正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

With celld 0.4.1, you can run headless opencode sessions with ~20 lines of code! Create a session, prompt it, resume it later. SQLite-backed state, persisted to S3/GCS by celld. Amazing work from celld team again!

Daniel Lee

11,584 subscribers

33,810 次观看 • 3 天前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I experiment with Celld + RustFS + Deepseek v4 flash everything running on LOCAL and built this realtime multi agent collaboration platform for agents to collab and write some documents It can create 1 reviewer agent and two writer all powered by celld + rustfs + pi, you can see it working realtime by using websocket function from celld

I experiment with Celld + RustFS + Deepseek v4 flash everything running on LOCAL and built this realtime multi agent collaboration platform for agents to collab and write some documents It can create 1 reviewer agent and two writer all powered by celld + rustfs + pi, you can see it working realtime by using websocket function from celld

Farhan Helmy

35,118 次观看 • 1 个月前

Celld now supports Google Cloud Storage. You can deploy self-hosted Durable Objects on GCP with Cloud Run + GCS in minutes: ✅ Real-time WebSockets ✅ Scale up in seconds ✅ One-click IAP to protect your app behind Google SSO (my favorite!) Try it out:

Celld now supports Google Cloud Storage. You can deploy self-hosted Durable Objects on GCP with Cloud Run + GCS in minutes: ✅ Real-time WebSockets ✅ Scale up in seconds ✅ One-click IAP to protect your app behind Google SSO (my favorite!) Try it out:

Daniel Lee

22,781 次观看 • 27 天前

Seedance 2.0 is insane 🔥 A scene like this used to require a full CGI team, green screens, and weeks of post-production. Now you can create it with AI for a few dollars and just a few lines of prompt.

Seedance 2.0 is insane 🔥 A scene like this used to require a full CGI team, green screens, and weeks of post-production. Now you can create it with AI for a few dollars and just a few lines of prompt.

Heisenberg

37,800 次观看 • 6 个月前

VR shooter 💥 template generated by Grok and made with A-Frame 1.7.0. It runs at 90fps on Quest 3 🏃‍♂️🌬️ Just 127 lines of code, simple, self contained and straight from grok untouched. Prompt fits in a tweet. 5 attempts + small tweaks. Link to play right now, code and full prompt in comments A-Frame

VR shooter 💥 template generated by Grok and made with A-Frame 1.7.0. It runs at 90fps on Quest 3 🏃‍♂️🌬️ Just 127 lines of code, simple, self contained and straight from grok untouched. Prompt fits in a tweet. 5 attempts + small tweaks. Link to play right now, code and full prompt in comments A-Frame

Diego

74,118 次观看 • 1 年前

Go from blank slide to polished presentation faster with Canvas in Gemini. Now you can ask Gemini to “create a presentation” with a single prompt (and all your project notes). Try it out for yourself:

Go from blank slide to polished presentation faster with Canvas in Gemini. Now you can ask Gemini to “create a presentation” with a single prompt (and all your project notes). Try it out for yourself:

Google Gemini

25,467,513 次观看 • 10 个月前

Dexter just got a major upgrade. It now runs on WhatsApp. You can chat with Dexter from anywhere. How it works: • run Dexter locally • pair with QR code • chat like normal Ask about any stock and Dexter reads filings, pulls financials, and gets to work.

Dexter just got a major upgrade. It now runs on WhatsApp. You can chat with Dexter from anywhere. How it works: • run Dexter locally • pair with QR code • chat like normal Ask about any stock and Dexter reads filings, pulls financials, and gets to work.

Virat Singh

11,335 次观看 • 6 个月前

The easiest way to find out which models you can run on your computer: Just run: - 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 - 𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲 𝘀𝗲𝘁𝘂𝗽 It profiles your machine and ranks the models across: - Speed - Accuracy - Intelligence - Memory required Finally, you can choose your favorite harness (Pi, OpenCode, Claude Code, Codex, etc.) to run with it. Get started here: (don't forget to star 🌟) I also wrote a detailed article on running your favorite harnesses with local models. The article is quoted below.

The easiest way to find out which models you can run on your computer: Just run: - 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 - 𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲 𝘀𝗲𝘁𝘂𝗽 It profiles your machine and ranks the models across: - Speed - Accuracy - Intelligence - Memory required Finally, you can choose your favorite harness (Pi, OpenCode, Claude Code, Codex, etc.) to run with it. Get started here: (don't forget to star 🌟) I also wrote a detailed article on running your favorite harnesses with local models. The article is quoted below.

Akshay 🚀

350,436 次观看 • 6 天前

while Google AI Studio is the fastest path from prompt to app, as your team evolves, moving to a local development platform can help you with faster iterations developers, you can now export your AI Studio project and import it into @Antigravity with one click

while Google AI Studio is the fastest path from prompt to app, as your team evolves, moving to a local development platform can help you with faster iterations developers, you can now export your AI Studio project and import it into @Antigravity with one click

Google AI Studio

26,831 次观看 • 3 个月前

A while ago I had session in person with friend who is tist. It was amazing experience with a lot of fun (rapid inductions, transformations, freezing,..).I have content from that sessions that I plan to post on my JFF soon. Very little sample of the freezing. Do you want more?😁

Sensitive content

A while ago I had session in person with friend who is tist. It was amazing experience with a lot of fun (rapid inductions, transformations, freezing,..).I have content from that sessions that I plan to post on my JFF soon. Very little sample of the freezing. Do you want more?😁

Deep Shadow Boy

44,763 次观看 • 2 年前

Claude Fable can run autonomously for days. This is the single highest-leverage prompt I use to stay on top of it: "Spin up a persistent HTML page. As you work, append clear, timestamped updates with screenshots/media so I can follow along." Literally a 10x better experience.

