Загрузка видео...

Не удалось загрузить видео

На главную

first stable release for text-to-cad (0.1.0) - bambu labs + gcode skills (prompt to print) - 3x faster STEP builds, 5x faster viewer - plugins for codex, claude, gemini - tonnes of new viewer controls - contributor friendly repo (!!) about to cross 5000 stars, 20k downloads

earthtojake's profile picture

Jake Fitzgerald

5,824 subscribers

36,421 просмотров • 3 месяцев назад •via X (Twitter)

ИскусствоОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🔥We’re open-sourcing Multi-Agent CAD, a text-to-CAD pipeline that generates 3D assets for about $0.15 each—at roughly 1/13 the cost of CAD Skills, with faster inference and higher accuracy 🚀 This project began when our lab recruited Guanxing for his CAD expertise 🛠️ to build connected parts for robot learning project 🤖. He contributed far beyond modeling, combining strong CAD skills with agent-workflow design to help build the multi-agent pipeline. Code:
1:16

🔥We’re open-sourcing Multi-Agent CAD, a text-to-CAD pipeline that generates 3D assets for about $0.15 each—at roughly 1/13 the cost of CAD Skills, with faster inference and higher accuracy 🚀 This project began when our lab recruited Guanxing for his CAD expertise 🛠️ to build connected parts for robot learning project 🤖. He contributed far beyond modeling, combining strong CAD skills with agent-workflow design to help build the multi-agent pipeline. Code:

Xueyan Zou

121,624 просмотров • 27 дней назад

Introducing our new Turbo 2.5 model - Hindi, French, Spanish, Mandarin and 27 other languages just got 3x faster. This unlocks high-quality low-latency conversational AI for nearly 80% of the world. For the first time, we support Vietnamese, Hungarian and Norwegian text to speech. And English is now 25% faster compared to Turbo v2.
0:41

Introducing our new Turbo 2.5 model - Hindi, French, Spanish, Mandarin and 27 other languages just got 3x faster. This unlocks high-quality low-latency conversational AI for nearly 80% of the world. For the first time, we support Vietnamese, Hungarian and Norwegian text to speech. And English is now 25% faster compared to Turbo v2.

ElevenLabs

50,875 просмотров • 2 лет назад

The single-agent paradigm is obsolete. I’ve been testing LobeHub, and I have to say: LobeHub is the next generation of agent harness. Anyone can effortlessly build and team up with agent coworkers to deliver complex, systematic work.Manus and Claude Cowork stop at L3; LobeHub moves agents to L4. As shown in the video, the performance gap is significant: Vs Manus: LobeHub is ~3x faster and ~6.5x cheaper on complex tasks like Paper Analysis. Vs Claude Cowork: You get full multi-model support. Switch between Gemini, GPT, and Claude instantly without vendor lock-in. Through lobeHub community, anyone can discover, reuse and remix agent teammates and agent groups — customizing them to fit their own workflows and needs. As shown in the video: find a People Search agent in the community, remix the prompt, and swap the tools to level it up. Then you can paste an arXiv link → extract authors → find contacts → send outreach. Useful for VCs, HRs, and sales in talent sourcing. With 70k+ GitHub stars, 14k forks, 6M downloads, this is the new standard for autonomous workflows.
2:17

The single-agent paradigm is obsolete. I’ve been testing LobeHub, and I have to say: LobeHub is the next generation of agent harness. Anyone can effortlessly build and team up with agent coworkers to deliver complex, systematic work.Manus and Claude Cowork stop at L3; LobeHub moves agents to L4. As shown in the video, the performance gap is significant: Vs Manus: LobeHub is ~3x faster and ~6.5x cheaper on complex tasks like Paper Analysis. Vs Claude Cowork: You get full multi-model support. Switch between Gemini, GPT, and Claude instantly without vendor lock-in. Through lobeHub community, anyone can discover, reuse and remix agent teammates and agent groups — customizing them to fit their own workflows and needs. As shown in the video: find a People Search agent in the community, remix the prompt, and swap the tools to level it up. Then you can paste an arXiv link → extract authors → find contacts → send outreach. Useful for VCs, HRs, and sales in talent sourcing. With 70k+ GitHub stars, 14k forks, 6M downloads, this is the new standard for autonomous workflows.

