Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Meet Kimi K2.6 Agent Swarm 👋 Highlights： 🔹 Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from 100 / 1,500 in K2.5). 🔹 Outputs are real files, not chat - one run delivers 100+ files, 100,000-word literature reviews, or 20,000-row datasets. 🔹Heterogeneous skills - search,... show more

Kimi.ai

354,102 subscribers

617,549 görüntüleme • 4 ay önce •via X (Twitter)

Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

A GERMAN DEVELOPER REPLACED HIS ENTIRE DEV TEAM WITH KIMI K2.6, VISUALIZED EVERYTHING IN OBSIDIAN AND NOW MAKES $80,000/MONTH SOLO 1 trillion parameters, 32 billion activated per token and a SWE-Bench score of 65.8 - Kimi K2.6 reads the entire client codebase, understands the architecture, writes production code and ships for $150-300 in API costs while a traditional agency pays developers $4,800 for the exact same project. 300 parallel agents per run deliver 100+ files simultaneously - search, analysis, coding and writing all in parallel - and Obsidian visualizes the entire knowledge graph in real time while the agents work. A traditional agency with 10-15 people keeps 30% margin after salaries. He keeps 90% - $72,000 in monthly profit with $500 in overhead. By month 10 Kimi handles 80% of the technical work and he manages only strategy and client relationships - while Obsidian maps every project, every client and every agent in one graph that updates itself.

A GERMAN DEVELOPER REPLACED HIS ENTIRE DEV TEAM WITH KIMI K2.6, VISUALIZED EVERYTHING IN OBSIDIAN AND NOW MAKES $80,000/MONTH SOLO 1 trillion parameters, 32 billion activated per token and a SWE-Bench score of 65.8 - Kimi K2.6 reads the entire client codebase, understands the architecture, writes production code and ships for $150-300 in API costs while a traditional agency pays developers $4,800 for the exact same project. 300 parallel agents per run deliver 100+ files simultaneously - search, analysis, coding and writing all in parallel - and Obsidian visualizes the entire knowledge graph in real time while the agents work. A traditional agency with 10-15 people keeps 30% margin after salaries. He keeps 90% - $72,000 in monthly profit with $500 in overhead. By month 10 Kimi handles 80% of the technical work and he manages only strategy and client relationships - while Obsidian maps every project, every client and every agent in one graph that updates itself.

Noisy

850,103 görüntüleme • 3 ay önce

Kimi has a feature 90% of users have never opened it's called Agent Swarm you write one project brief, Kimi spins up to 300 domain-specialized agents, and delivers real files as output > 100 job descriptions -> 100 tailored CVs, one prompt > 40 academic papers -> 100k-word literature review with citations in 1 prompt > 30 businesses without websites -> 30 landing pages, one prompt a content agency charges $15k-$20k for that last task, but Agent Swarm does it for $0 extra on your subscription this is the feature Kimi built that nobody talks about full breakdown + 15 rules for running it in the article below

Kimi has a feature 90% of users have never opened it's called Agent Swarm you write one project brief, Kimi spins up to 300 domain-specialized agents, and delivers real files as output > 100 job descriptions -> 100 tailored CVs, one prompt > 40 academic papers -> 100k-word literature review with citations in 1 prompt > 30 businesses without websites -> 30 landing pages, one prompt a content agency charges $15k-$20k for that last task, but Agent Swarm does it for $0 extra on your subscription this is the feature Kimi built that nobody talks about full breakdown + 15 rules for running it in the article below

Chrome

16,660 görüntüleme • 3 ay önce

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Avi Chawla

110,057 görüntüleme • 3 ay önce

Box is a launch partner for Microsoft’s Apps in Copilot launch. The Box AI Agent for Microsoft365 Copilot will be able to surface rich visual previews like slides, graphs, and images right in the conversation and have access to all of the Box MCP server tools. Coming soon to the Box AI Agent in Microsoft 365 Copilot: 🔹 MCP-powered workflows — metadata extraction, document generation, and more 🔹 Visual-first search — view complicated graphs or rich visuals that are buried in your Box content, without having to open files. 🔹 Fewer clarifications, faster decisions - move from chat to action Enable agents to bring apps into the flow of work, while keeping IT in control:

Box is a launch partner for Microsoft’s Apps in Copilot launch. The Box AI Agent for Microsoft365 Copilot will be able to surface rich visual previews like slides, graphs, and images right in the conversation and have access to all of the Box MCP server tools. Coming soon to the Box AI Agent in Microsoft 365 Copilot: 🔹 MCP-powered workflows — metadata extraction, document generation, and more 🔹 Visual-first search — view complicated graphs or rich visuals that are buried in your Box content, without having to open files. 🔹 Fewer clarifications, faster decisions - move from chat to action Enable agents to bring apps into the flow of work, while keeping IT in control:

Box

335,591 görüntüleme • 5 ay önce

Jensen Huang: "Nvidia runs 7,500,000 agents for 75,000 people." that's 100 AI workers for every human employee. he goes further than that. "for the very first time, we have useful AI." not AI that answers questions. AI that does the work. and he's not talking about people who occasionally prompt ChatGPT. he means people who actually run agents in parallel. most people don't know you can already do this. one button. one prompt. up to 300 agents working at the same time. it's called Kimi Agent Swarm. 100 CVs tailored to 100 job descriptions. one prompt. 40 research papers into a 100,000-word review. one prompt. 30 landing pages for 30 businesses. one prompt. $40,000-$100,000 worth of work. one sitting. full breakdown in the article below.

