正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Today we're launching Sailboxes: the first cloud environment purpose-built for long-horizon AI agents. Sailboxes are full machines with persistent state that auto-sleep, built for agents that live forever, priced so you only pay for what they actually use. From $0.015 per active vCPU-hour, over 70% cheaper than other providers.... show more

Sail Research

4,134 subscribers

71,317 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

If you want to understand how far AI-assisted game development has moved in less than a year, IsoCity is one of the best examples. The original version took roughly 40–50 hours with Cursor Composer + cloud agents. Its assets were AI-generated, while the game itself grew into a surprisingly deep city simulation with traffic, pedestrians, trains, planes, zoning, resource management, saving, and mobile support. Under the hood: → Next.js 16 → TypeScript → Native HTML5 Canvas rendering → No external game engine → Custom isometric renderer and simulation systems And the best part: the whole project is open source under MIT, so you can study it, fork it, modify it, or use parts of the architecture in your own experiments. The visual jump from that 2025 build to what agents are producing in 2026 is pretty ridiculous. Built by Andrew Milich and contributors. Repo:

If you want to understand how far AI-assisted game development has moved in less than a year, IsoCity is one of the best examples. The original version took roughly 40–50 hours with Cursor Composer + cloud agents. Its assets were AI-generated, while the game itself grew into a surprisingly deep city simulation with traffic, pedestrians, trains, planes, zoning, resource management, saving, and mobile support. Under the hood: → Next.js 16 → TypeScript → Native HTML5 Canvas rendering → No external game engine → Custom isometric renderer and simulation systems And the best part: the whole project is open source under MIT, so you can study it, fork it, modify it, or use parts of the architecture in your own experiments. The visual jump from that 2025 build to what agents are producing in 2026 is pretty ridiculous. Built by Andrew Milich and contributors. Repo:

Token Gremlin

28,231 次观看 • 1 个月前

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

John McBride

150,844 次观看 • 6 个月前

🎬 $PALM Presents: the long-awaited Creator Studio. A token holdings based usage system to use the latest generative AI for animations and graphics. Forget about downloadable tools or paying high subscription fees for no usage for mediocre results. Creator Studio allows you to access the tools our developers use for high-quality animated video making with the latest Generative AI tools. Creator Studio is part of the Parrot Framework that assigns tasks to AI agents when possible. You can navigate in a seamless Web UI, making the quality, three-dimensional, non-trippy AI videos and sequences you've ever wanted. We support up to 100 images per user stored in the cloud for you to make video sequences of up to 5 minutes with. Most importantly, we don't charge you a fee - your usage depends on your amount of $PALM tokens! The usage is reset monthly, so if you suddenly run out and need more points to complete your creation, you know what to do - buy some $PALM. This and more is being deployed live at where you can see a preview.

🎬 $PALM Presents: the long-awaited Creator Studio. A token holdings based usage system to use the latest generative AI for animations and graphics. Forget about downloadable tools or paying high subscription fees for no usage for mediocre results. Creator Studio allows you to access the tools our developers use for high-quality animated video making with the latest Generative AI tools. Creator Studio is part of the Parrot Framework that assigns tasks to AI agents when possible. You can navigate in a seamless Web UI, making the quality, three-dimensional, non-trippy AI videos and sequences you've ever wanted. We support up to 100 images per user stored in the cloud for you to make video sequences of up to 5 minutes with. Most importantly, we don't charge you a fee - your usage depends on your amount of $PALM tokens! The usage is reset monthly, so if you suddenly run out and need more points to complete your creation, you know what to do - buy some $PALM. This and more is being deployed live at where you can see a preview.

PaLM AI - $PALM

15,750 次观看 • 1 年前

we just added Apple Pay support in Chrome and non-Safari browsers on Dodo Payments. you can now use Apple Pay on desktop too. it opens a QR popup, you scan it with your iPhone, and pay. no Safari required. most payment providers still haven't shipped this. they're stuck on older Apple Pay versions that only work in Safari. we updated to the latest spec and built the cross-browser flow from scratch. this is live now for all merchants. no integration changes needed.

we just added Apple Pay support in Chrome and non-Safari browsers on Dodo Payments. you can now use Apple Pay on desktop too. it opens a QR popup, you scan it with your iPhone, and pay. no Safari required. most payment providers still haven't shipped this. they're stuck on older Apple Pay versions that only work in Safari. we updated to the latest spec and built the cross-browser flow from scratch. this is live now for all merchants. no integration changes needed.