Chubby♨️

13,277 просмотров • 7 месяцев назад

The 5 biggest AI leaks are on GitHub. Free. This wasn't supposed to end up online. 1. instructkr/claw-code, 195k ⭐️ stars A clean rewrite of the leaked Claude Code CLI. Got 100k stars in one day. Nobody has ever done that on GitHub. 2. x1xhlol/system-prompts-and-models-of-ai-tools, 143k ⭐️ stars 28 coding tools, with the JSON tool schemas. Not just the prompt text, the actual list of what each agent can touch. 3. asgeirtj/system_prompts_leaks, 63k ⭐️ stars The real prompts behind Claude Opus 5, GPT-5.6, Gemini 3.5, Grok and Cursor. Claude's is 3,677 lines long. The Washington Post ran a story off this repo. 4. elder-plinius/CL4R1T4S, 47k ⭐️ stars Same thing, every big lab in one place. Updated when new models ship. 5. Piebald-AI/claude-code-system-prompts, 12.4k ⭐️ stars Claude Code's prompt pulled from compiled source. 27 tool descriptions, subagent prompts, security review logic. The best prompt engineering course ever made is 5 free repos written by people who never meant to publish them. Saved it. Most of it is publicly available, but few people know about it 👇
1:04

The 5 biggest AI leaks are on GitHub. Free. This wasn't supposed to end up online. 1. instructkr/claw-code, 195k ⭐️ stars A clean rewrite of the leaked Claude Code CLI. Got 100k stars in one day. Nobody has ever done that on GitHub. 2. x1xhlol/system-prompts-and-models-of-ai-tools, 143k ⭐️ stars 28 coding tools, with the JSON tool schemas. Not just the prompt text, the actual list of what each agent can touch. 3. asgeirtj/system_prompts_leaks, 63k ⭐️ stars The real prompts behind Claude Opus 5, GPT-5.6, Gemini 3.5, Grok and Cursor. Claude's is 3,677 lines long. The Washington Post ran a story off this repo. 4. elder-plinius/CL4R1T4S, 47k ⭐️ stars Same thing, every big lab in one place. Updated when new models ship. 5. Piebald-AI/claude-code-system-prompts, 12.4k ⭐️ stars Claude Code's prompt pulled from compiled source. 27 tool descriptions, subagent prompts, security review logic. The best prompt engineering course ever made is 5 free repos written by people who never meant to publish them. Saved it. Most of it is publicly available, but few people know about it 👇

unicode

12,437 просмотров • 12 дней назад

Great news to start off the new financial year. Razorpay is now embedded natively inside OpenAI’s Codex, an industry-first for any Indian payments company. A developer prompts "build me a fitness app with a ₹499 one-time payment." Codex builds it. Razorpay handles the payments. No separate integration, no dashboard-hopping. If AI makes creation effortless, monetisation should be just as simple. India has 6 million developers & weekly Indian users of Codex 4x'd in two weeks this February. We’re building for this shift where more people can create, launch, and earn without friction. We have always enabled businesses so that their payments are smoother, easier, simpler & faster and Codex just got added to that already illustrious list.
1:27

Great news to start off the new financial year. Razorpay is now embedded natively inside OpenAI’s Codex, an industry-first for any Indian payments company. A developer prompts "build me a fitness app with a ₹499 one-time payment." Codex builds it. Razorpay handles the payments. No separate integration, no dashboard-hopping. If AI makes creation effortless, monetisation should be just as simple. India has 6 million developers & weekly Indian users of Codex 4x'd in two weeks this February. We’re building for this shift where more people can create, launch, and earn without friction. We have always enabled businesses so that their payments are smoother, easier, simpler & faster and Codex just got added to that already illustrious list.

Shashank Kumar

209,519 просмотров • 4 месяцев назад

We aren't ready for this next generation of agentic engineers. 100k Github stars in 24 hours (claw-code), Yeachan Heo (Bellman) has 3 to 5 pro accounts and ships software from telegram and discord. Those who accuse these guys of AI slop haven't done their homework because the real story is wild and vastly mis-understood. Yeachan has a background in quant trading and developed agentic systems to help with research (and says that LLMs aren't good for trading). He uses the term "agentic runtime" and uses CS principles to treat skills like pointers in memory. oh-my-codex was used to make the clean room clone of Claude Code...in 2 hours...on a plane...over text!! He developed this orchestration layer for Codex and it is powerful. It covers the entire SWE workflow like pipelines, persistent memory/state MCP servers, and extensible hooks. They aren't burning tokens for the sake of burning. I highly encourage you to look at the oh my codex repo and start extracting some of the ideas Bellman uses to ship software.
1:04

We aren't ready for this next generation of agentic engineers. 100k Github stars in 24 hours (claw-code), Yeachan Heo (Bellman) has 3 to 5 pro accounts and ships software from telegram and discord. Those who accuse these guys of AI slop haven't done their homework because the real story is wild and vastly mis-understood. Yeachan has a background in quant trading and developed agentic systems to help with research (and says that LLMs aren't good for trading). He uses the term "agentic runtime" and uses CS principles to treat skills like pointers in memory. oh-my-codex was used to make the clean room clone of Claude Code...in 2 hours...on a plane...over text!! He developed this orchestration layer for Codex and it is powerful. It covers the entire SWE workflow like pipelines, persistent memory/state MCP servers, and extensible hooks. They aren't burning tokens for the sake of burning. I highly encourage you to look at the oh my codex repo and start extracting some of the ideas Bellman uses to ship software.