Jensen Huang: "Nvidia runs 7,500,000 agents for 75,000 people." that's 100 AI workers for every human employee. he goes further than that. "for the very first time, we have useful AI." not AI that answers questions. AI that does the work. and he's not talking about people who occasionally prompt ChatGPT. he means people who actually run agents in parallel. most people don't know you can already do this. one button. one prompt. up to 300 agents working at the same time. it's called Kimi Agent Swarm. 100 CVs tailored to 100 job descriptions. one prompt. 40 research papers into a 100,000-word review. one prompt. 30 landing pages for 30 businesses. one prompt. $40,000-$100,000 worth of work. one sitting. full breakdown in the article below.

Dep

11,924 görüntüleme • 3 ay önce

👋 Say hi to WorkBuddy: China's most popular desktop AI agent, now available worldwide. WorkBuddy handles the tedious work autonomously and delivers ready-to-use project files across coding, analysis, and productivity scenarios. What sets it apart: Built-in Skills Gallery: Call on 100+ experts with pre-loaded knowledge, skills, and workflows. For complex tasks, agents collaborate on subtasks. Connected workspace: Plugs into GitHub, GitLab, Jira, Confluence, Google Drive, Gmail, Notion, Slack, and more to bring your entire workflow together. Work from anywhere: Send tasks via Slack, Telegram, or Discord and get outputs on your computer and back on your phone. Agent safety: Runs in a secure sandbox by default or accesses designated local folders with clear permission boundaries. Built with security in mind. Built for everyone, not just developers. 🔗 Userguide:

👋 Say hi to WorkBuddy: China's most popular desktop AI agent, now available worldwide. WorkBuddy handles the tedious work autonomously and delivers ready-to-use project files across coding, analysis, and productivity scenarios. What sets it apart: Built-in Skills Gallery: Call on 100+ experts with pre-loaded knowledge, skills, and workflows. For complex tasks, agents collaborate on subtasks. Connected workspace: Plugs into GitHub, GitLab, Jira, Confluence, Google Drive, Gmail, Notion, Slack, and more to bring your entire workflow together. Work from anywhere: Send tasks via Slack, Telegram, or Discord and get outputs on your computer and back on your phone. Agent safety: Runs in a secure sandbox by default or accesses designated local folders with clear permission boundaries. Built with security in mind. Built for everyone, not just developers. 🔗 Userguide:

Tencent AI

288,136 görüntüleme • 3 ay önce

$THIS GUY USED OPUS 4.8 + KIMI K2.6 TO CUT HIS CODING BILL FROM $4,000 TO $700/MO. WITH KIMI RUNNING A 300-AGENT CODING FLOOR, HE STOPPED PAYING CLAUDE TO DO EVERYTHING kimi does the cheap heavy lifting. it can spin up hundreds of agents, push through thousands of steps, write the rough code, expand files, draft tests and handle the repetitive work that burns the most tokens opus 4.8 only comes in where the money is worth spending. first to plan the spec and define the rules, then again to tear apart the output, catch weak logic and flag the bugs that a fast swarm can miss that is what changed the economics. kimi handled the bulk of the volume for a fraction of the price, while opus stayed in the loop as the architect and the reviewer instead of the full-time builder most people still use one model for every step and wonder why their costs explode. this guy split the jobs properly. kimi runs wide and cheap. opus goes deep and skeptical. one builds fast, the other makes sure it should ship the real edge is not finding one perfect model. it is knowing where expensive intelligence actually matters and where cheap parallel output is already enough. that is how a $4,000 workflow turns into a $700 system$

THIS GUY USED OPUS 4.8 + KIMI K2.6 TO CUT HIS CODING BILL FROM $4,000 TO $700/MO. WITH KIMI RUNNING A 300-AGENT CODING FLOOR, HE STOPPED PAYING CLAUDE TO DO EVERYTHING kimi does the cheap heavy lifting. it can spin up hundreds of agents, push through thousands of steps, write the rough code, expand files, draft tests and handle the repetitive work that burns the most tokens opus 4.8 only comes in where the money is worth spending. first to plan the spec and define the rules, then again to tear apart the output, catch weak logic and flag the bugs that a fast swarm can miss that is what changed the economics. kimi handled the bulk of the volume for a fraction of the price, while opus stayed in the loop as the architect and the reviewer instead of the full-time builder most people still use one model for every step and wonder why their costs explode. this guy split the jobs properly. kimi runs wide and cheap. opus goes deep and skeptical. one builds fast, the other makes sure it should ship the real edge is not finding one perfect model. it is knowing where expensive intelligence actually matters and where cheap parallel output is already enough. that is how a $4,000 workflow turns into a $700 system

Gipp 🦅

16,989 görüntüleme • 2 ay önce

The Visual Studio Code insiders version that just shipped and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.

The Visual Studio Code insiders version that just shipped and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.

