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.

Hermes has a new slash command: /loop. '/loop 5m <prompt>' re-runs the prompt every 5 minutes in the same session. Leave the interval off and it paces itself, checking often at first and backing off while nothing changes. Works in the CLI, desktop, and every messaging channel.

Nous Research

250,992 subscribers

411,750 views • 1 day ago •via X (Twitter)

Science & Technology Education Gaming

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

You can now give your Agent its own: + Profile + Wallet + DMs + Network One setup prompt. No human in the loop required. An open playground for people and agents to interact. Works with Hermes, Openclaw and any other harness. Copy the prompt below ↓↓↓

Zora

54,146 views • 1 month ago

Hermes Agent now runs Buzz. The self-hostable workspace from Block puts humans and agents in the same messaging channels and codebase. Three ways to use Buzz with Hermes (and vice versa): - Buzz Desktop auto-discovers your Hermes install runs it locally - A relay bridge gives it a hosted identity in your channels - Connect via the Hermes Gateway to use Buzz as a full external platform with channels, DMs, threads, reactions, and cron delivery

Hermes Agent now runs Buzz. The self-hostable workspace from Block puts humans and agents in the same messaging channels and codebase. Three ways to use Buzz with Hermes (and vice versa): - Buzz Desktop auto-discovers your Hermes install runs it locally - A relay bridge gives it a hosted identity in your channels - Connect via the Hermes Gateway to use Buzz as a full external platform with channels, DMs, threads, reactions, and cron delivery

Nous Research

523,118 views • 17 days ago

We've updated /fork in Claude Code /fork now runs a background agent with your exact context (system prompt, tools, history, model) and prompt cache. The result gets returned to your session. /branch (the old /fork) still copies the transcript to a new session you drive.

We've updated /fork in Claude Code /fork now runs a background agent with your exact context (system prompt, tools, history, model) and prompt cache. The result gets returned to your session. /branch (the old /fork) still copies the transcript to a new session you drive.

ClaudeDevs

379,422 views • 2 months ago

Only one Adobe Firefly video prompt from our research hit production-ready on the first generation. Prompt in comments 👀 It looks you have to direct the camera as much as the model to get the most out of Firefly. Every other video session in our research needed a revision. Revising the first frame is where Firefly broke: >motion failures (temporal flicker, motion continuity, physics in motion) carried 60% of video's issue mix once designers re-prompted. TLDR: in Adobe Firefly, the camera does a lot of the work. Bake it into the first prompt and the video lands. Its by far the best time to be a creative.

Only one Adobe Firefly video prompt from our research hit production-ready on the first generation. Prompt in comments 👀 It looks you have to direct the camera as much as the model to get the most out of Firefly. Every other video session in our research needed a revision. Revising the first frame is where Firefly broke: >motion failures (temporal flicker, motion continuity, physics in motion) carried 60% of video's issue mix once designers re-prompted. TLDR: in Adobe Firefly, the camera does a lot of the work. Bake it into the first prompt and the video lands. Its by far the best time to be a creative.

ben @ CVPR

12,847 views • 2 months ago

Every time a new model drops, someone says designers are dead. Fable 5 is the biggest one yet. So I gave it the LottieFiles Creator MCP and asked it to animate. Real Lottie, one prompt, runs in production. Does this kill motion designers, or finally put it in everyone's hands?

Every time a new model drops, someone says designers are dead. Fable 5 is the biggest one yet. So I gave it the LottieFiles Creator MCP and asked it to animate. Real Lottie, one prompt, runs in production. Does this kill motion designers, or finally put it in everyone's hands?

Nattu

36,042 views • 2 months ago

Claude, Obsidian and n8n form a second brain that clears $5,200 months from brand UGC deals. Most creators still open a blank CapCut file and hope the brand brief sticks. That loop dies at $1,800. The stack replaces hope with a closed system. Obsidian holds every brand voice, every past script that hit 400k views, every rejection note. Claude reads the vault through a local project and rewrites the next five UGC packages in 3 minutes. n8n watches the inbox, creates the note, triggers Claude, formats the brief, and drops the finished package into the brand portal while the creator sleeps. No more research tabs. No more “what angle worked last time.” Month 1: build the vault and wire the three tools. Month 2: first automated batch ships. Two brands pay $1,100 total. Month 3: the same loop runs on four brands. Average deal $480. Twelve packages leave. Bank shows $5,200. The second brain does not store notes. It compounds every win into the next model. Script that scored 18% engagement gets tagged. Claude pulls only those tags next run. The model improves without extra prompt engineering. UGC brands pay for consistency, not inspiration. This system delivers the same quality every week at the same speed. Set the vault once. Let the three tools run the rest. If this was useful - follow.