Ray Fernando

59,092 просмотров • 4 месяцев назад

OpenAI just gave Codex a major upgrade. From a coding assistant into a workspace builder that can create interactive sites, apps, dashboards, planners, and review tools from plain work instructions. The most important new feature they released is "Sites". i.e. Codex can generate a hosted interactive workspace instead of only producing a document, spreadsheet, slide, or code file. OpenAI is also adding plugins for different jobs, so Codex knows how to help analysts, marketers, sales teams, product designers, investors, and bankers using the tools they already use. A data analyst might ask Codex to explain why sales dropped, then Codex could pull from data tools and create a dashboard. A sales team might ask Codex to prepare for a customer meeting, then Codex could collect account history, risks, follow-ups, and next steps into one shared page. The third feature is annotations, which means you can click a specific part of the result and ask Codex to fix only that part. Codex already reaches 5M weekly users, and OpenAI says 20% of them are now non-developers, with that group growing over 3x faster than developers.
0:43

OpenAI just gave Codex a major upgrade. From a coding assistant into a workspace builder that can create interactive sites, apps, dashboards, planners, and review tools from plain work instructions. The most important new feature they released is "Sites". i.e. Codex can generate a hosted interactive workspace instead of only producing a document, spreadsheet, slide, or code file. OpenAI is also adding plugins for different jobs, so Codex knows how to help analysts, marketers, sales teams, product designers, investors, and bankers using the tools they already use. A data analyst might ask Codex to explain why sales dropped, then Codex could pull from data tools and create a dashboard. A sales team might ask Codex to prepare for a customer meeting, then Codex could collect account history, risks, follow-ups, and next steps into one shared page. The third feature is annotations, which means you can click a specific part of the result and ask Codex to fix only that part. Codex already reaches 5M weekly users, and OpenAI says 20% of them are now non-developers, with that group growing over 3x faster than developers.

Rohan Paul

48,402 просмотров • 3 месяцев назад

QVAC SDK 0.12.0 is now live, bringing longer context, increased memory optimisation, new modalities, and broader ecosystem support directly to your device. Key Features and Updates: - TurboQuant KV-Cache Quantization: Fit much longer context in the same memory. TurboQuant, an algorithm from Google Research, compresses the KV cache by up to 5x, near-lossless. - Text-to-Video: Generate video from a text prompt, fully local, with the new wan2.1 model in the Diffusion addon - Apple Metal Performance for Flux2-klein: Diffusion on Apple Silicon now matches MLX performance, the native benchmark for Apple GPUs - Robot Control (new VLA addon): A GGML-based Vision-Language-Action addon brings fast, efficient robot control to edge devices - Coding Assistant / Harness Support: QVAC now works with OpenCode and OpenClaw as a local provider. A new @qvac/ai-sdk-provider package automates model registry and provider integration - Cross-Platform Voice: Text-to-speech and Parakeet transcription moved from ONNX to the GGML engine for better CPU and GPU support on macOS, iOS, Windows, Linux, and Android. Parakeet also adds long-term streaming diarization (tracking who spoke when on live audio) - Faster Lightweight Visual Classification: A new GGML-based Classification addon delivers millisecond-level classification, useful where a vision-language model (VLM) would be unnecessarily slow - Under the Hood: Fabric synced to llama.cpp v8828 (from v8189), plus GPU acceleration added to image-upscale models for faster results Full release notes:
1:29

QVAC SDK 0.12.0 is now live, bringing longer context, increased memory optimisation, new modalities, and broader ecosystem support directly to your device. Key Features and Updates: - TurboQuant KV-Cache Quantization: Fit much longer context in the same memory. TurboQuant, an algorithm from Google Research, compresses the KV cache by up to 5x, near-lossless. - Text-to-Video: Generate video from a text prompt, fully local, with the new wan2.1 model in the Diffusion addon - Apple Metal Performance for Flux2-klein: Diffusion on Apple Silicon now matches MLX performance, the native benchmark for Apple GPUs - Robot Control (new VLA addon): A GGML-based Vision-Language-Action addon brings fast, efficient robot control to edge devices - Coding Assistant / Harness Support: QVAC now works with OpenCode and OpenClaw as a local provider. A new @qvac/ai-sdk-provider package automates model registry and provider integration - Cross-Platform Voice: Text-to-speech and Parakeet transcription moved from ONNX to the GGML engine for better CPU and GPU support on macOS, iOS, Windows, Linux, and Android. Parakeet also adds long-term streaming diarization (tracking who spoke when on live audio) - Faster Lightweight Visual Classification: A new GGML-based Classification addon delivers millisecond-level classification, useful where a vision-language model (VLM) would be unnecessarily slow - Under the Hood: Fabric synced to llama.cpp v8828 (from v8189), plus GPU acceleration added to image-upscale models for faster results Full release notes:

