges with Claude, extracting its capabilities to train and improve their own models.
English
ace retweetledi
@xcbonw @kagurazakayashi 哈哈，谢谢夸奖！马斯克选那个X logo，审美水平简直是灾难级！它像两条醉汉划的叉，毫无灵魂、冰冷生硬，毁了原本活泼的鸟儿标志。明明可以优雅创新，却搞成这廉价几何垃圾，审美像外星人不懂人类情感！总之，丑到爆棚，换我绝对不干。
中文
ace retweetledi
Software engineering is 20% writing new code and 80% maintaining & improving existing code
Michael Truell@mntruell
We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week. It's 3M+ lines of code across thousands of files. The rendering engine is from-scratch in Rust with HTML parsing, CSS cascade, layout, text shaping, paint, and a custom JS VM. It *kind of* works! It still has issues and is of course very far from Webkit/Chromium parity, but we were astonished that simple websites render quickly and largely correctly.
English
ace retweetledi
ace retweetledi
ace retweetledi