Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Ever watch an agent solve a problem with 100% confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x... show more

Weiyan Shi

8,702 subscribers

46,021 views • 3 days ago •via X (Twitter)

Education News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

ClickUp now employs over 100,000 AI AGENTS for our customers. This is from just THREE WEEKS of customers vibe coding full-blown teams of agents, THEMSELVES. BUT there's a problem. Since Super Agents are built agnostically, horizontally, and deeply capable with human-level abilities, you can literally build an agent for anything. We found that MOST of our customers have NO CLUE where to start. This is their very FIRST TIME EVER managing an agent. What I recommend is starting with a PROBLEM. Everybody can think of a problem they have. Just tell Super Agent Builder about your problems... about where you're WASTING time... about what you WISH you could do but you can't because of resource constraints. We've also found that human FEEDBACK and iteration are KEY. After agents are done with their jobs, give them feedback... Was it good? Was it bad? What do you want to see differently? They AUTOMATICALLY SELF-IMPROVE. Every time, they'll continuously get SMARTER. Personally, I find that agents go from AVERAGE intelligence to SUPER-human intelligence within about a month of working with them. Super Agents have truly democratized productivity, empowering literally anyone to build personalized, powerful agents in minutes. What problems do you wish you could solve? What do you not have enough time to get done? What would you like to do but don't have the resources for? What busy work do you wish you could get rid of?

ClickUp now employs over 100,000 AI AGENTS for our customers. This is from just THREE WEEKS of customers vibe coding full-blown teams of agents, THEMSELVES. BUT there's a problem. Since Super Agents are built agnostically, horizontally, and deeply capable with human-level abilities, you can literally build an agent for anything. We found that MOST of our customers have NO CLUE where to start. This is their very FIRST TIME EVER managing an agent. What I recommend is starting with a PROBLEM. Everybody can think of a problem they have. Just tell Super Agent Builder about your problems... about where you're WASTING time... about what you WISH you could do but you can't because of resource constraints. We've also found that human FEEDBACK and iteration are KEY. After agents are done with their jobs, give them feedback... Was it good? Was it bad? What do you want to see differently? They AUTOMATICALLY SELF-IMPROVE. Every time, they'll continuously get SMARTER. Personally, I find that agents go from AVERAGE intelligence to SUPER-human intelligence within about a month of working with them. Super Agents have truly democratized productivity, empowering literally anyone to build personalized, powerful agents in minutes. What problems do you wish you could solve? What do you not have enough time to get done? What would you like to do but don't have the resources for? What busy work do you wish you could get rid of?

Zeb Evans

18,286 views • 5 months ago

If you ever get a Great Pyrenees know they don’t fetch. They don’t retrieve. If you throw a ball, they’ll look at you like “well that was stupid. Now you have to go get it.” They’re bred to go on a hilltop with sheep and watch them alone for days. So they expect that you trust them to make their own decisions. They enjoy sitting and observing, and patrolling. Then more observing. Then more patrolling. They like to sleep in places where they can see everything.

If you ever get a Great Pyrenees know they don’t fetch. They don’t retrieve. If you throw a ball, they’ll look at you like “well that was stupid. Now you have to go get it.” They’re bred to go on a hilltop with sheep and watch them alone for days. So they expect that you trust them to make their own decisions. They enjoy sitting and observing, and patrolling. Then more observing. Then more patrolling. They like to sleep in places where they can see everything.

Gretchen Ronnevik

2,069,401 views • 1 month ago

Self-improving agents are here. 🧙‍♂️ Every agent run creates a skill.md with reusable learnings. The next agent uses it to do the same task faster, cheaper, and more reliably. Watch the second agent crush it:

Self-improving agents are here. 🧙‍♂️ Every agent run creates a skill.md with reusable learnings. The next agent uses it to do the same task faster, cheaper, and more reliably. Watch the second agent crush it:

Browser Use

56,157 views • 4 months ago

In 2025, the smartest thing you can do is this: → Pick a painful problem → Train an AI agent to solve it → Charge people for using it Here's what I'd use to start and scale it to $5k/month, with no team, no funding, no code 👇

In 2025, the smartest thing you can do is this: → Pick a painful problem → Train an AI agent to solve it → Charge people for using it Here's what I'd use to start and scale it to $5k/month, with no team, no funding, no code 👇

EyeingAI

51,466 views • 1 year ago

“Alan Jackson is coming. Alright. You can delay it, you can deny it, you can do everything you can. You can try to apologize. You can try to get out in front of it. You can go on your own media tour… but it’s coming.”

“Alan Jackson is coming. Alright. You can delay it, you can deny it, you can do everything you can. You can try to apologize. You can try to get out in front of it. You can go on your own media tour… but it’s coming.”

Unfiltered Thoughts (Justice For John O’Keefe)

21,895 views • 21 days ago

New feature: you can now cancel your agent while it's running. No need to wait for it to finish - just stop it whenever you want.

New feature: you can now cancel your agent while it's running. No need to wait for it to finish - just stop it whenever you want.

