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。

Introducing Scheduled Tasks. Continuous Integration meets Continuous AI. Set the frequency: nightly package releases, weekly dependency updates, or monthly backlog sweeps. Jules not only can publish the release but can fix any errors while doing it, all in background while you focus on what matters (or get some sleep).... show more

Jules

32,142 subscribers

69,362 次观看 • 9 个月前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

22 条评论

Jules 的头像

Jules9 个月前

Learn more on our changelog:

Leon Lin 的头像

Leon Lin9 个月前

woahhh why are there so many new features dropping today 🔥🔥

Jules 的头像

Jules9 个月前

@LexnL89916 Happy Shipmas

Leon Lin 的头像

Leon Lin9 个月前

happy shipmas back! 💙

David Mansaray 👨🏾‍💻 的头像

David Mansaray 👨🏾‍💻9 个月前

This is huge ! Thank you !

jack 的头像

jack9 个月前

oh this is quite a nice one

Tanuki The Dev 的头像

Tanuki The Dev9 个月前

This is an excellent feature! Being able to continuously provide important information like dependency updates and backlog sweeps is really valuable. It would be cool if we could also choose which model to use for the implementation like Antigravity do, I'd leave it to Opus 4.5 or Codex 5.1

Digital Adam 的头像

Digital Adam9 个月前

@simpsoka Ok I gotta admit this is pretty novel. Well done.

Vijar Kohli 的头像

Vijar Kohli9 个月前

woah this is a brilliant feature. thank you!

Conan 的头像

Conan9 个月前

Brilliant new shipment 🚚

Trey Griffin 的头像

Trey Griffin9 个月前

This is actually cool.

⚡️Mirthtime ⚡️ 的头像

⚡️Mirthtime ⚡️9 个月前

Wow you guys are relentless

Pietro Montaldo 的头像

Pietro Montaldo9 个月前

Continuous AI just got easier

Yusuf Adeyemo 的头像

Yusuf Adeyemo9 个月前

The 'get some sleep' part of this update is the real MVP feature. 😅 Having an agent handle dependency updates and backlog sweeps in the background and fixing its own breakages exactly the kind of automation I need.

The Longer Game 的头像

The Longer Game9 个月前

Scheduled tasks are exactly the kind of workflow boost teams need when juggling releases and maintenance. Being able to hand off routine jobs like package updates and backlog cleanup, and having the agent fix issues along the way, takes a big load off the engineering cycle.

Saïd Aitmbarek 的头像

Saïd Aitmbarek9 个月前

let's go guys! definitely on next weekend's shortlist would love to explore a collab w/ @microlaunchhq btw (builders events/challenges, hackathons)

Himanshu Kumar 的头像

Himanshu Kumar9 个月前

Wow, that's some impressive automation, Jules; I wonder if it's truly error-proof, though!

Chukwuemeka John 的头像

Chukwuemeka John9 个月前

Jules is all you need 😁. Please do you have a YouTube channel that demonstrates all these use cases in real time?

Ging Freecss 的头像

Ging Freecss9 个月前

Kindly add a chat with the git repo. Before planning with Jules, I wish to talk about it and get clarification, so it would be great.

sjsjsj 的头像

sjsjsj9 个月前

Notification functionality is not working on jules chrome browser (android). @julesagent can you please fix that. Because I don't get any notification after task completion which waste my time more.

Galin Denev 的头像

Galin Denev9 个月前

I have ultra on my account from workspace and says i dont have plan?!?!

Arjun Krishna 的头像

Arjun Krishna9 个月前

@amitavkrshna

相关视频

Nightly used to suck because I couldn't use Optimism... Or Arbitrum... Or MovementLabs EVM... or any of the others. You get it. But not anymore! We're proud to announce that from now on, you can enjoy EVMs on Nightly—all in one place! But what does this mean?👇

Nightly used to suck because I couldn't use Optimism... Or Arbitrum... Or MovementLabs EVM... or any of the others. You get it. But not anymore! We're proud to announce that from now on, you can enjoy EVMs on Nightly—all in one place! But what does this mean?👇

Nightly

46,925 次观看 • 2 年前

🧵5/5 In the coming months, we’ll be introducing agentic capabilities to Gemini in Chrome so it can handle those tedious tasks that take up so much of your time, like booking a haircut or ordering your weekly groceries. You tell Gemini what you want to get done, and it can take action on web pages on your behalf while you focus on other things. It can be stopped at any time so you’re in control.