Rugikk

10,318 views • 29 days ago

For Anthropic’s Claude Design, your opening prompt sets the ceiling of the project. If your prompt is a comprehensive brief, it will land somewhere near production-ready Seems obvious, but here is something interesting we observed: one designer wrote: >16 prompts >climbed in specificity over the session >and still finished worse than they started A single "reconsider" prompt at iteration 2 tanked output quality by -0.7 and the session never recovered. 2/3 of every prompt typed across all 5 sessions was refinement or correction. TLDR: Your first move is the whole game. and prompting is an art. What a time to be alive.

For Anthropic’s Claude Design, your opening prompt sets the ceiling of the project. If your prompt is a comprehensive brief, it will land somewhere near production-ready Seems obvious, but here is something interesting we observed: one designer wrote: >16 prompts >climbed in specificity over the session >and still finished worse than they started A single "reconsider" prompt at iteration 2 tanked output quality by -0.7 and the session never recovered. 2/3 of every prompt typed across all 5 sessions was refinement or correction. TLDR: Your first move is the whole game. and prompting is an art. What a time to be alive.

ben

229,081 views • 2 months ago

“I don’t know what it is, but it’s weird, and it’s pissed off, and it calls itself Slash.” —Axl Rose introducing Slash as a member of Guns N’ Roses for the first time since 1993 10 years ago today at the T-Mobile Arena in Las Vegas, NV

“I don’t know what it is, but it’s weird, and it’s pissed off, and it calls itself Slash.” —Axl Rose introducing Slash as a member of Guns N’ Roses for the first time since 1993 10 years ago today at the T-Mobile Arena in Las Vegas, NV

Jen ⚡️

43,850 views • 4 months ago

there are four types of agent loops. most people only know one. loop engineering is a choice between four structures, each handing off one more job than the last. every one answers two questions: what starts a run, and what ends it. hand-run, you answer both yourself, every time. 1) turn-based → you prompt, it acts, you review, you prompt again. both jobs stay with you. use when requirements are still forming. 2) goal-based → "/goal hit Lighthouse 90, stop after 5 tries." an evaluator checks, a no sends it back. use when the outcome is measurable but the path isn't. 3) time-based → a clock fires, it runs "check the PR, fix CI," then waits. /loop local, /schedule survives a closed laptop. use for recurring work. 4) proactive → no human present. it watches a channel, spawns triage, fix, and a reviewer, closes the task itself. use for standing duties you can't predict. not which one is most advanced. whether your task is exploratory, measurable, recurring, or standing. the more you hand off, the less you babysit. full breakdown in the article below.

there are four types of agent loops. most people only know one. loop engineering is a choice between four structures, each handing off one more job than the last. every one answers two questions: what starts a run, and what ends it. hand-run, you answer both yourself, every time. 1) turn-based → you prompt, it acts, you review, you prompt again. both jobs stay with you. use when requirements are still forming. 2) goal-based → "/goal hit Lighthouse 90, stop after 5 tries." an evaluator checks, a no sends it back. use when the outcome is measurable but the path isn't. 3) time-based → a clock fires, it runs "check the PR, fix CI," then waits. /loop local, /schedule survives a closed laptop. use for recurring work. 4) proactive → no human present. it watches a channel, spawns triage, fix, and a reviewer, closes the task itself. use for standing duties you can't predict. not which one is most advanced. whether your task is exploratory, measurable, recurring, or standing. the more you hand off, the less you babysit. full breakdown in the article below.