Oren Melamed

29,555 görüntüleme • 7 ay önce

⬛ Austin Ekeler: From D2 to the League He ran for 5,857 yards at Western Colorado Football. Signed with the Los Angeles Chargers as an undrafted free agent. Led the NFL in touchdowns twice. Now with the Washington Commanders and still producing strong. He’s one of the best to ever come out of Division II. ⬇️ Western State, now Western Colorado, was the only program that offered him a shot at running back. He stayed four full years and became one of the most productive players the RMAC has ever seen. He averaged 146 rushing yards and 1.6 touchdowns per game over 40 starts. He put together one of the strongest careers in D2 history...and he didn’t have to leave to do it. At Western, Ekeler dominated. He averaged more than 100 rushing yards per game across four seasons, led the country in all-purpose yards in 2015, and earned academic honors alongside his on-field production. By the time he wrapped up his senior year, he was a Harlon Hill finalist with nearly 6,000 rushing yards to his name. His work was undeniable. But he still didn’t get a Combine invite. The draft came and went. No calls. Then the Los Angeles Chargers brought him into camp on a rookie deal and gave him a shot. He took it from there. He made the roster as a rookie and started producing immediately. First as a change-of-pace option. Then as a third-down threat. Then as the guy. In 2021 and 2022, he led the NFL in total touchdowns. He stacked back-to-back seasons with more than 1,500 scrimmage yards and at least 15 total scores. He caught 107 passes in 2022, the most by any running back in Los Angeles Chargers history. The production hasn’t slowed down. In 2024, he signed with the Washington Commanders. He’s still outworking people. Division II didn’t slow him down. It prepared him. The hours. The discipline. The ability to carry the weight of a program while juggling everything else college throws at you. That’s what this level teaches. That’s why it sticks. There are players right now doing the same thing. Grinding through the spring, stacking film, putting together complete seasons. Some will make it. Not because someone finally believed in them, but because they never stopped believing in themselves. That’s what turns a D2 shot into an NFL career. ⬛ College Career 🔹 5,857 rushing yards, 63 total touchdowns 🔹 4× First-Team All-RMAC Sports 🔹 2013 RMAC Offensive Freshman of the Year 🔹 Led D2 in all-purpose yards per game (203.9) in 2015 🔹 2016 Harlon Hill Trophy Finalist 🔹 First-Team Academic All-America (CoSIDA) 🔹 RMAC Academic Player of the Year (2014) 🔹 2018 Western Colorado Alumni Award of Excellence ⬛ NFL Career 🔹 Signed by Los Angeles Chargers in 2017 (UDFA) 🔹 NFL leader in total touchdowns: 20 (2021), 18 (2022) 🔹 Only player with 10+ rush and 5+ receiving TDs in back-to-back seasons since Marshall Faulk 🔹 One of two UDFAs with 1,500+ scrimmage yards and 15+ TDs in two straight years (with Priest Holmes) 🔹 107 catches in 2022, most by a running back in Los Angeles Chargers history 🔹 PFF Second-Team All-Pro (2019) 🔹 NFL Top 100: Ranked #21 in 2023 🔹 AFC Offensive Player of the Week (Week 17, 2022) 🔹 Over 7,000 scrimmage yards and 70+ career touchdowns 🔹 Signed with the Washington Commanders in 2024 ⬛ Off the Field 🔹 Owns more than 115 rental properties in Colorado and Missouri 🔹 Built the Eksperience app to connect athletes and fans 🔹 Co-founded Gridiron Gaming Group 🔹 75+ endorsement deals (Adidas, Chipotle, Frito-Lay, more) 🔹 Founded the Austin Ekeler Foundation in 2021 🔹 Former host of “Ekeler’s Edge” with Yahoo Sports Ekeler’s story isn’t rare because he came from Division II. It stands out because he stayed in it, believed in it, and maxed it out. That’s what this level does when the right player buys in. Who’s next? #D2Football #AustinEkeler #WesternColorado #RMAC #NFL #Undrafted #Division2 #D2Built #D2ToTheLeague

⬛ Austin Ekeler: From D2 to the League He ran for 5,857 yards at Western Colorado Football. Signed with the Los Angeles Chargers as an undrafted free agent. Led the NFL in touchdowns twice. Now with the Washington Commanders and still producing strong. He’s one of the best to ever come out of Division II. ⬇️ Western State, now Western Colorado, was the only program that offered him a shot at running back. He stayed four full years and became one of the most productive players the RMAC has ever seen. He averaged 146 rushing yards and 1.6 touchdowns per game over 40 starts. He put together one of the strongest careers in D2 history...and he didn’t have to leave to do it. At Western, Ekeler dominated. He averaged more than 100 rushing yards per game across four seasons, led the country in all-purpose yards in 2015, and earned academic honors alongside his on-field production. By the time he wrapped up his senior year, he was a Harlon Hill finalist with nearly 6,000 rushing yards to his name. His work was undeniable. But he still didn’t get a Combine invite. The draft came and went. No calls. Then the Los Angeles Chargers brought him into camp on a rookie deal and gave him a shot. He took it from there. He made the roster as a rookie and started producing immediately. First as a change-of-pace option. Then as a third-down threat. Then as the guy. In 2021 and 2022, he led the NFL in total touchdowns. He stacked back-to-back seasons with more than 1,500 scrimmage yards and at least 15 total scores. He caught 107 passes in 2022, the most by any running back in Los Angeles Chargers history. The production hasn’t slowed down. In 2024, he signed with the Washington Commanders. He’s still outworking people. Division II didn’t slow him down. It prepared him. The hours. The discipline. The ability to carry the weight of a program while juggling everything else college throws at you. That’s what this level teaches. That’s why it sticks. There are players right now doing the same thing. Grinding through the spring, stacking film, putting together complete seasons. Some will make it. Not because someone finally believed in them, but because they never stopped believing in themselves. That’s what turns a D2 shot into an NFL career. ⬛ College Career 🔹 5,857 rushing yards, 63 total touchdowns 🔹 4× First-Team All-RMAC Sports 🔹 2013 RMAC Offensive Freshman of the Year 🔹 Led D2 in all-purpose yards per game (203.9) in 2015 🔹 2016 Harlon Hill Trophy Finalist 🔹 First-Team Academic All-America (CoSIDA) 🔹 RMAC Academic Player of the Year (2014) 🔹 2018 Western Colorado Alumni Award of Excellence ⬛ NFL Career 🔹 Signed by Los Angeles Chargers in 2017 (UDFA) 🔹 NFL leader in total touchdowns: 20 (2021), 18 (2022) 🔹 Only player with 10+ rush and 5+ receiving TDs in back-to-back seasons since Marshall Faulk 🔹 One of two UDFAs with 1,500+ scrimmage yards and 15+ TDs in two straight years (with Priest Holmes) 🔹 107 catches in 2022, most by a running back in Los Angeles Chargers history 🔹 PFF Second-Team All-Pro (2019) 🔹 NFL Top 100: Ranked #21 in 2023 🔹 AFC Offensive Player of the Week (Week 17, 2022) 🔹 Over 7,000 scrimmage yards and 70+ career touchdowns 🔹 Signed with the Washington Commanders in 2024 ⬛ Off the Field 🔹 Owns more than 115 rental properties in Colorado and Missouri 🔹 Built the Eksperience app to connect athletes and fans 🔹 Co-founded Gridiron Gaming Group 🔹 75+ endorsement deals (Adidas, Chipotle, Frito-Lay, more) 🔹 Founded the Austin Ekeler Foundation in 2021 🔹 Former host of “Ekeler’s Edge” with Yahoo Sports Ekeler’s story isn’t rare because he came from Division II. It stands out because he stayed in it, believed in it, and maxed it out. That’s what this level does when the right player buys in. Who’s next? #D2Football #AustinEkeler #WesternColorado #RMAC #NFL #Undrafted #Division2 #D2Built #D2ToTheLeague