🧵5/5 In the coming months, we’ll be introducing agentic capabilities to Gemini in Chrome so it can handle those tedious tasks that take up so much of your time, like booking a haircut or ordering your weekly groceries. You tell Gemini what you want to get done, and it can take action on web pages on your behalf while you focus on other things. It can be stopped at any time so you’re in control.

Google AI

40,681 次观看 • 1 年前

Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation. Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)

Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation. Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)

Poe

22,015 次观看 • 10 个月前

Introducing Scheduled Tasks 2.0 — a major upgrade to recurring work in Manus. Scheduling is no longer just about running something at the right time. It is about running it in the right place, with the right context. Now scheduled work can continue in the same task, power background actions in Manus-built web apps, and give you clearer visibility into upcoming and past runs. Available now to all users.

Introducing Scheduled Tasks 2.0 — a major upgrade to recurring work in Manus. Scheduling is no longer just about running something at the right time. It is about running it in the right place, with the right context. Now scheduled work can continue in the same task, power background actions in Manus-built web apps, and give you clearer visibility into upcoming and past runs. Available now to all users.

Manus

96,174 次观看 • 4 个月前

Introducing arcads ai hook generator this hook generated over 100M views… recreate it... or ANY HOOK using Arcads AI Latest update Available TODAY for all users! We created a library of the most viral hooks ready for you to steal: comment "hook generator" to get it

Introducing arcads ai hook generator this hook generated over 100M views… recreate it... or ANY HOOK using Arcads AI Latest update Available TODAY for all users! We created a library of the most viral hooks ready for you to steal: comment "hook generator" to get it

arcads AI

193,275 次观看 • 10 个月前

Most teams governing AI agents focus on what they can access. The harder problem is what they can do with it. Box MCP Server admin controls let admins govern tool access enterprise-wide or per AI integration, set read-only or read-and-write permissions, and configure down to the individual tool level. When a tool is disabled, agents can no longer discover or invoke it. Enforced at runtime, not just at setup.

Most teams governing AI agents focus on what they can access. The harder problem is what they can do with it. Box MCP Server admin controls let admins govern tool access enterprise-wide or per AI integration, set read-only or read-and-write permissions, and configure down to the individual tool level. When a tool is disabled, agents can no longer discover or invoke it. Enforced at runtime, not just at setup.

Box

389,154 次观看 • 1 个月前

Serious one today, they made me stand infront of camera. Anyone's who's left knows how much of a ballache transition can be. Too many orgnaisations not doing very much. I've been working on this Johnny and Ben, who makes AI stuff, to try and sort some of the issues in the space. Have a look, let me know any questions or feedback. Essentially has all the support available and jobs, while sorting it all with AI so it's actually relevant.

Serious one today, they made me stand infront of camera. Anyone's who's left knows how much of a ballache transition can be. Too many orgnaisations not doing very much. I've been working on this Johnny and Ben, who makes AI stuff, to try and sort some of the issues in the space. Have a look, let me know any questions or feedback. Essentially has all the support available and jobs, while sorting it all with AI so it's actually relevant.

fill your boots

28,999 次观看 • 1 年前

We just killed paid AI workspaces. Introducing robinhood:0xa92768863a55d8a0591709f7f5e594a249d36ea3 Collab. Work in groups of up to 12 people, share the same stream of knowledge, AI and workload. Make as many sessions and topics as you want in any collab workspace. Free to enter, only pay for the credits you use. Anyone in the collab can make a prompt, and anyone can top up the collab balance. No more middle manning prompts or information. Anyone can finish the code, fix an image, or any job. Any AI model you want sits in that chat and listens when you tag Fadi. Build something professional, or just have a group chat with an AI ready to generate memes as you want. Collab is for everyone. Collab beta is live to all users on just invite your friends @ to get started.