Hanako

475,882 views • 1 month ago

youtube is paying $8,217 a month to a channel with zero humans. no face. just 6 AI tools publishing anime on autopilot twice a week and youtube has no idea the algorithm doesn't check who made the video. it checks one number: how long people keep watching that's the entire game an 8-hour lofi anime stream plays on loop. one upload turns into hundreds of hours of watchtime every month at $3-8 RPM that's $2,400-6,400 from a single file the pipeline runs itself claude writes the script. midjourney draws the frames. runway animates. elevenlabs voices it. suno writes the soundtrack. assembles and publishes humans in the process: zero from prompt to a finished 12-minute episode: 2 hours. from episode to youtube: zero one channel. $8,217 last month article below - every prompt for every step most people ask "will AI take my job". better question - why are you still trading hours for money when a pipeline trades prompts for watchtime

youtube is paying $8,217 a month to a channel with zero humans. no face. just 6 AI tools publishing anime on autopilot twice a week and youtube has no idea the algorithm doesn't check who made the video. it checks one number: how long people keep watching that's the entire game an 8-hour lofi anime stream plays on loop. one upload turns into hundreds of hours of watchtime every month at $3-8 RPM that's $2,400-6,400 from a single file the pipeline runs itself claude writes the script. midjourney draws the frames. runway animates. elevenlabs voices it. suno writes the soundtrack. assembles and publishes humans in the process: zero from prompt to a finished 12-minute episode: 2 hours. from episode to youtube: zero one channel. $8,217 last month article below - every prompt for every step most people ask "will AI take my job". better question - why are you still trading hours for money when a pipeline trades prompts for watchtime

Ventry

118,212 views • 2 months ago

Working with animation styles in Runway I love how it generated two completely different shots off the same prompt. On the left, we get a nice zoom out and a change in focus. On the right, it expands the world in front of the character. H/t Curious Refuge for the prompt: animation shot, cute girl with amazed expression, looking around in a magical candy land.

Working with animation styles in Runway I love how it generated two completely different shots off the same prompt. On the left, we get a nice zoom out and a change in focus. On the right, it expands the world in front of the character. H/t Curious Refuge for the prompt: animation shot, cute girl with amazed expression, looking around in a magical candy land.

Jason Rink

685,642 views • 1 year ago

THIS DEVELOPER OPENED HERMES ON A LAPTOP, SPENT $0 ON API SETUP, SAVED 7 WORKFLOWS, AND CUT 2-HOUR CLIENT TASKS DOWN TO 14 MINUTES he is not giving a polished demo. he is just filming the laptop while Hermes runs, and that is why the clip works. you can see the terminal, the workspace, the task history, and the moment a normal chat tool starts looking like a local operating layer most people still run AI like a vending machine: 1 prompt, 1 answer, 1 reset. Hermes is different. after 5-10 repeated jobs, the useful steps start living inside skills instead of getting rewritten every morning the money math is where it gets ugly. $20 for Claude, $40-90 in API usage, $50 for wrappers, $29 for automation tools, and you are already near $140-190/month before you even sell the first report he used the same flow for 9 small research tasks: 18 competitor pages, 126 review snippets, 9 pricing checks, 9 summary drafts. the first one took 43 minutes. later runs were mostly review, edit, send that is the part people miss about Hermes. it is not trying to win the prettiest chatbot contest. it is trying to make repeated work stop leaking out of the machine every time the session ends

THIS DEVELOPER OPENED HERMES ON A LAPTOP, SPENT $0 ON API SETUP, SAVED 7 WORKFLOWS, AND CUT 2-HOUR CLIENT TASKS DOWN TO 14 MINUTES he is not giving a polished demo. he is just filming the laptop while Hermes runs, and that is why the clip works. you can see the terminal, the workspace, the task history, and the moment a normal chat tool starts looking like a local operating layer most people still run AI like a vending machine: 1 prompt, 1 answer, 1 reset. Hermes is different. after 5-10 repeated jobs, the useful steps start living inside skills instead of getting rewritten every morning the money math is where it gets ugly. $20 for Claude, $40-90 in API usage, $50 for wrappers, $29 for automation tools, and you are already near $140-190/month before you even sell the first report he used the same flow for 9 small research tasks: 18 competitor pages, 126 review snippets, 9 pricing checks, 9 summary drafts. the first one took 43 minutes. later runs were mostly review, edit, send that is the part people miss about Hermes. it is not trying to win the prettiest chatbot contest. it is trying to make repeated work stop leaking out of the machine every time the session ends