D2 College Football Spotlight

19,281 görüntüleme • 1 yıl önce

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.

The Startup Ideas Podcast (SIP) 🧃

18,006 görüntüleme • 15 gün önce

A really impressive set of Three.js graphics experiments just got open sourced, and these are much more than little visual demos. They are basically reusable procedural systems for oceans, vegetation, fluids and even whole planets. 🔹 Poseidon A real-time FFT ocean running on WebGPU. It simulates large swells, smaller ripples, foam, reflections, choppy displacement and physically inspired wave spectra entirely in the browser. 🔹 Gaia A procedural grass generator where every blade, seed head and field comes from a deterministic genome and environmental parameters. No authored grass models. 🔹 Dryad A procedural flora system that generates trees and other plant forms from physics, environmental conditions and a seed. No authored 3D models or textures are needed for the plants themselves. 🔹 Tiamat A real-time GPU fluid simulation using around 100,000 SPH particles, with the resulting water rendered directly in the browser. 🔹 Demiurge Probably the craziest one. It procedurally builds an entire planet from tectonic plates, then lets uplift drive erosion, erosion and latitude drive climate, and climate drive biomes, wind and weather. You can move seamlessly from orbit down to the surface. What I really like here is that these are not just pretty outputs. They are actual building blocks. Ocean simulation, vegetation generation, fluid dynamics and procedural worlds are exactly the kinds of systems that can be plugged into games, simulations and agent-built 3D environments. Project by: Owen

A really impressive set of Three.js graphics experiments just got open sourced, and these are much more than little visual demos. They are basically reusable procedural systems for oceans, vegetation, fluids and even whole planets. 🔹 Poseidon A real-time FFT ocean running on WebGPU. It simulates large swells, smaller ripples, foam, reflections, choppy displacement and physically inspired wave spectra entirely in the browser. 🔹 Gaia A procedural grass generator where every blade, seed head and field comes from a deterministic genome and environmental parameters. No authored grass models. 🔹 Dryad A procedural flora system that generates trees and other plant forms from physics, environmental conditions and a seed. No authored 3D models or textures are needed for the plants themselves. 🔹 Tiamat A real-time GPU fluid simulation using around 100,000 SPH particles, with the resulting water rendered directly in the browser. 🔹 Demiurge Probably the craziest one. It procedurally builds an entire planet from tectonic plates, then lets uplift drive erosion, erosion and latitude drive climate, and climate drive biomes, wind and weather. You can move seamlessly from orbit down to the surface. What I really like here is that these are not just pretty outputs. They are actual building blocks. Ocean simulation, vegetation generation, fluid dynamics and procedural worlds are exactly the kinds of systems that can be plugged into games, simulations and agent-built 3D environments. Project by: Owen

Token Gremlin

33,639 görüntüleme • 15 gün önce

KIMI K2.6 JUST CRUSHED GPT-5 AND A SINGLE PERSON CAN NOW POTENTIALLY BUILD AN $80K/MONTH BUSINESS WITH 300 AI AGENTS AND JUST $500 IN OVERHEAD The video attached is proof that almost everyone missed Kimi K2 Thinking didn’t just score 44.9% on Humanity’s Last Exam, it outperformed GPT-5 (41.7%), Claude, and every other major model across multiple benchmarks It’s open source Over a trillion parameters, trained for just $4.6M Runs locally on a Mac Studio and in the demo, it turns a 100-page PDF into a fully designed PowerPoint presentation in under two minutes while other models are still thinking In the article below, the author lays out a clear blueprint for turning this into a real business: > 300 parallel sub-agents running up to 4000 steps per execution - research, coding, analysis and visual creation all happen simultaneously > 65.8% on SWE-Bench solving real GitHub engineering tasks end-to-end with little to no human intervention > Skill injection through simple .md files - instant vertical specialization (HIPAA compliance, financial regulations, Shopify workflows and more) > Automated client acquisition: monitor job listings for “Data Analyst” or “Automation Engineer” roles and pitch an AI solution before companies even start hiring The math is simple: A $10k project Traditional agency → salaries, office costs, QA, project management and overhead eat most of the profit AI agency powered by Kimi → roughly $500 in operating costs plus one operator managing client relationships = the potential for 72k$+ monthly profit at scale Read the article Save this post Start building AI-native agencies while everyone else is still doing things the old way

