全部 AI 动态

我们构建了一个技能，可以将任何 agent 连接到任何 API。 Stripe。NASA 火星车。国际空间站追踪器。Evil Insult Generator。全部即时连接。 在回复中丢出你能找到的最冷门的 API。我们会挑选出令人惊喜的那些，展示它们如何运作——并送你 25 美元的免费 Membrane 额度。 越极客越好。 npx skills add membranehq/agent-skills@integrate-anything

Soooo @trq212 has straight up changed my life with these 5 words: "HTML is the new markdown." It's so obvious in hindsight: while .md is simple to write and agents can read it well, it's a total slog to eyeball as a human. In this special ep recorded live at Code with Claude, Thariq walks me through how he: - uses HTML artifacts as interactive specs - builds throwaway micro-UIs - maintains a living design system in HTML - prompts Claude with "whatever is needed" to give it room to actually think He also tells us what comes after the SWE + PM role 👀 As always, a huge TY to our amazing sponsors: 🔀 @celigoinc - Intelligent automation built for AI: https://celigo.com/howIAI 🪪 @withpersona - trusted identity verification for any use case: https://withpersona.com/lp/howiai Watch now on YT: https://www.youtube.com/watch?v=Qrpm7E80wQ0

My colleagues wrote up a great post on using Goals in Codex. They go through when to use them, what changes when a Goal is active, and how to write Goals that give Codex a clear outcome, constraints and verification criteria. Also how we designed Goals at the architecture level if you’re curious. https://developers.openai.com/cookbook/examples/codex/using_goals_in_codex

a prompt I've been using a lot recently: implement <SPEC> and while you do, keep a running implementation-notes.html file (or markdown) with decisions you had to make weren't in the spec, things you had to change, tradeoffs you had to make or anything else I should know

My colleagues wrote up a great post on using Goals in Codex. They go through when to use them, what changes when a Goal is active, and how to write Goals that give Codex a clear outcome, constraints and verification criteria. Also how we designed Goals at the architecture level if you’re curious. https://developers.openai.com/cookbook/examples/codex/using_goals_in_codex

AI hype can be pretty easy to find. But clear explanations are definitely harder. Deep Learning with R, Third Edition by @fchollet and Tomasz Kalinowski helps cut through that noise with practical examples that build your understanding step by step, so you learn why deep learning models work, not just how to run them. Now in print and 50% off through May 25th: https://hubs.la/Q04gQbC90

We analyzed real skill call data from TRAE users. Here are the 10 Most Popular Agent Skills that people actually use, not just install. From design-first thinking to browser automation, these skills are shaping how people build with agents today 👇

Attempt to use Grok Build to visualize some physics concepts for education. Prompt: "I want you to explain Navier-Stokes equations and how it relates to airfoil design. visualize this with math-manim tool"

I finally used /goal in Codex and I’m absolutely mind blown. I had it look through my last 500 archived emails. Then look for an unsubscribe link and unsubscribe if there is one. It found 87 and it clicked them all. It handled the “are you sure” pages AND flagged 14 that required login. Ran unsupervised for over an hour and now I’m marketing email free. Absolutely wild.