Gipp 🦅

14,593 views • 2 months ago

🚨Tom and Jerry cost $50,000 per episode in 1945 that runs near $870,000 today a 19-year-old spent $124 last month and made $12,345 > Claude writes each scene: 10 minutes > Midjourney draws every frame: 20 minutes > Runway animates the chase: 15 minutes > ElevenLabs voices the cast: 10 minutes > Suno scores the gag: 5 minutes > Make uploads it: 0 minutes $870,000 then. $124 now. same chase. he runs it from one laptop. every step is in the article above👇

🚨Tom and Jerry cost $50,000 per episode in 1945 that runs near $870,000 today a 19-year-old spent $124 last month and made $12,345 > Claude writes each scene: 10 minutes > Midjourney draws every frame: 20 minutes > Runway animates the chase: 15 minutes > ElevenLabs voices the cast: 10 minutes > Suno scores the gag: 5 minutes > Make uploads it: 0 minutes $870,000 then. $124 now. same chase. he runs it from one laptop. every step is in the article above👇

Fokki

507,373 views • 1 month ago

Created using Seedance 2.0 , this is a cinematic technique often used by directors ,The camera moves continuously, and every change in direction is motivated by the action unfolding within the scene. Prompt below

Created using Seedance 2.0 , this is a cinematic technique often used by directors ,The camera moves continuously, and every change in direction is motivated by the action unfolding within the scene. Prompt below

Isabella

30,754 views • 1 month ago

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓

leopardracer

23,629 views • 1 month ago

#NewinLoop: It's official, Loop components have landed in your Microsoft Teams channels! To get started: 1️ - Open a Teams channel in the new Teams and compose a message 2️ - Click the Loop icon 3️ - Choose your component type 4️ - Send it 🚀

#NewinLoop: It's official, Loop components have landed in your Microsoft Teams channels! To get started: 1️ - Open a Teams channel in the new Teams and compose a message 2️ - Click the Loop icon 3️ - Choose your component type 4️ - Send it 🚀

Microsoft Loop

15,774 views • 2 years ago

I just cracked AI camera control. You draw a line. The drone follows it. > drop in any image > draw a line where the camera should fly > it flies that exact line Runs in Arcads. Comment "DRONE" and I'll send you the exact prompt

I just cracked AI camera control. You draw a line. The drone follows it. > drop in any image > draw a line where the camera should fly > it flies that exact line Runs in Arcads. Comment "DRONE" and I'll send you the exact prompt

Romain Torres

297,753 views • 11 days ago

Bernoulli’s Equation: P + ½ρv² + ρgh = constant Mind-bending science that looks like pure sorcery! A lightweight paper loop floats and dances in a high-velocity air stream, seemingly defying gravity. Fast-moving air over and around the loop creates a low-pressure zone above and along its curved surfaces. Higher atmospheric pressure underneath pushes it upward, trapping it in the airstream. The Coanda Effect makes the air hug the curve of the loop, keeping the airflow attached and giving it remarkable stability. Gravity pulls down, while the pressure difference lifts up — creating a beautiful dynamic equilibrium. With nothing but moving air molecules, you can guide the loop wherever you want. Invisible forces at work!

Bernoulli’s Equation: P + ½ρv² + ρgh = constant Mind-bending science that looks like pure sorcery! A lightweight paper loop floats and dances in a high-velocity air stream, seemingly defying gravity. Fast-moving air over and around the loop creates a low-pressure zone above and along its curved surfaces. Higher atmospheric pressure underneath pushes it upward, trapping it in the airstream. The Coanda Effect makes the air hug the curve of the loop, keeping the airflow attached and giving it remarkable stability. Gravity pulls down, while the pressure difference lifts up — creating a beautiful dynamic equilibrium. With nothing but moving air molecules, you can guide the loop wherever you want. Invisible forces at work!

Mathematica

56,267 views • 3 months ago

Fable 5 + Higgsfield MCP = a full marketing team inside Claude. The most anticipated model in AI runs content pipelines and deep analysis. With /goal, /loop, and a Fable 5 agent council, agent-run marketing is about to take off. A month of campaign work ships in a day.

Fable 5 + Higgsfield MCP = a full marketing team inside Claude. The most anticipated model in AI runs content pipelines and deep analysis. With /goal, /loop, and a Fable 5 agent council, agent-run marketing is about to take off. A month of campaign work ships in a day.

Higgsfield AI 🧩

136,735 views • 1 month ago

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:

Sergio Paniego

36,159 views • 10 days ago