KIMI K2.6 JUST CRUSHED GPT-5 AND A SINGLE PERSON CAN NOW POTENTIALLY BUILD AN $80K/MONTH BUSINESS WITH 300 AI AGENTS AND JUST $500 IN OVERHEAD The video attached is proof that almost everyone missed Kimi K2 Thinking didn’t just score 44.9% on Humanity’s Last Exam, it outperformed GPT-5 (41.7%), Claude, and every other major model across multiple benchmarks It’s open source Over a trillion parameters, trained for just $4.6M Runs locally on a Mac Studio and in the demo, it turns a 100-page PDF into a fully designed PowerPoint presentation in under two minutes while other models are still thinking In the article below, the author lays out a clear blueprint for turning this into a real business: > 300 parallel sub-agents running up to 4000 steps per execution - research, coding, analysis and visual creation all happen simultaneously > 65.8% on SWE-Bench solving real GitHub engineering tasks end-to-end with little to no human intervention > Skill injection through simple .md files - instant vertical specialization (HIPAA compliance, financial regulations, Shopify workflows and more) > Automated client acquisition: monitor job listings for “Data Analyst” or “Automation Engineer” roles and pitch an AI solution before companies even start hiring The math is simple: A $10k project Traditional agency → salaries, office costs, QA, project management and overhead eat most of the profit AI agency powered by Kimi → roughly $500 in operating costs plus one operator managing client relationships = the potential for 72k$+ monthly profit at scale Read the article Save this post Start building AI-native agencies while everyone else is still doing things the old way

Bonsai 🌳

21,487 görüntüleme • 3 ay önce

Make your CLI 10x more powerful with custom subagents! Mistral Vibe is an open-source coding agent that runs in your terminal. Most terminal agents give you one assistant that does everything. With Vibe, you can build custom subagents for targeted tasks like deploy scripts, PR reviews, and test generation, then invoke them on demand. Here's how it works: Each subagent runs independently and handles its job without cluttering your main workflow. You might have one for PR reviews, another for testing, and another for deployment. The agent also has full access to your codebase. It scans your project structure and Git status automatically, so it understands context across multiple files, not just the one you're editing. Key capabilities: • Web search and fetching - query and fetch content from the web mid-session for documentation, or API references. • Multi-choice clarifications - when your instruction is ambiguous, Vibe prompts with options instead of guessing. You pick the right path before it acts. • Full skills support - slash commands for preconfigured workflows, custom subagents for specialized tasks, and extensibility through the Agent Skills standard. Vibe works in your terminal or connects to VS Code, JetBrains, and Zed through the Agent Client Protocol. Mistral Vibe is available through Le Chat Pro and Team plans. It's 100% open source Link to Mistral Vibe in the comments!

Make your CLI 10x more powerful with custom subagents! Mistral Vibe is an open-source coding agent that runs in your terminal. Most terminal agents give you one assistant that does everything. With Vibe, you can build custom subagents for targeted tasks like deploy scripts, PR reviews, and test generation, then invoke them on demand. Here's how it works: Each subagent runs independently and handles its job without cluttering your main workflow. You might have one for PR reviews, another for testing, and another for deployment. The agent also has full access to your codebase. It scans your project structure and Git status automatically, so it understands context across multiple files, not just the one you're editing. Key capabilities: • Web search and fetching - query and fetch content from the web mid-session for documentation, or API references. • Multi-choice clarifications - when your instruction is ambiguous, Vibe prompts with options instead of guessing. You pick the right path before it acts. • Full skills support - slash commands for preconfigured workflows, custom subagents for specialized tasks, and extensibility through the Agent Skills standard. Vibe works in your terminal or connects to VS Code, JetBrains, and Zed through the Agent Client Protocol. Mistral Vibe is available through Le Chat Pro and Team plans. It's 100% open source Link to Mistral Vibe in the comments!