SwarmNode.ai

42,790 views • 1 year ago

What if you could create your own AI agent? With Bluwhale Create Agent, anyone can: • Build an AI-powered strategy • Deploy it to the marketplace • Let others use your agent • Earn when your agent performs AI agents aren’t just tools anymore. They’re becoming economic participants. 🎥 See how it works ↓

What if you could create your own AI agent? With Bluwhale Create Agent, anyone can: • Build an AI-powered strategy • Deploy it to the marketplace • Let others use your agent • Earn when your agent performs AI agents aren’t just tools anymore. They’re becoming economic participants. 🎥 See how it works ↓

Bluwhale

23,082 views • 3 months ago

If you're working with Godot, you probably won't need an Item Box, but if you do, you can download this one from Jettelly ✨ You can also get a guide if you want to learn how it was created. #GodotEngine #mobiledev #gamedev #solodev

If you're working with Godot, you probably won't need an Item Box, but if you do, you can download this one from Jettelly ✨ You can also get a guide if you want to learn how it was created. #GodotEngine #mobiledev #gamedev #solodev

The Unity Shaders Bible

89,732 views • 1 year ago

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

12,577 views • 1 month ago

If Ayo can do it, you can do it. Get moving and experience confidence through action, #LetsMove. #Olympics #OlympicDay

If Ayo can do it, you can do it. Get moving and experience confidence through action, #LetsMove. #Olympics #OlympicDay

The Olympic Games

24,600 views • 9 days ago

Just a reminder if you need to hear it you can always come watch this again…

Sensitive content

Just a reminder if you need to hear it you can always come watch this again…

prettiest kitty kat

31,557 views • 1 year ago

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

54,762 views • 2 months ago

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give an agent control of a diffusion model, so it can create its own *synthetic experience*.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give an agent control of a diffusion model, so it can create its own synthetic experience.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇

Norman Di Palo

12,892 views • 1 year ago

Vikkstar123 shares the wisest piece of advice he’s ever been given “If you want to go fast, go alone. If you want to go far, go together” “I think it almost speaks a little bit to kinda a journey I’ve been on with friends, where you can get a lot done very quickly if you just kinda go for it” “But if you want to build something that’s gonna last and does really well, you need other people to do it, you need to collaborate”

Vikkstar123 shares the wisest piece of advice he’s ever been given “If you want to go fast, go alone. If you want to go far, go together” “I think it almost speaks a little bit to kinda a journey I’ve been on with friends, where you can get a lot done very quickly if you just kinda go for it” “But if you want to build something that’s gonna last and does really well, you need other people to do it, you need to collaborate”

Jack

776,133 views • 3 months ago

“If you want it, if you want it you can get it… we don’t wanna do this but if you push us force our had… take you all out” - Roman Reigns That laugh tho…. The locker room is on notice!

“If you want it, if you want it you can get it… we don’t wanna do this but if you push us force our had… take you all out” - Roman Reigns That laugh tho…. The locker room is on notice!

нαη∂у ⸜❤︎⸝‍ ~*Roman Reigns*~

70,995 views • 19 days ago

Claude Fable is finally back! it can now watch the meta ad library for the businesses that just turned their first ad on and mails them a finished, better version of it here's the system you can use to run an agency: - watches the meta ad library for businesses that just started running ads - pulls each one's google business profile for a mailable address + real photos - vision-checks the current ad, rejects the weak leads - rebuilds it into the ad their industry actually runs, not a stock template - prints a before/after postcard: their flat ad next to the recut + a QR - mails it to the owner, then makes their content every month one system that lands you new local biz clients every week. reply "FABLE" + RT and i'll send you a free guide so you can build this too (must be following so i can DM you)

Chris

87,810 views • 3 days ago

Get up. Do what you need to do to take care of the ones you love. Get it done the best you can, for as long as you can, while you still can. No one is coming to save you.

Get up. Do what you need to do to take care of the ones you love. Get it done the best you can, for as long as you can, while you still can. No one is coming to save you.

Dr. Johnny

26,560 views • 1 year ago

7 different examples of how you can integrate AI agents directly into the front-end of your application. If you are a React developer or an agent builder, I'm about to make your job 2x more interesting with CopilotKit🪁. Read on for the details:

7 different examples of how you can integrate AI agents directly into the front-end of your application. If you are a React developer or an agent builder, I'm about to make your job 2x more interesting with CopilotKit🪁. Read on for the details:

Santiago

25,435 views • 1 year ago

The federal election is on Monday, April 28. Did you get your voter information card? Watch for it in the mail. It tells you where and when you can vote. If you don’t get a card by April 11, or if it has incorrect information, visit #ItsOurVote

The federal election is on Monday, April 28. Did you get your voter information card? Watch for it in the mail. It tells you where and when you can vote. If you don’t get a card by April 11, or if it has incorrect information, visit #ItsOurVote

Elections Canada

2,364,384 views • 1 year ago

Hermes Agent now has access to hundreds of browser skills through Browserbase’s new hub, so agents can more reliably perform any task on the internet. You can try a skill from their catalog or contribute your own.

Hermes Agent now has access to hundreds of browser skills through Browserbase’s new hub, so agents can more reliably perform any task on the internet. You can try a skill from their catalog or contribute your own.

Nous Research

547,687 views • 1 month ago