We just killed paid AI workspaces. Introducing robinhood:0xa92768863a55d8a0591709f7f5e594a249d36ea3 Collab. Work in groups of up to 12 people, share the same stream of knowledge, AI and workload. Make as many sessions and topics as you want in any collab workspace. Free to enter, only pay for the credits you use. Anyone in the collab can make a prompt, and anyone can top up the collab balance. No more middle manning prompts or information. Anyone can finish the code, fix an image, or any job. Any AI model you want sits in that chat and listens when you tag Fadi. Build something professional, or just have a group chat with an AI ready to generate memes as you want. Collab is for everyone. Collab beta is live to all users on just invite your friends @ to get started.

Askr

40,052 次观看 • 5 天前

You’re already training Big Tech’s AI models. So why aren’t you getting compensated for it? With Action Model you can download our browser extension and train AI passively in the background or by completing ActionFi tasks, while earning rewards and ownership in the model itself. This is what the future of AI should look like. Ownership back in the hands of the people who help build it, not billionaire control.

You’re already training Big Tech’s AI models. So why aren’t you getting compensated for it? With Action Model you can download our browser extension and train AI passively in the background or by completing ActionFi tasks, while earning rewards and ownership in the model itself. This is what the future of AI should look like. Ownership back in the hands of the people who help build it, not billionaire control.

Action Model

26,415 次观看 • 5 个月前

Built something with the goal of not leaving anyone behind. Now need some testers for this soft-launch. Check it out at Build whatever you can think of. Don't have any ideas? Just talk with your new team. Designed to get you away from the screens, not glued to them. Works great on mobile. Full real world capabilities. The free tier is perfect for people looking to get into AI and learn what its all about. The 'Empir3 Bridge' is for more advanced users and can power the whole empir3 team with your AI subscriptions... Grok, Claude, OpenAI, Google, or your local LLM. Everything runs local making it TOS friendly. Make them all work together in that same session. Fully opensource on GitHub You can use it with or without empir3. Full MCP, just point your AI at that repo and it will set it up. MIT license. New features weekly. *limited space and time until providers give me more channels.

Built something with the goal of not leaving anyone behind. Now need some testers for this soft-launch. Check it out at Build whatever you can think of. Don't have any ideas? Just talk with your new team. Designed to get you away from the screens, not glued to them. Works great on mobile. Full real world capabilities. The free tier is perfect for people looking to get into AI and learn what its all about. The 'Empir3 Bridge' is for more advanced users and can power the whole empir3 team with your AI subscriptions... Grok, Claude, OpenAI, Google, or your local LLM. Everything runs local making it TOS friendly. Make them all work together in that same session. Fully opensource on GitHub You can use it with or without empir3. Full MCP, just point your AI at that repo and it will set it up. MIT license. New features weekly. *limited space and time until providers give me more channels.

Z®

44,153 次观看 • 1 个月前

Bob Lazar on the craft's propulsion system: "They cut into the reactor while it was under load, and the reactor exploded. That's what killed or hurt the person I replaced." "I tried to touch it. You can push down but you can't get close to it. The closer you get, the more it pushes back. At some point you can't push back on it at all, but it didn't move away when you pushed on it. It just prevented you from touching it."

Bob Lazar on the craft's propulsion system: "They cut into the reactor while it was under load, and the reactor exploded. That's what killed or hurt the person I replaced." "I tried to touch it. You can push down but you can't get close to it. The closer you get, the more it pushes back. At some point you can't push back on it at all, but it didn't move away when you pushed on it. It just prevented you from touching it."

TFTC

154,504 次观看 • 5 个月前

5/ We're introducing Gemini Agent: It uses Gemini 3's advanced reasoning to break down complex tasks, like booking local services or organizing your inbox, into actionable steps. It can then propose actions like drafting your replies or archiving emails, all using deeper integrations with Google apps. Available on the web for Google AI Ultra subscribers in the US.