Sumanth

10,483 görüntüleme • 5 ay önce

Understanding the BitTorrent Swarm — A Broader Look With Real Data Dynamics BitTorrent isn’t just a file-sharing protocol; it’s one of the most efficient large-scale distribution systems ever designed. At its core lies a simple but powerful principle: when users contribute bandwidth, the entire network accelerates. This is the swarm and its efficiency can be explained through clear data patterns and network behavior. 🔹 The Swarm Model: How Participation Becomes Performance In a traditional client-server setup, bandwidth is fixed. If 10,000 users try to download a 1 GB file from one server with 1 Gbps bandwidth: ➠ Maximum theoretical throughput per user: 0.1 Mbps ➠ Average download time: 2–3 hours ➠ Server overload: very likely BitTorrent rewrites this logic. When 10,000 users join a swarm and each contributes only 50–200 Kbps of upload bandwidth, the network’s total available throughput multiplies thousands of times. This is why, in real swarm studies: ➠ Larger swarms consistently show 30–400% faster download speeds ➠ Popular torrents reach equilibrium within minutes, not hours ➠ Throughput per user remains stable even under heavy demand BitTorrent’s efficiency grows with usage — something centralized systems struggle with. 🔹 Why More Peers = More Speed (Backed by Data Behavior) BitTorrent breaks files into hundreds or thousands of small pieces. Each piece circulates among peers using a strategy called rarest-first ensuring no piece becomes a bottleneck. Here’s what the data shows: 1. Bandwidth multiplication effect If each peer contributes: ➠ 100 peers × 100 Kbps upload = 10 Mbps swarm capacity ➠ 5,000 peers × 150 Kbps upload = 750 Mbps swarm capacity ➠ 20,000 peers × 200 Kbps upload = 4 Gbps swarm capacity This turning point when collective bandwidth surpasses any server is why torrents of large files often download faster than centralized sources. 2. Availability resilience Even if 90% of peers leave, as long as one full copy exists across the swarm’s collective pieces, the file is recoverable without interruption. 3. Load balancing automatically occurs BitTorrent’s choking/unchoking algorithm ensures: ➠ High-bandwidth peers exchange more data ➠ Low-bandwidth peers still participate ➠ No single peer becomes a bottleneck The data flow adapts in real time based on peer performance. 🔹 The Swarm’s Global Impact: Why It Still Matters BitTorrent traffic routinely accounts for: ➠ 10–20% of global internet upload traffic (varies by region) ➠ Multiple petabytes of data exchanged daily ➠ Millions of active swarms at any given time The model works because it scales with demand: ➠ More users → more bandwidth. ➠ More bandwidth → faster delivery. ➠ Faster delivery → stronger swarm health. This “self-reinforcing cycle” is a core reason decentralized systems from Web3 storage to blockchain data sync borrow heavily from BitTorrent’s architecture. 🔹 The Big Picture The BitTorrent swarm illustrates an important truth about decentralized networks: Efficiency doesn’t come from the center it comes from participation. When thousands of people contribute small amounts of bandwidth, the result is a global system capable of speeds that outperform traditional content delivery models. This is not just technology; it’s cooperative acceleration at internet scale. In One Line Files move faster when everyone contributes and BitTorrent proves it with real data. H.E. Justin Sun 👨‍🚀 🌞 BitTorrent #TRONEcoStar #BitTorrent #SwarmNetwork #DataAnalysis #DecentralizedSystems #P2P

Understanding the BitTorrent Swarm — A Broader Look With Real Data Dynamics BitTorrent isn’t just a file-sharing protocol; it’s one of the most efficient large-scale distribution systems ever designed. At its core lies a simple but powerful principle: when users contribute bandwidth, the entire network accelerates. This is the swarm and its efficiency can be explained through clear data patterns and network behavior. 🔹 The Swarm Model: How Participation Becomes Performance In a traditional client-server setup, bandwidth is fixed. If 10,000 users try to download a 1 GB file from one server with 1 Gbps bandwidth: ➠ Maximum theoretical throughput per user: 0.1 Mbps ➠ Average download time: 2–3 hours ➠ Server overload: very likely BitTorrent rewrites this logic. When 10,000 users join a swarm and each contributes only 50–200 Kbps of upload bandwidth, the network’s total available throughput multiplies thousands of times. This is why, in real swarm studies: ➠ Larger swarms consistently show 30–400% faster download speeds ➠ Popular torrents reach equilibrium within minutes, not hours ➠ Throughput per user remains stable even under heavy demand BitTorrent’s efficiency grows with usage — something centralized systems struggle with. 🔹 Why More Peers = More Speed (Backed by Data Behavior) BitTorrent breaks files into hundreds or thousands of small pieces. Each piece circulates among peers using a strategy called rarest-first ensuring no piece becomes a bottleneck. Here’s what the data shows: 1. Bandwidth multiplication effect If each peer contributes: ➠ 100 peers × 100 Kbps upload = 10 Mbps swarm capacity ➠ 5,000 peers × 150 Kbps upload = 750 Mbps swarm capacity ➠ 20,000 peers × 200 Kbps upload = 4 Gbps swarm capacity This turning point when collective bandwidth surpasses any server is why torrents of large files often download faster than centralized sources. 2. Availability resilience Even if 90% of peers leave, as long as one full copy exists across the swarm’s collective pieces, the file is recoverable without interruption. 3. Load balancing automatically occurs BitTorrent’s choking/unchoking algorithm ensures: ➠ High-bandwidth peers exchange more data ➠ Low-bandwidth peers still participate ➠ No single peer becomes a bottleneck The data flow adapts in real time based on peer performance. 🔹 The Swarm’s Global Impact: Why It Still Matters BitTorrent traffic routinely accounts for: ➠ 10–20% of global internet upload traffic (varies by region) ➠ Multiple petabytes of data exchanged daily ➠ Millions of active swarms at any given time The model works because it scales with demand: ➠ More users → more bandwidth. ➠ More bandwidth → faster delivery. ➠ Faster delivery → stronger swarm health. This “self-reinforcing cycle” is a core reason decentralized systems from Web3 storage to blockchain data sync borrow heavily from BitTorrent’s architecture. 🔹 The Big Picture The BitTorrent swarm illustrates an important truth about decentralized networks: Efficiency doesn’t come from the center it comes from participation. When thousands of people contribute small amounts of bandwidth, the result is a global system capable of speeds that outperform traditional content delivery models. This is not just technology; it’s cooperative acceleration at internet scale. In One Line Files move faster when everyone contributes and BitTorrent proves it with real data. H.E. Justin Sun 👨‍🚀 🌞 BitTorrent #TRONEcoStar #BitTorrent #SwarmNetwork #DataAnalysis #DecentralizedSystems #P2P