Claude Fable can run autonomously for days. This is the single highest-leverage prompt I use to stay on top of it: "Spin up a persistent HTML page. As you work, append clear, timestamped updates with screenshots/media so I can follow along." Literally a 10x better experience.

Matt Shumer

263,543 次观看 • 3 个月前

Code Interpreter in ChatGPT is incredible! Took me 5 mins to make this game. You can make your own game assets with any AI generator and then ask GPT-4 with Code Interpreter to write code. If you have any problems you can ask it to fix the errors. 1. Write this prompt: "write p5.js code for Asteroids where you control a spaceship with the mouse and shoot asteroids with the left click of the mouse. If your spaceship collides with an asteroid, you lose. If you shoot down all asteroids, you win! I want to use my own textures for the spaceship and for asteroids." 2. Go to Openprocessing website create and save sketch (you'll need to save it before uploading any texture files). Copy paste code from GPT-4 3. Generate texture files and remove backgrounds, for example in Clip Drop 4. Replace names of files with your filenames 5. Run the program 6. If something doesn't work ask GPT-4 to fix it (you can copy an error and paste in GPT-4) like you would ask a human programmer 7. To learn a bit of programming write these prompts to GPT-4: "Act as my programming teacher. Tell me an algorithm of Asteroids game in detail and make names of functions and explain what each of these functions will do. Don't write the code just yet." and then " Can you describe the algorithm overall for a 10-year-old child"

Code Interpreter in ChatGPT is incredible! Took me 5 mins to make this game. You can make your own game assets with any AI generator and then ask GPT-4 with Code Interpreter to write code. If you have any problems you can ask it to fix the errors. 1. Write this prompt: "write p5.js code for Asteroids where you control a spaceship with the mouse and shoot asteroids with the left click of the mouse. If your spaceship collides with an asteroid, you lose. If you shoot down all asteroids, you win! I want to use my own textures for the spaceship and for asteroids." 2. Go to Openprocessing website create and save sketch (you'll need to save it before uploading any texture files). Copy paste code from GPT-4 3. Generate texture files and remove backgrounds, for example in Clip Drop 4. Replace names of files with your filenames 5. Run the program 6. If something doesn't work ask GPT-4 to fix it (you can copy an error and paste in GPT-4) like you would ask a human programmer 7. To learn a bit of programming write these prompts to GPT-4: "Act as my programming teacher. Tell me an algorithm of Asteroids game in detail and make names of functions and explain what each of these functions will do. Don't write the code just yet." and then " Can you describe the algorithm overall for a 10-year-old child"

Kris Kashtanova

1,675,286 次观看 • 3 年前

Building a harness to run scans with an agent. It is absolutely garbage. Completely useless. There’s literally 0 benefit to using it over plain Claude Code. Everything it can do, you can just do via Skills etc. Many were preaching the benefits of a harness, but I’m not sure.

Building a harness to run scans with an agent. It is absolutely garbage. Completely useless. There’s literally 0 benefit to using it over plain Claude Code. Everything it can do, you can just do via Skills etc. Many were preaching the benefits of a harness, but I’m not sure.

solst/ICE of Astarte

56,130 次观看 • 4 个月前

This is 2026 and some of you are still keeping money with someone? As in you’re waiting turn by turn to collect your money from someone who can run away with it? Anyways,Piggyvest has a message for these ladies

This is 2026 and some of you are still keeping money with someone? As in you’re waiting turn by turn to collect your money from someone who can run away with it? Anyways,Piggyvest has a message for these ladies

‘deola.

50,772 次观看 • 4 个月前

You won't believe it, but this AIApply video was made by Claude... ✨ One-shot prompt ✨ Claude code + Github + Remotion ✨ Taking elements straight from our codebase Imagine a world where a 1-person growth team can automate and deploy product content on any channel just by linking GitHub to LLMs...

You won't believe it, but this AIApply video was made by Claude... ✨ One-shot prompt ✨ Claude code + Github + Remotion ✨ Taking elements straight from our codebase Imagine a world where a 1-person growth team can automate and deploy product content on any channel just by linking GitHub to LLMs...

Yoann Pavy

86,837 次观看 • 7 个月前

You don’t need to run a store to earn from it Robots can scan groceries, restock shelves, and share profits with you and other co-owners The future of retail is autonomous, tokenized, and powered by people – on peaq

You don’t need to run a store to earn from it Robots can scan groceries, restock shelves, and share profits with you and other co-owners The future of retail is autonomous, tokenized, and powered by people – on peaq

peaq

58,157 次观看 • 10 个月前

Anyone telling you AI can one-prompt motion videos is bullshitting you Here's what it really takes to produce this kind of work: - Ideation: we have multiple people with years of editing and animation experience come up with ideas, pacing etc - Design: each animation gets designed by multiple professional product designers - Production: absolutely goated motion designers work together on it & art director is making sure that everything is hitting the quality standard One-prompt this, sure

Anyone telling you AI can one-prompt motion videos is bullshitting you Here's what it really takes to produce this kind of work: - Ideation: we have multiple people with years of editing and animation experience come up with ideas, pacing etc - Design: each animation gets designed by multiple professional product designers - Production: absolutely goated motion designers work together on it & art director is making sure that everything is hitting the quality standard One-prompt this, sure

leo

34,208 次观看 • 2 个月前