你应该在 Twitter 上关注的 30 个与 AI 相关的账号： 英文： @karpathy，Andrej Karpathy，Eureka Labs创始人，OpenAI早期成员，前Tesla AI负责人，擅长把神经网络、LLM、Agent讲到普通工程师也能听懂。 @fchollet，François Chollet，Keras作者、ARC-AGI提出者，Ndea和ARC Prize联合创始人，长期讨论AGI、抽象推理和「智能到底是什么」。 @ylecun，Yann LeCun，图灵奖得主、CNN/深度学习代表人物，NYU教授，前Meta首席AI科学家，现在做AMI，长期主张开源、世界模型和非纯LLM路线。 @AndrewYNg，吴恩达，http://DeepLearning.AI、AI Fund、Landing AI创始人，Coursera联合创始人，AI教育和AI落地应用领域最有影响力的人之一。 @rasbt，Sebastian Raschka，LLM研究工程师、作者，写过《Build a Large Language Model From Scratch》，适合看模型原理、训练细节和代码实现。 @dair_ai，http://DAIR.AI，AI研究和教育社区，也是Prompt Engineering Guide背后的项目，适合看prompt、context engineering、agent相关资料。 @lilianweng，Lilian Weng，Thinking Machines Lab联合创始人，前OpenAI研究与安全VP，Lil’Log作者，agent、RL、AI安全综述写得非常系统。 @jeremyphoward，Jeremy Howard，http://fast.ai联合创始人、http://Answer.AI创始CEO，做AI教育、实用深度学习和面向开发者的AI工具。 @simonw，Simon Willison，Datasette作者、Django联合作者，长期追踪LLM工具、开源生态、prompt injection和AI Agent安全问题。 @_akhaliq，AK，AI论文信息流账号，机器学习背景，主要快速转发新论文、新模型、新项目，适合跟踪前沿动态。 @ID_AA_Carmack，John Carmack，id Software创始人、前Oculus CTO，现在在Keen Technologies做AGI，典型硬核工程派。 @gwern，Gwern Branwen，独立研究者和长文作者，写AI scaling、心理学、统计学、理性主义和长期主义相关内容。 @goodside，Riley Goodside，最早出圈的prompt engineer之一，曾在Scale AI和Google DeepMind，常发模型行为、prompt技巧和AI产品边界测试。 @drfeifei，李飞飞，Stanford教授、World Labs联合创始人兼CEO，ImageNet关键推动者之一，长期做计算机视觉、空间智能和human-centered AI。 @demishassabis，Demis Hassabis，Google DeepMind联合创始人兼CEO，AlphaGo、AlphaFold背后的核心人物之一，2024年诺贝尔化学奖得主。 中文： @dotey，宝玉，中文AI圈非常重要的信息源，长期翻译和整理LLM、Prompt Engineering、Context Engineering、AI工程实践内容，也会分享很多一手产品和技术判断。 @op7418，歸藏，AIGC周刊主理人，关注AI、LLM、AI图像视频和设计，适合追踪新工具、新模型和AI创作玩法。 @xiaohu，小互，中文AI新闻和工具资讯号，主打全球前沿科技、AI动态，也做小互AI日报社群。 @WaytoAGI，通往AGI之路，中文AI知识库和社区型账号，适合系统性补AI资料、工具、教程和行业信息。 @Khazix0918，数字生命卡兹克，AI自媒体和热点监控型账号，做了AIHOT这类AI热点监控网站，适合看中文AI圈正在炒什么、什么值得跟。 @Gorden_Sun，Gorden Sun，稳定更新AI资讯日报，适合当每日AI新闻索引看。 @FinanceYF5，Will，偏AI资讯和行业数据整理，会做AI网站流量、产品数据、行业观察，适合看数据型信息差。 @vista8，向阳乔木，关注LLM、Prompt、效率工具和AI产品落地，内容偏实用观察和产品判断。 @shao__meng，meng shao，关注上下文工程、AI智能体、企业AI落地和AI培训，也经常整理中文AI领域账号合集。 @oran_ge，橘子，前MiniMax AI工具产品负责人，http://orange.ai主理人，长期写AI产品、模型、应用和行业判断。 @hanqing_me，汗青，AI Talk创始人，重点在AI短视频、AI数字人、AI艺术和内容创作方向。 @jesselaunz，遁一子，关注AI资讯、AI实际应用和Prompt探索，偏实践派，适合看普通人怎么把AI用起来。 @thinkingjimmy，JimmyWong，http://learningprompt.wiki作者，也做Comflowy，内容偏Prompt、AI工作流、内容生产和产品思考。 @xicilion，响马，西祠胡同创始人、老程序员，分享LLM实战、工程判断和开发者视角，对AI工具链的理解比较硬。 @AI_Jasonyu，鱼总聊AI，关注AI、出海、创业、独立开发和副业方向，经常整理AI博主、工具和产品机会。 有哪些我漏掉了？欢迎补充

wow i just had codex analyze 3 years worth of text messages... i had it use direct quotes in its analysis and it brought me to tears. if you have mac you can just ask codex to do this. you will need to give it permissions

My laptop has become a “satellite device” since I started using Codex from my phone. And my Mac mini has become the “home.” It’s clunky, but the end state feels more like how we’re going to be working in the near future: I’m currently running the Codex app on 2 devices: 1. my MacBook 2. my Mac mini My laptop isn’t reliably connected to Wi-Fi enough, so I keep a Mac mini on my desk that is always connected. When I kick off new threads from my phone, I start them on the Mac mini. When I’m working from my desk, I run them there too. The cool part is that I’ve added my MacBook and Mac mini as connected devices to each other. That means I can start and resume threads from either device. So if I’m in a meeting but want to continue a thread on my laptop that was started on my Mac mini, I can do that. I’ve also set up mutual SSH for Mac mini <> MacBook, so files are easy to access from either side. It’s not fully seamless yet, but the model works. What this means: - I have an always-on Codex that is accessible from my phone, with its own dev environment - All threads are always accessible from any of the 3 devices - I can run heartbeat threads that stay on 24/7 It’s a little makeshift today, but the shape of it feels very real to me: Codex is no longer tied to whichever computer happens to be open in front of me. It starts to feel like something I can stay connected to across whatever device I’m using.

use this Codex prompt to automate things you do repetitively during the day: "Look through my Chronicle memories and check for workflows that i'm repeating multiple times. Turn them into skills."