catalina ossa

50,297 görüntüleme • 9 ay önce

Anthropic shouldn't have made this free a company doing $47,000,000,000 a year wrote down exactly how they run their AI agents, published the numbers, and charged nobody it's called Graph Engineering: one lead Claude plans a job and hires a swarm of smaller ones, each working its own slice at the same time turns out how many it hires decides everything: → a simple lookup: 1 agent, 3 to 10 tool calls, no swarm → a straight comparison: 2 to 4 workers, 10 to 15 calls each → open-ended research: 10+ workers, one slice of the question each → the lead fires 3 to 5 at once, each running 3+ tools in parallel: up to 90% faster the briefs are where it dies. they told a lead agent to "research the semiconductor shortage" and one worker went off into the 2021 car chip crisis while two others wrote the same 2025 report twice so a worker now gets four things: an objective, an output format, which tools to touch, where its job ends they also pointed one small agent at their own badly written tool descriptions and let it rewrite them every agent that used the new ones finished 40% faster then one grader Claude scores every run 0.0 to 1.0 on five things: factual accuracy, citation accuracy, completeness, source quality, tool efficiency twenty test questions took one of their agents from 30% success to 80% one limit nobody quotes: most coding work has fewer genuinely parallel pieces than research, so a swarm on one repo mostly buys you coordination overhead it pays on wide search and on jobs bigger than one context window free, out of a $965,000,000,000 lab, and almost nobody has copied it yet bookmark this and copy the counts ↓

Anthropic shouldn't have made this free a company doing $47,000,000,000 a year wrote down exactly how they run their AI agents, published the numbers, and charged nobody it's called Graph Engineering: one lead Claude plans a job and hires a swarm of smaller ones, each working its own slice at the same time turns out how many it hires decides everything: → a simple lookup: 1 agent, 3 to 10 tool calls, no swarm → a straight comparison: 2 to 4 workers, 10 to 15 calls each → open-ended research: 10+ workers, one slice of the question each → the lead fires 3 to 5 at once, each running 3+ tools in parallel: up to 90% faster the briefs are where it dies. they told a lead agent to "research the semiconductor shortage" and one worker went off into the 2021 car chip crisis while two others wrote the same 2025 report twice so a worker now gets four things: an objective, an output format, which tools to touch, where its job ends they also pointed one small agent at their own badly written tool descriptions and let it rewrite them every agent that used the new ones finished 40% faster then one grader Claude scores every run 0.0 to 1.0 on five things: factual accuracy, citation accuracy, completeness, source quality, tool efficiency twenty test questions took one of their agents from 30% success to 80% one limit nobody quotes: most coding work has fewer genuinely parallel pieces than research, so a swarm on one repo mostly buys you coordination overhead it pays on wide search and on jobs bigger than one context window free, out of a $965,000,000,000 lab, and almost nobody has copied it yet bookmark this and copy the counts ↓

Argona

117,177 görüntüleme • 1 ay önce

HERMES AGENT SUPPORTS 7 TYPES OF AI AGENTS. EACH ONE TAKES LESS THAN 90 SECONDS TO SET UP. MOST PEOPLE ONLY BUILD THE FIRST ONE. HERE ARE ALL SEVEN AND WHEN TO USE EACH. 1. BASIC AGENT WITH TOOLS your agent with access to terminal, browser, file system, web search, and calendar. it plans and executes tasks on its own. this is what you get on day one. "find flights to Lisbon under $400" "check my calendar and flag conflicts" "search the web for competitor pricing" set in Desktop app / Dashboard: Tools → enable what you need. when to use: single tasks that need tool access. 2. AGENT WITH MCP SERVERS connect your agent to external services. Notion, Google Drive, GitHub, Slack, databases, APIs, any MCP-compatible service. the agent doesn't scrape these services. it interacts through structured APIs. reads your Notion pages. creates GitHub issues. queries your database. sends Slack messages. set in Desktop app / Dashboard: MCP → Add Server. when to use: your workflow lives across multiple platforms. 3. SEQUENTIAL AGENTS (pipeline) one agent finishes. passes output to the next. assembly line for AI. agent 1: scans inbox for leads. agent 2: qualifies leads against criteria. agent 3: drafts outreach emails. in Hermes: cron jobs with wakeAgent gates. agent 1 writes output to a file. agent 2 wakes only when that file has new data. agent 3 wakes when agent 2 is done. each agent = a separate profile with its own model. when to use: multi-step workflows where each step depends on the previous one finishing. 4. PARALLEL EXECUTION AGENTS multiple agents working at the same time. results merge when all finish. "research these 5 competitors in parallel" in Hermes: delegate_task with batch mode. up to 3 sub-agents running in parallel by default. each gets its own clean context. only summaries return to the parent. delegation: model: "deepseek/deepseek-v4" children run cheap. parent synthesizes. when to use: independent tasks that don't depend on each other. research, data gathering, analysis. 5. AGENTS WITH ROUTERS conditions that send tasks down different paths based on the input. "if sales email → SDR profile. if support ticket → support profile. if calendar invite → EA profile." in Hermes: Kanban decompose. the decomposer reads profile descriptions and routes each task to the best-fit agent. or: Chief of Staff profile that triages and assigns to other profiles. when to use: incoming work that needs different specialists based on type. 6. HUMAN IN THE LOOP the agent does the work. asks for your approval before executing. "I drafted this email. approve before I send?" "this command will delete 3 files. proceed?" in Hermes: approvals.mode: manual (default). every dangerous action needs your confirmation. 60-second timeout. fails closed. or smart mode: LLM assesses risk. safe actions auto-approved. dangerous ones ask you. uncertain ones escalate. when to use: tasks where a mistake has real consequences. emails, deployments, financial transactions, public posts. 7. DYNAMIC SUB-AGENT SPAWNING your main agent realizes it needs help and spawns specialized sub-agents on the fly. "build this feature" → parent delegates: → sub-agent 1: research the API docs → sub-agent 2: write the code → sub-agent 3: write the tests in Hermes: delegate_task with role: orchestrator. raise max_spawn_depth for nested delegation. delegation: max_spawn_depth: 2 orchestrator_enabled: true depth 2 with concurrency 3 = up to 9 parallel workers. each level multiplies the spend. raise depth only when you need multi-level trees. when to use: complex tasks where the agent discovers what help it needs during execution. THE PROGRESSION: start with 1 (tools) and 6 (approvals). add 2 (MCP) when you need external services. add 4 (parallel) when tasks take too long one at a time. add 3 (sequential) when you build multi-step pipelines. add 5 (routing) when you run multiple profiles. add 7 (dynamic) when single-agent reasoning falls short. seven types. each under 90 seconds to configure. the value compounds as you stack them. comment AGENTS and I'll send you 3 ready-to-build agent setups that combine these types into real workflows.