5/ We're introducing Gemini Agent: It uses Gemini 3's advanced reasoning to break down complex tasks, like booking local services or organizing your inbox, into actionable steps. It can then propose actions like drafting your replies or archiving emails, all using deeper integrations with Google apps. Available on the web for Google AI Ultra subscribers in the US.

Sundar Pichai

132,065 次观看 • 10 个月前

Wow Microsoft just announced Copilot Actions for local files 🤯 You can basically ask Copilot to perform any task on your machine autonomously. Yes. - Open Copilot in Windows - Assign a goal in natural language - Copilot launches a contained environment - It works autonomously for you Copilot can use both your desktop and any web app. And you can take back control at any time. This allows you to do whatever you want while the AI performs your tasks... or even do nothing at all. The entire OS becomes agentic. Impressive.

Wow Microsoft just announced Copilot Actions for local files 🤯 You can basically ask Copilot to perform any task on your machine autonomously. Yes. - Open Copilot in Windows - Assign a goal in natural language - Copilot launches a contained environment - It works autonomously for you Copilot can use both your desktop and any web app. And you can take back control at any time. This allows you to do whatever you want while the AI performs your tasks... or even do nothing at all. The entire OS becomes agentic. Impressive.

Paul Couvert

87,452 次观看 • 11 个月前

Just found an open-source tool that lets you see how well an AI can actually use a computer. it’s called OSWorld 2.0. you give the AI a real task on a computer, then watch to see if it can figure everything out and finish it. it gives you: → real computer tasks, not simple questions → tasks that can take many steps to finish → the same computer setup for every AI → websites made for testing → all the files and tasks for free this is also the environment used to test computer-use systems from OpenAI and Anthropic. so if you’re building AI agents, researching computer use, or just want to see what these models can actually do, you can run the same tests yourself instead of relying only on benchmark scores. the labs publish the scores. this repo is where the actual tests come from. bookmark this.

Just found an open-source tool that lets you see how well an AI can actually use a computer. it’s called OSWorld 2.0. you give the AI a real task on a computer, then watch to see if it can figure everything out and finish it. it gives you: → real computer tasks, not simple questions → tasks that can take many steps to finish → the same computer setup for every AI → websites made for testing → all the files and tasks for free this is also the environment used to test computer-use systems from OpenAI and Anthropic. so if you’re building AI agents, researching computer use, or just want to see what these models can actually do, you can run the same tests yourself instead of relying only on benchmark scores. the labs publish the scores. this repo is where the actual tests come from. bookmark this.

MIKE

14,387 次观看 • 13 天前

Axis Robotics Point System - Free Airdrop Guide: Axis Robotics {Robotics Sector} Currently, I think this is the one of the free airdrop you should focus on because: - Raised $12M (led by Hack VC) - Building on AI + Robotics (robotics could be the next hot sector after AI) - Cost free tasks (only requires effort) - Low competition due to the difficult tasks + negative sentiment around airdrops STEPS 👇🏻 🔗 • Create an account • Complete all the available tasks. There are many live tasks to complete. It might feel hard when you start but once you adapt, it gets easier. • The more tasks you complete, the more points you'll earn • Sign all the tasks you complete (you can use bulk signing) Point distribution: Based on: • Volume of tasks • Difficulty level • Variety of tasks completed Points are distributed every 2 weeks (MONDAY) Snapshot taken on Friday. Special tasks: There are some special tasks that give higher points, but not everyone can access them (requires an access code). Will update if I get any. For special tasks, click on Alliance and complete the tasks there. Still very early, as the point system went live only a few days ago. You can contribute now and try to climb the leaderboard. Added a video showing how the tasks are completed by controlling the robots👇🏻