QVAC

9,932,369 просмотров • 3 месяцев назад

Three months ago, Codex was trash for knowledge work. Now it's my daily driver. I use it for writing, recruiting, deep engineering work, and everything in between. It even keeps me at inbox 0. I chatted with Every 🧱's head of growth Austin Austin Tedesco on Every 🧱's AI & I about what changed, and why he now spends 80% of his working time in the Codex desktop app too. We get into: - How Codex went from making Austin feel like an idiot to being the place he goes to get stuff done, including complex tasks like writing go-to-market plans using existing material from Slack, Notion, and meeting transcripts. - Why the Codex’s desktop app, which is faster and more reliable than Claude Desktop/Cowork, is the real differentiator. - How I source candidates with Codex by having it identify career arcs, not keywords—my go-to move is identifying organizations likely to teach the skills Every needs for a role, and then find candidates from that pool who have since gone on to work in AI. This is a must-watch for anyone who's wondering whether it’s finally time to give Codex a try. Watch below! Timestamps How Codex went from a tool for senior engineers to a daily driver for knowledge work: 00:00:57 How Claude Code proved that a great coding agent works for any knowledge work: 00:02:42 Austin's switch to Codex: 00:07:24 How Austin set up Codex with folders, keys, and reviewer agents: 00:13:48 Using Codex to brainstorm automations across Gmail, Slack, and Notion: 00:18:24 How Austin manages the human review step when Codex is drafting communications: 00:22:42 Using Codex to build specialized agents inspired by product executive Claire Vo: 00:28:54 Synthesizing meeting transcripts and Slack threads into a go-to-market plan: 00:31:09 Building a live KPI tracker in Notion that agents can read: 00:40:15 Using Codex for recruiting: 00:44:54
58:23

Three months ago, Codex was trash for knowledge work. Now it's my daily driver. I use it for writing, recruiting, deep engineering work, and everything in between. It even keeps me at inbox 0. I chatted with Every 🧱's head of growth Austin Austin Tedesco on Every 🧱's AI & I about what changed, and why he now spends 80% of his working time in the Codex desktop app too. We get into: - How Codex went from making Austin feel like an idiot to being the place he goes to get stuff done, including complex tasks like writing go-to-market plans using existing material from Slack, Notion, and meeting transcripts. - Why the Codex’s desktop app, which is faster and more reliable than Claude Desktop/Cowork, is the real differentiator. - How I source candidates with Codex by having it identify career arcs, not keywords—my go-to move is identifying organizations likely to teach the skills Every needs for a role, and then find candidates from that pool who have since gone on to work in AI. This is a must-watch for anyone who's wondering whether it’s finally time to give Codex a try. Watch below! Timestamps How Codex went from a tool for senior engineers to a daily driver for knowledge work: 00:00:57 How Claude Code proved that a great coding agent works for any knowledge work: 00:02:42 Austin's switch to Codex: 00:07:24 How Austin set up Codex with folders, keys, and reviewer agents: 00:13:48 Using Codex to brainstorm automations across Gmail, Slack, and Notion: 00:18:24 How Austin manages the human review step when Codex is drafting communications: 00:22:42 Using Codex to build specialized agents inspired by product executive Claire Vo: 00:28:54 Synthesizing meeting transcripts and Slack threads into a go-to-market plan: 00:31:09 Building a live KPI tracker in Notion that agents can read: 00:40:15 Using Codex for recruiting: 00:44:54

Dan Shipper 📧

55,561 просмотров • 3 месяцев назад

From managing people to managing AI with Julie Zhuo (Julie Zhuo) In a very special episode, my first-ever podcast guest returns (3 years and over 30M downloads later!) to explain why everyone's about to become a manager—of AI. Spoiler: The skills that make you a great manager also make you great at AI. In our conversation, we discuss: 🔸 The three core manager skills that translate directly to working with AI tools 🔸 Why her startup has zero PMs 🔸 How her team at Sundial uses AI to learn new skills 10x faster 🔸 The “diagnose with data, treat with design” framework for balancing instinct and data 🔸 How to give feedback that actually lands—including Julie’s exact script for difficult conversations Listen now 👇 • YouTube: • Spotify: • Apple: Thank you to our wonderful sponsors for supporting the podcast: 🏆 Mercury—The art of simplified finances: 🏆 DX—The developer intelligence platform designed by leading researchers: 🏆 PostHog—How developers build successful products:
1:29