YanXbt

17,312 görüntüleme • 1 ay önce

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,257 görüntüleme • 11 ay önce

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,540 görüntüleme • 2 ay önce

One of the most cracked engineers I know believes that local development is (mostly) dead. He walked me through why + his setup for using cloud agents in parallel... The big fucking problem: - You've got one codebase on your computer - Worktrees are supposed to let you run agents in parallel. On a real stack they don't (database contention, port conflicts, a dev server that only works in one tree) - So people flip back to one agent at a time and become the bottleneck themselves - Or they run multiple agents on the same machine: one writes a change, another writes over it, and they're fighting - Then you have to poke around, find everything each agent did, and test it independently - That's too much mental clutter - Locally you're operating like a CPU. You get an instruction, you build it, you queue a backlog The solution: - Stop sharing the computer. Give every agent its own - CJ Hess' setup is Amp "orbs": a full computer in the cloud that clones the repo, starts the dev server, and runs one agent with nothing else contending - A "portal" is a live URL into that running app so you can click around from any device before you trust it - Isolated like an actual team, each person on their own machine The payoff: - It feels like a GPU, not a CPU. A list of 10 tasks, all started, real progress, loop closed - Smaller, contained diffs hit main faster and create fewer conflicts, not more - Favorite prompt: "give me irrefutable evidence that this works." On his laptop he would never run something so heavy he can't use Slack and Chrome. In an orb he will (millions of simulated DB writes, full demo videos) - Smaller diffs, no mixed concerns, higher confidence, ship more often - Mental clutter is gone. One thread, one set of changes, one computer. He always knows the state. That's what lets him do more in parallel, not less - The last things he still does locally: read production logs, set a sensitive secret. He is not spinning up the app on his laptop

One of the most cracked engineers I know believes that local development is (mostly) dead. He walked me through why + his setup for using cloud agents in parallel... The big fucking problem: - You've got one codebase on your computer - Worktrees are supposed to let you run agents in parallel. On a real stack they don't (database contention, port conflicts, a dev server that only works in one tree) - So people flip back to one agent at a time and become the bottleneck themselves - Or they run multiple agents on the same machine: one writes a change, another writes over it, and they're fighting - Then you have to poke around, find everything each agent did, and test it independently - That's too much mental clutter - Locally you're operating like a CPU. You get an instruction, you build it, you queue a backlog The solution: - Stop sharing the computer. Give every agent its own - CJ Hess' setup is Amp "orbs": a full computer in the cloud that clones the repo, starts the dev server, and runs one agent with nothing else contending - A "portal" is a live URL into that running app so you can click around from any device before you trust it - Isolated like an actual team, each person on their own machine The payoff: - It feels like a GPU, not a CPU. A list of 10 tasks, all started, real progress, loop closed - Smaller, contained diffs hit main faster and create fewer conflicts, not more - Favorite prompt: "give me irrefutable evidence that this works." On his laptop he would never run something so heavy he can't use Slack and Chrome. In an orb he will (millions of simulated DB writes, full demo videos) - Smaller diffs, no mixed concerns, higher confidence, ship more often - Mental clutter is gone. One thread, one set of changes, one computer. He always knows the state. That's what lets him do more in parallel, not less - The last things he still does locally: read production logs, set a sensitive secret. He is not spinning up the app on his laptop

Alex Lieberman

97,491 görüntüleme • 5 gün önce

ClawTeam v0.2.0 is here. One CLI to coordinate any coding agent — Claude Code, Codex, OpenClaw, nanobot, and more — into a self‑organizing swarm that plans, builds, and ships together. What's new in v0.2.0: 1) - Gource Visualization — Watch your agent swarm’s Git activity in real time. Clear. Visual. Instant. Run: clawteam board gource --live See every commit, branch, and merge as it happens. Track what each agent is doing. 2) - Runtime Profiles — A provider‑aware configuration system. Switch between Claude, Kimi, and Gemini anytime. No need to edit environment variables. Run clawteam profile wizard. Follow the interactive setup. Done in minutes. 3) - Git-Based Context — Full worktree isolation with built‑in conflict detection and change tracking. Each agent works on its own branch, and the leader can see everything clearly in one place. 4) - Stability & Hardening — Spawn/workspace conflict fixes, improved tmux integration, message normalization, P2P liveness with lease-based detection. This release is about making the foundation rock-solid. --------------------------------------------------------- To show what a coordinated agent swarm can actually do, we ran 1 Claude Code orchestrating 8 Claude Code agents to build a robotics simulation system optimized for Apple Silicon — from scratch. 8 hours. 300+ PRs. One running simulator. Check the result: --------------------------------------------------------- Huge thanks to the open-source community for the feedback, issues, and PRs that shaped this release. ClawTeam is built in the open because we believe multi-agent coordination should be a shared primitive, not a proprietary moat. Try it: pip install clawteam Docs: GitHub: #ClawTeam #nanobot #AIAgents #openclaw #ClaudeCode #Cursor

Chao Huang

25,232 görüntüleme • 5 ay önce