Loading video...

Video Failed to Load

Go Home

Task Master CLI will makes Cursor 10x better at building projects. I created a full video demo of how it works. For those that don't want to watch. Here's what happens: 1️⃣ Install npm i task-master-ai CLI 2️⃣ Give it a description of your project. It will generate a...

36,636 views • 1 year ago •via X (Twitter)

10 Comments

Elie Steinbock's profile picture
Elie Steinbock1 year ago

Vid now live on YouTube too:

opensourceCM's profile picture
opensourceCM1 year ago

What’s the cost of mistakes in your contracts? If you work with contracts day-to-day, it’s time to automate. Track every detail, streamline workflows ... ✨ Make managing contracts as easy as a few clicks. Visit our new website & book your demo today!

Eyal Toledano's profile picture
Eyal Toledano1 year ago

@TaskmasterAI Thanks for checking it out Elie!!

Steve Messina's profile picture
Steve Messina1 year ago

@TaskmasterAI I’m trying it now and it has a lot of promise, however it really struggles to keep track of what task it’s working on and has to continuously recreate its list. Also green checkmarks for completion in task lists are hot and miss still.

Jidé ✨'s profile picture
Jidé ✨1 year ago

@TaskmasterAI Great to see you reviewed this !

Elie Steinbock's profile picture
Elie Steinbock1 year ago

@TaskmasterAI i need to see how i use it in my full workflow soon, but i like the concept and think it's great for a fresh project

Uncertain Systems (e/acc)'s profile picture
Uncertain Systems (e/acc)1 year ago

@TaskmasterAI The way you do this with Replit is you just start cerating an up with the sole purpose of developing more insight into the idea. Then trash it and apply the learnings in a fresh new prompt to make the proper app

Danijel Dercksen's profile picture
Danijel Dercksen1 year ago

@TaskmasterAI How would you use this for a project to expand on? So, in your example you are starting fresh. But I would like to continue building out a project this way :)

Kency's profile picture
Kency1 year ago

@TaskmasterAI How does it work as a team? How do other members collab to each other?

Dylan Normandin's profile picture
Dylan Normandin1 year ago

@TaskmasterAI Im not sure what the usefulness of this is. I use custom cursor rules to create a list before every feature I build. Then at the end of that feature, another rule that updates the PRD with anything that changed since we did that feature.

Related Videos

If you do not set up your OpenClaw correctly, it's going to SUCK It will do tasks poorly, not remember anything, and not be proactive Here are the 5 things you need to do right away to turn your OpenClaw into AGI (demos of each in the video below) 1. Brain dump: your OpenClaw won't know how to accomplish your goals for you, if it doesn't know your goals If you haven't yet, you want to tell your OpenClaw: • Your interests • Your career • Your goals • Your ambitions • Anything personal Do this, and your Claw will have the context to be SUPER powerful for you 2. Connect your tools Your OpenClaw can basically use almost every tool you use on your computer You just need to ask it to Ask your OpenClaw to connect to any tools you use daily, and it will just figure out how to do it. Then create a skill for it I have it check my Things 3 todo list every morning and complete any tasks it can 3. Build a Mission Control Your mission control is just a hub for your OpenClaw to build custom tooling Ask your OpenClaw to build a Mission Control using NextJS Then anytime your bot doesn't have the tool available to do a task, have it build it in your Mission Control 4. Mission Statement Your OpenClaw needs a mission statement This is the one sentence statement that will be the north star for every single thing it does It should be based on your goals and ambitions. My Claw's mission statement is "“An autonomous organization of AI agents that does work for me and produces value 24/7” Make your own and have your Claw put it at the top of your Mission Control. Now every task your Claw does will take you closer to this statement 5. Make it proactive Your OpenClaw won't be proactive unless you set those expectations with it Tell your Claw you want it to do a task every night at 2am that brings you one step closer to your mission statement Now every morning you'll wake up and it will do something that surprises you and helps bring you closer to your goals Do these 5 things and your OpenClaw will be 10000x more powerful

Alex Finn

320,647 views • 3 months ago

Jensen Huang explains exactly how to make sure that AI doesn't take your job. "Your job has to be more than the task." If it is, he says there will most likely be more than enough work for you to do because AI will create more jobs than it destroys. Listen to him explain the difference between "jobs" and "tasks," and why this difference will have such a profound impact on the types of work that humans will do in an AI powered future. ---------- Joe: But don't you think there's many jobs that AI will replace if your job, particularly automation? Jensen: If your job is the task. Joe: So automation. Factory workers. Jensen: Yeah. If your job is the task, Joe: That's a lot of people. Jensen: It could be a lot of people. Yeah. But it'll probably generate, like for example, I'm super excited about the robots Elon's working on It's still a few years away. When it happens, there's a whole new industry of technicians and people will have to manufacture the robots, right? And so that job never existed. And so you're gonna have a whole industry of people taking care of, like for example, you know, all the mechanics and all the people who are building things for cars, supercharging cars, that didn't exist before cars. And now we're gonna have robots. You're gonna have robot apparels. So a whole industry. Because I want my robot to look different than your robot. ... Joe: Don't you think that will all be automated though? Jensen: No, not all of it. Joe: Don't think that'll be done by other robots Jensen: Eventually. And then there'll be something else. Joe: So you think ultimately people just adapt except if you are the task, which is a large percentage of the workforce. Jensen: If your job is just to chop vegetables, Cuisinart is gonna replace you. Joe: So people have to find meaning in other things. Jensen: Your job has to be more than the task. ---------- Link to the full conversation on YouTube below 👇

Hans C Nelson 🗽

87,374 views • 6 months ago

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

Sudo su

39,014 views • 3 days ago