From managing people to managing AI with Julie Zhuo (Julie Zhuo) In a very special episode, my first-ever podcast guest returns (3 years and over 30M downloads later!) to explain why everyone's about to become a manager—of AI. Spoiler: The skills that make you a great manager also make you great at AI. In our conversation, we discuss: 🔸 The three core manager skills that translate directly to working with AI tools 🔸 Why her startup has zero PMs 🔸 How her team at Sundial uses AI to learn new skills 10x faster 🔸 The “diagnose with data, treat with design” framework for balancing instinct and data 🔸 How to give feedback that actually lands—including Julie’s exact script for difficult conversations Listen now 👇 • YouTube: • Spotify: • Apple: Thank you to our wonderful sponsors for supporting the podcast: 🏆 Mercury—The art of simplified finances: 🏆 DX—The developer intelligence platform designed by leading researchers: 🏆 PostHog—How developers build successful products:

Lenny Rachitsky

183,085 просмотров • 11 месяцев назад

BREAKING 🚨 Anthropic just unveiled "Cowork," a major feature that turns Claude into a fully autonomous virtual assistant for everyone. It brings the deep agentic capabilities previously reserved for coders to general users, allowing Claude to perform complex tasks directly on your computer. The tool was built after Anthropic noticed developers using "Claude Code" for everyday admin tasks. Cowork now lets anyone grant Claude access to folders to manage files, research, and complete multi-step workflows independently acting as a digital employee that "does" instead of just chats. Cowork is available today as a research preview for Claude Max subscribers on the macOS app 😡. Claude is releasing new coding/desktop agents much faster than all of there competitors. This launch exposes a massive gap in the current AI landscape: in 2026, Google still explicitly lacks a consumer browser agent, and xAI has yet to release a native CLI or agentic interface. While OpenAI has "Operator" and Google has the developer-focused "Antigravity," Anthropic is now the only other major lab providing a true "do-it-for-me" experience for general users.
0:31

BREAKING 🚨 Anthropic just unveiled "Cowork," a major feature that turns Claude into a fully autonomous virtual assistant for everyone. It brings the deep agentic capabilities previously reserved for coders to general users, allowing Claude to perform complex tasks directly on your computer. The tool was built after Anthropic noticed developers using "Claude Code" for everyday admin tasks. Cowork now lets anyone grant Claude access to folders to manage files, research, and complete multi-step workflows independently acting as a digital employee that "does" instead of just chats. Cowork is available today as a research preview for Claude Max subscribers on the macOS app 😡. Claude is releasing new coding/desktop agents much faster than all of there competitors. This launch exposes a massive gap in the current AI landscape: in 2026, Google still explicitly lacks a consumer browser agent, and xAI has yet to release a native CLI or agentic interface. While OpenAI has "Operator" and Google has the developer-focused "Antigravity," Anthropic is now the only other major lab providing a true "do-it-for-me" experience for general users.

Chris

502,372 просмотров • 7 месяцев назад

Announcing the latest release from Qodo: Modern engineering runs across hundreds of repos, dozens of teams, and AI that writes code faster than anyone can review it. Today, Qodo releases features built for these teams. - Cross Repo Review: Qodo now maps dependencies across your repos and catches breaking changes before they merge. A change to a shared SDK, API contract, or database schema no longer ships before anyone knows it broke something downstream. - Rules Miner: Qodo analyzes your PR review history, recurring comments, accepted vs. rejected suggestions, and reviewer patterns, and turns them into enforceable rules. The standards that lived in senior engineers' heads are now in the system. - Skill Review Standards: Skills are now a managed entity in Qodo, with visibility, governance controls, and per-skill analytics. The instructions encoding how your team builds software are visible to the people responsible for enforcing them. All of these features are now available in BETA. Sign up for a 14-day free trial.
2:04

Announcing the latest release from Qodo: Modern engineering runs across hundreds of repos, dozens of teams, and AI that writes code faster than anyone can review it. Today, Qodo releases features built for these teams. - Cross Repo Review: Qodo now maps dependencies across your repos and catches breaking changes before they merge. A change to a shared SDK, API contract, or database schema no longer ships before anyone knows it broke something downstream. - Rules Miner: Qodo analyzes your PR review history, recurring comments, accepted vs. rejected suggestions, and reviewer patterns, and turns them into enforceable rules. The standards that lived in senior engineers' heads are now in the system. - Skill Review Standards: Skills are now a managed entity in Qodo, with visibility, governance controls, and per-skill analytics. The instructions encoding how your team builds software are visible to the people responsible for enforcing them. All of these features are now available in BETA. Sign up for a 14-day free trial.