Axis Robotics Point System - Free Airdrop Guide: Axis Robotics {Robotics Sector} Currently, I think this is the one of the free airdrop you should focus on because: - Raised $12M (led by Hack VC) - Building on AI + Robotics (robotics could be the next hot sector after AI) - Cost free tasks (only requires effort) - Low competition due to the difficult tasks + negative sentiment around airdrops STEPS 👇🏻 🔗 • Create an account • Complete all the available tasks. There are many live tasks to complete. It might feel hard when you start but once you adapt, it gets easier. • The more tasks you complete, the more points you'll earn • Sign all the tasks you complete (you can use bulk signing) Point distribution: Based on: • Volume of tasks • Difficulty level • Variety of tasks completed Points are distributed every 2 weeks (MONDAY) Snapshot taken on Friday. Special tasks: There are some special tasks that give higher points, but not everyone can access them (requires an access code). Will update if I get any. For special tasks, click on Alliance and complete the tasks there. Still very early, as the point system went live only a few days ago. You can contribute now and try to climb the leaderboard. Added a video showing how the tasks are completed by controlling the robots👇🏻

Abhi.eth

20,754 次观看 • 1 个月前

House Intel Committee Member DEMANDS Release of the CIA Epstein Files to Reveal Any Evidence of Involvement with U.S. or Foreign Intelligence Rep. Steube: “We have not had any briefings on that but I certainly can ask and see what we can get… it would be interesting to see from an intelligence standpoint to see if there we actors from the intelligence perspective that were involved in all of this.”

House Intel Committee Member DEMANDS Release of the CIA Epstein Files to Reveal Any Evidence of Involvement with U.S. or Foreign Intelligence Rep. Steube: “We have not had any briefings on that but I certainly can ask and see what we can get… it would be interesting to see from an intelligence standpoint to see if there we actors from the intelligence perspective that were involved in all of this.”

Benny Johnson

49,015 次观看 • 7 个月前

We've got wunderful news: Today, we're releasing Superlist 1.0 – the new home to all your lists. 💥 To-do lists, shopping lists, reading lists, playlists…we all work with lists every day. Superlist brings a modern approach to organizing your work, seamlessly blending personal and professional tasks so you can get it all done in one place. It’s integrated with all the tools you already love to use to keep your life in sync. And our powerful AI features make going through your to do’s much faster and easier, giving you the ultimate luxury in today's fast-paced world: More time to focus on what really matters. Superlist 1.0 is just the beginning. We have plenty of exciting features in the pipeline, but with this release, we’re ready to get new eyes on the product (and of course, to make it possible for all of our old Wunderlist users to take Superlist for a spin!). ❤️ 👉

We've got wunderful news: Today, we're releasing Superlist 1.0 – the new home to all your lists. 💥 To-do lists, shopping lists, reading lists, playlists…we all work with lists every day. Superlist brings a modern approach to organizing your work, seamlessly blending personal and professional tasks so you can get it all done in one place. It’s integrated with all the tools you already love to use to keep your life in sync. And our powerful AI features make going through your to do’s much faster and easier, giving you the ultimate luxury in today's fast-paced world: More time to focus on what really matters. Superlist 1.0 is just the beginning. We have plenty of exciting features in the pipeline, but with this release, we’re ready to get new eyes on the product (and of course, to make it possible for all of our old Wunderlist users to take Superlist for a spin!). ❤️ 👉

Superlist

131,311 次观看 • 2 年前

Introducing Mobile Live Trips. Not just the driver: passengers can configure and edit trips too, right from their phone, before you get in the car and even while you're on the road. Search for a stop, add one, or reorder your route, and it all syncs instantly between the Rivian App and your R1 or R2. Requires Rivian App 3.16 and Rivian OS 2.

Introducing Mobile Live Trips. Not just the driver: passengers can configure and edit trips too, right from their phone, before you get in the car and even while you're on the road. Search for a stop, add one, or reorder your route, and it all syncs instantly between the Rivian App and your R1 or R2. Requires Rivian App 3.16 and Rivian OS 2.

Wassym Bensaid

38,291 次观看 • 21 天前