CODEX SKILL THAT FINDS COMPLEXITY HOTSPOTS IN YOUR CODEBASE! I made a Codex skill that analyzes your codebase and reports where performance can be improved safely. Scan your project while Codex checks loops, repeated lookups, render-heavy code, N+1 patterns, and places where complexity can potentially be reduced without breaking behavior. -> codebase complexity analysis -> O(n²), O(n*m), repeated scan detection -> before/after complexity estimates -> safe optimization suggestions -> risk level + tests needed -> report-only mode by default -> one-command install Install: npx --yes codex-complexity-optimizer 100% open source. Repo in Bio.

Teach your AI agents to create beautiful text animations. Exact specs wrapped as a skill - timings, curves, and effects. Library-agnostic, so it works with Remotion, Motion/GSAP, or plain JS/CSS. npx skills add pixel-point/animate-text --skill animate-text Example of usage: copy the name of the effect from the site and then /animate-text apply per-word-crossfade to the headline Link below:

Hermes Agent vs OpenClaw using Qwen 35B Local Model We asked agents to scrape GitHub star history for both tools, find what caused the growth spikes, build a live dashboard in the browser. MacBook Pro M5 Max 64Gb OpenClaw: 203k tokens, 12m 01s - wrote a bash script Hermes: 257k tokens, 33m 01s - wrote a SKILL.md OpenClaw hit GitHub API, got truncated responses, paginated through contributors, pulled star-history JSON, found a security incident in OpenClaw's history, fetched SVGs, fixed broken HTML from trimming, rewrote it clean. Hermes parallel tool calls across GitHub API, web search, and browser. Hit Google rate limit, auto-switched to DuckDuckGo. Fetched article contents, mapped viral moments, then built the dashboard. Both shipped a live dashboard with star growth charts and spike annotations

CODEX SKILL THAT TURNS LOCAL SEARCH INTO CLIENT LEADS! I made a Codex skill that helps find local businesses that may need a website. Search nearby shops, gyms, restaurants, salons, and local activities while Codex checks who has a real website and who only has socials. -> local business prospecting -> website vs social-only checks -> lead scoring -> phone/contact fields -> chat or CSV-style output -> one-command install Install: npx --yes local-client-prospector-skill 100% open source. Repo in Bio.

POV: The SuperSport cameraman finds the main character 😭⚽ The funniest part about these viral stadium cams is how RANDOMLY iconic they feel. So I recreated a live Brazil vs England SuperSport-style broadcast moment using @PixVerse_ and the realism is honestly ridiculous🔥 One World. One Goal. Created with PixVerse. ⚽✨ #WEARE26 #PixVerseChallenge #FIFAWorldCup 📌Check the prompts below👇🏾

Multi-Token Prediction (MTP) for Qwen on LLaMA.cpp! +40% performance! 90% acceptance rate. Running locally on a MacBook Pro M5 Max 64GB We patched LLaMA.cpp, quantized Qwen 3.6 27B into GGUF format with TurboQuant and shipped MTP drafts on top. Benchmark, Source code & models👇

We are continuing to invest in making agents work better on Windows. Highly recommend reading David's engineering post on our unique approach to windows sandboxing for Codex: https://openai.com/index/building-codex-windows-sandbox/

Just tried building a tiny Roblox game on @gg_lemonade with Step 3.5 Flash (free & unlimited). What I did: - Started with a basic collectible system that tracks points - Did a quick tweak - Made the collectibles respawn - Polished the map a bit to make it look nicer Nothing crazy, super beginner-friendly. It was pretty fun to see those prompts turn into a playable game loop, and you can keep adding new features from there. Prompts below 👇

Gossip Goblin is arguably the best AI filmmaker in the world. His new film THE PATCHWRIGHT is a masterpiece (10M+ views). But nobody knows how he actually makes these. Until now. He let me share every step of the workflow with you 🧵👇

Creating with Krea 2 🧵 First step: building a moodboard. Don't stress about filling all 250 image slots. Even 10–20 strong references are enough to establish a solid visual direction and already produce great results.

Introducing Renderers RL trainers work in tokens. Environments work in messages. Going back and forth corrupts sampled tokens, wasting compute on every agentic turn. With Renderers, we fix this mismatch. This unlocks >3x throughput on popular open models.