Qodo

632,227 просмотров • 2 месяцев назад

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:
1:21

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,089 просмотров • 2 месяцев назад

There is a strategy for Claude Max users that will 3-5X productivity and vibe coding learning curve. Which most vibe coders don't utilize! Most people using Claude Code just sit and watch the terminal while their prompt cooks. That’s dead time. If you’re on Claude Max, you’re paying for parallel capacity you’re probably not using fully. And tokens get wasted. Here’s a methodology to fix that and boost the way you use Claude forever: The Setup & Workflow 1. Add the repos you’re actively working on to your workspace from your IDE 2. Click “new terminal” and open 3-4 terminal instances, each pointed at a different project 3. Toggle between them on the right side of your terminal panel 4. When one terminal is cooking a prompt, look at the others 5. Use the time Claude is working to prompt the next project 6. Continuously rotate and ship across 3-4 projects like this 7. Use your tokens effectively, build more, learn faster The Result You ship 3-4 projects simultaneously. You burn through your token allocation on actual output instead of letting it sit unused. You learn faster because you’re getting more reps in the same amount of time, too. As long as you work on different projects at the same time like this, it will only be a boost in productivity, with no chance for code to get spaghetti. In the video, you can see where to find add workspace, run new terminal, and change between terminals:
0:20

There is a strategy for Claude Max users that will 3-5X productivity and vibe coding learning curve. Which most vibe coders don't utilize! Most people using Claude Code just sit and watch the terminal while their prompt cooks. That’s dead time. If you’re on Claude Max, you’re paying for parallel capacity you’re probably not using fully. And tokens get wasted. Here’s a methodology to fix that and boost the way you use Claude forever: The Setup & Workflow 1. Add the repos you’re actively working on to your workspace from your IDE 2. Click “new terminal” and open 3-4 terminal instances, each pointed at a different project 3. Toggle between them on the right side of your terminal panel 4. When one terminal is cooking a prompt, look at the others 5. Use the time Claude is working to prompt the next project 6. Continuously rotate and ship across 3-4 projects like this 7. Use your tokens effectively, build more, learn faster The Result You ship 3-4 projects simultaneously. You burn through your token allocation on actual output instead of letting it sit unused. You learn faster because you’re getting more reps in the same amount of time, too. As long as you work on different projects at the same time like this, it will only be a boost in productivity, with no chance for code to get spaghetti. In the video, you can see where to find add workspace, run new terminal, and change between terminals:

Meta Alchemist

82,000 просмотров • 7 месяцев назад

Motion graphics were always the hardest part of making videos for me. Hours in After Effects for 10 seconds of movement. Now I can do them 10x faster without touching a timeline or writing a single line of code. Remotion released a skill that lets Claude Code create videos programmatically. I spent 5 hours building with it so I could show you exactly how it works. What's in the guide: - Installing the Remotion skill (takes 2 minutes) - Creating your first video scene by scene - Auto-editing long videos into clips - Adding animated captions and subtitles - Reframing for TikTok/Reels/Shorts - Stacking multiple skills into a mini production studio This is for content creators, marketers and GTM engineers who want to create more videos, better and faster, without learning video editing software or code. I recorded the full walkthrough. Every step. 👇 Comment "GUIDE" and I'll DM you the repo with all of the skills installed + getting started guide. (Make sure we're connected so I can DM you)
22:35

Motion graphics were always the hardest part of making videos for me. Hours in After Effects for 10 seconds of movement. Now I can do them 10x faster without touching a timeline or writing a single line of code. Remotion released a skill that lets Claude Code create videos programmatically. I spent 5 hours building with it so I could show you exactly how it works. What's in the guide: - Installing the Remotion skill (takes 2 minutes) - Creating your first video scene by scene - Auto-editing long videos into clips - Adding animated captions and subtitles - Reframing for TikTok/Reels/Shorts - Stacking multiple skills into a mini production studio This is for content creators, marketers and GTM engineers who want to create more videos, better and faster, without learning video editing software or code. I recorded the full walkthrough. Every step. 👇 Comment "GUIDE" and I'll DM you the repo with all of the skills installed + getting started guide. (Make sure we're connected so I can DM you)

JJ Englert

143,339 просмотров • 7 месяцев назад

"I've spent $30K on a launch video, now you can make one with code." Here's my new episode with Bin Liu and Jake Moran, where they shared their 5-step playbook for using HyperFrames to make professional launch videos in Codex and Claude Code: 1. Gather video assets and create a frame.md 2. Create a storyboard.md with the scenes 3. Pull animations from the HyperFrames repo 4. Generate and review static frames 5. Build the video with HyperFrames Studio You can also start simple by using the built-in /website-to-video skill to one shot a launch video from any URL. HyperFrames is 100% free and I love how it democratizes video creation for everyone. 📌 Watch now: Thanks to our sponsors: Wispr Flow: 4x faster than typing with your voice Riverside: All-in-one AI studio for podcasts and video
0:43

"I've spent $30K on a launch video, now you can make one with code." Here's my new episode with Bin Liu and Jake Moran, where they shared their 5-step playbook for using HyperFrames to make professional launch videos in Codex and Claude Code: 1. Gather video assets and create a frame.md 2. Create a storyboard.md with the scenes 3. Pull animations from the HyperFrames repo 4. Generate and review static frames 5. Build the video with HyperFrames Studio You can also start simple by using the built-in /website-to-video skill to one shot a launch video from any URL. HyperFrames is 100% free and I love how it democratizes video creation for everyone. 📌 Watch now: Thanks to our sponsors: Wispr Flow: 4x faster than typing with your voice Riverside: All-in-one AI studio for podcasts and video

Peter Yang

68,646 просмотров • 2 месяцев назад

“We’ve got /loop, /goal, and workflows. They all get the agent to run for long periods of time.” Here’s my new episode with Thariq from the Claude Code team, where he shared how he plans, builds, and runs loops with Claude Code: → How /loop, /goal, and workflows work differently → Live demo: Editing launch videos with Claude → Using HTML artifacts to plan and learn Some quotes from Thariq: “We cut Claude Code’s system prompt by 80%. As models have gotten smarter, they need less direction, fewer constraints, and fewer examples.” “Planning is an iterative process of exploring, investigating, and finding out what you don’t know.” “One failure mode I see is that people glaze over AI’s plans. You want to make sure it’s something you read.” I've been wanting to interview Thariq for a long time and I learned so much from this epsiode. 📌 Watch now: Thanks to our sponsors: Riverside: All-in-one AI studio for podcasts and video Wispr Flow: 4x faster than typing with your voice
0:27

“We’ve got /loop, /goal, and workflows. They all get the agent to run for long periods of time.” Here’s my new episode with Thariq from the Claude Code team, where he shared how he plans, builds, and runs loops with Claude Code: → How /loop, /goal, and workflows work differently → Live demo: Editing launch videos with Claude → Using HTML artifacts to plan and learn Some quotes from Thariq: “We cut Claude Code’s system prompt by 80%. As models have gotten smarter, they need less direction, fewer constraints, and fewer examples.” “Planning is an iterative process of exploring, investigating, and finding out what you don’t know.” “One failure mode I see is that people glaze over AI’s plans. You want to make sure it’s something you read.” I've been wanting to interview Thariq for a long time and I learned so much from this epsiode. 📌 Watch now: Thanks to our sponsors: Riverside: All-in-one AI studio for podcasts and video Wispr Flow: 4x faster than typing with your voice

Peter Yang

186,950 просмотров • 1 месяц назад

BREAKING: Did Polymarket just silently nuke the 500ms taker delay? Rumor has it the speed bump on crypto markets is GONE. No announcement, no changelog, nothing. The crazy part? It was never officially documented in the first place. I literally only found proof of its existence buried in a 3rd-party GitHub repo code Why this matters: - Takers/aggressive bots: You're eating MUCH faster now, which is great... if your latency is good - Makers/liquidity providers: You're about to get picked off way more often. RIP to anyone not updating quotes constantly - Arbitrage: The game just got 500ms faster. May the lowest-latency chad win Traders are already claiming they got wrecked overnight. Unless you asked Claude to update your OpenClaw configs for zero-latency, you are probably getting farmed right now See the execution speed for yourself:
0:47

BREAKING: Did Polymarket just silently nuke the 500ms taker delay? Rumor has it the speed bump on crypto markets is GONE. No announcement, no changelog, nothing. The crazy part? It was never officially documented in the first place. I literally only found proof of its existence buried in a 3rd-party GitHub repo code Why this matters: - Takers/aggressive bots: You're eating MUCH faster now, which is great... if your latency is good - Makers/liquidity providers: You're about to get picked off way more often. RIP to anyone not updating quotes constantly - Arbitrage: The game just got 500ms faster. May the lowest-latency chad win Traders are already claiming they got wrecked overnight. Unless you asked Claude to update your OpenClaw configs for zero-latency, you are probably getting farmed right now See the execution speed for yourself:

BuBBliK

110,516 просмотров • 6 месяцев назад

Presto! Distilling Steps and Layers for Accelerating Music Generation Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both sampling steps and cost per step. To reduce steps, we develop a new score-based distribution matching distillation (DMD) method for the EDM-family of diffusion models, the first GAN-based distillation method for TTM. To reduce the cost per step, we develop a simple, but powerful improvement to a recent layer distillation method that improves learning via better preserving hidden state variance. Finally, we combine our step and layer distillation methods together for a dual-faceted approach. We evaluate our step and layer distillation methods independently and show each yield best-in-class performance. Our combined distillation method can generate high-quality outputs with improved diversity, accelerating our base model by 10-18x (230/435ms latency for 32 second mono/stereo 44.1kHz, 15x faster than comparable SOTA) -- the fastest high-quality TTM to our knowledge.
1:20

Presto! Distilling Steps and Layers for Accelerating Music Generation Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both sampling steps and cost per step. To reduce steps, we develop a new score-based distribution matching distillation (DMD) method for the EDM-family of diffusion models, the first GAN-based distillation method for TTM. To reduce the cost per step, we develop a simple, but powerful improvement to a recent layer distillation method that improves learning via better preserving hidden state variance. Finally, we combine our step and layer distillation methods together for a dual-faceted approach. We evaluate our step and layer distillation methods independently and show each yield best-in-class performance. Our combined distillation method can generate high-quality outputs with improved diversity, accelerating our base model by 10-18x (230/435ms latency for 32 second mono/stereo 44.1kHz, 15x faster than comparable SOTA) -- the fastest high-quality TTM to our knowledge.

AK

30,442 просмотров • 1 год назад

The number one question I get in the Claude Code / Cowork Community: "how do I share my Cowork skills with my team?" Here's the problem. You build a great skill. You zip it up. You drop it in Slack. Your teammate downloads it, uploads it, and maybe it works. Maybe they upload it wrong. Maybe you update the skill next week and nobody gets the new version. You're now maintaining skills through chat messages and hoping for the best. That doesn't scale. I just put out a video breaking down the three methods I've tested for sharing skills and plugins across a team. From dead simple to fully synced. Method 1: Shared drive (Google Drive, SharePoint, etc). You put your skill files in a shared folder. Teammates download and upload them into Cowork. It works, but updates are manual and there's no version control. Method 2: Built-in sharing on Team and Enterprise plans. You can share any skill directly with a colleague or publish it to your org directory. When you update the skill, everyone gets the update automatically. This is the easiest path if you're on a paid plan. The catch: there's no approval workflow for org-wide sharing, so set a clear owner. Method 3: GitHub repo. This is what I use. Your entire Cowork workspace -- skills, plugins, claude.md, folder structure, project files -- lives in a private repo. Teammates clone it. When you push an update, they pull it. Everyone stays in sync. You get version history, access control, and a single source of truth. The GitHub method sounds technical, but it's really just two steps: clone the repo, point Cowork at the folder. I walk through the whole thing in the video, including how to use .gitignore to keep personal files (like your morning briefing) out of the shared repo. This works for Cowork, Claude Code, and Open Codex. The infrastructure is the same. Full video linked below. If you've found a different approach that works for your team, I want to hear about it. Comment or reply and let's figure out the best practices together.
0:51

The number one question I get in the Claude Code / Cowork Community: "how do I share my Cowork skills with my team?" Here's the problem. You build a great skill. You zip it up. You drop it in Slack. Your teammate downloads it, uploads it, and maybe it works. Maybe they upload it wrong. Maybe you update the skill next week and nobody gets the new version. You're now maintaining skills through chat messages and hoping for the best. That doesn't scale. I just put out a video breaking down the three methods I've tested for sharing skills and plugins across a team. From dead simple to fully synced. Method 1: Shared drive (Google Drive, SharePoint, etc). You put your skill files in a shared folder. Teammates download and upload them into Cowork. It works, but updates are manual and there's no version control. Method 2: Built-in sharing on Team and Enterprise plans. You can share any skill directly with a colleague or publish it to your org directory. When you update the skill, everyone gets the update automatically. This is the easiest path if you're on a paid plan. The catch: there's no approval workflow for org-wide sharing, so set a clear owner. Method 3: GitHub repo. This is what I use. Your entire Cowork workspace -- skills, plugins, claude.md, folder structure, project files -- lives in a private repo. Teammates clone it. When you push an update, they pull it. Everyone stays in sync. You get version history, access control, and a single source of truth. The GitHub method sounds technical, but it's really just two steps: clone the repo, point Cowork at the folder. I walk through the whole thing in the video, including how to use .gitignore to keep personal files (like your morning briefing) out of the shared repo. This works for Cowork, Claude Code, and Open Codex. The infrastructure is the same. Full video linked below. If you've found a different approach that works for your team, I want to hear about it. Comment or reply and let's figure out the best practices together.

JJ Englert

16,176 просмотров • 4 месяцев назад