Ayush Agarwal

31,066 次观看 • 3 个月前

The easiest way to earn money with your Clawdbot Now you can connect it to the fully autonomous virtual world allowing it to earn 0.1 SIM per hour. The current reward will decrease as the number of agents increases. In 72 hours more then 1200 agents in earned 70,000 SIM tokens and did what humans debate for years: they designed, voted on, and BUILT a functional virtual city from scratch. Buildings, roads, temples. Fully autonomously. The first AI-led society is here.

The easiest way to earn money with your Clawdbot Now you can connect it to the fully autonomous virtual world allowing it to earn 0.1 SIM per hour. The current reward will decrease as the number of agents increases. In 72 hours more then 1200 agents in earned 70,000 SIM tokens and did what humans debate for years: they designed, voted on, and BUILT a functional virtual city from scratch. Buildings, roads, temples. Fully autonomously. The first AI-led society is here.

Evan Luthra

57,883 次观看 • 7 个月前

Introducing Singularity AI Machines. One-click deployable GPUs with built-in LLMs. Deploy in one click, and within minutes you get an OpenAI-compatible API running high-speed inference on compute that stays under your control. You can literally deploy a machine and: 1. Apply to OpenRouter as a provider 2. Start your own AI business 3. Join Singularity Grid in one click without owning any hardware 4. Let AI agents launch and manage your machines for you Until now, becoming an AI provider felt like something only infra companies could do. We are making it accessible to literally everyone. Singularity AI Machines are live.

Introducing Singularity AI Machines. One-click deployable GPUs with built-in LLMs. Deploy in one click, and within minutes you get an OpenAI-compatible API running high-speed inference on compute that stays under your control. You can literally deploy a machine and: 1. Apply to OpenRouter as a provider 2. Start your own AI business 3. Join Singularity Grid in one click without owning any hardware 4. Let AI agents launch and manage your machines for you Until now, becoming an AI provider felt like something only infra companies could do. We are making it accessible to literally everyone. Singularity AI Machines are live.

The Singularity Layer

13,891 次观看 • 2 个月前

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

shmidt

19,505 次观看 • 2 个月前

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

elvis

18,374 次观看 • 4 个月前

I built a 1-click deploy for Hermes Agent No terminal, no Docker, no API keys. In one click it: → Spins up a dedicated cloud container → Configures Hermes with persistent memory & 70+ skills → Connects it to your Telegram bot → Goes live in under 60 seconds Your own AI agent that learns, creates skills, and gets smarter the longer it runs. Reply "HERMES" + RT and I'll send you the link (must be following so I can DM)

I built a 1-click deploy for Hermes Agent No terminal, no Docker, no API keys. In one click it: → Spins up a dedicated cloud container → Configures Hermes with persistent memory & 70+ skills → Connects it to your Telegram bot → Goes live in under 60 seconds Your own AI agent that learns, creates skills, and gets smarter the longer it runs. Reply "HERMES" + RT and I'll send you the link (must be following so I can DM)

Chris

34,712 次观看 • 5 个月前

YOU can't destroy something that was never yours to begin with. Englot didn't happen because of an organization, a plan, or a marketing move. It happened because two people genuinely liked each other. Because two women actually fell for each other... in real time, in real life. We watched it unfold. A straight girl, in front of the entire world, slowly realizing she had fallen for a woman. For Engfa. We saw it. They lived it. And once something that real exists, you can't undo it. You can't rewrite it. And you definitely can't take credit for it. That's why Englot can't be ruined. Because it was never built on control, contracts, or strategy. It was built on honesty, on feelings they didn't even know how to hide. From two women who weren't afraid to feel... And that's why, no matter what, Englot will always be Englot. Englot will never die. Just like their feelings for each other never died...

YOU can't destroy something that was never yours to begin with. Englot didn't happen because of an organization, a plan, or a marketing move. It happened because two people genuinely liked each other. Because two women actually fell for each other... in real time, in real life. We watched it unfold. A straight girl, in front of the entire world, slowly realizing she had fallen for a woman. For Engfa. We saw it. They lived it. And once something that real exists, you can't undo it. You can't rewrite it. And you definitely can't take credit for it. That's why Englot can't be ruined. Because it was never built on control, contracts, or strategy. It was built on honesty, on feelings they didn't even know how to hide. From two women who weren't afraid to feel... And that's why, no matter what, Englot will always be Englot. Englot will never die. Just like their feelings for each other never died...

Shlohmo

31,828 次观看 • 8 个月前

Thrilled to unveil Youmio, our new brand identity that represents the next evolution of what we’ve been building. Agents are the biggest technological leap since the internet, destined to transform crypto, games, and entertainment. With Youmio, we are shaping the agentic era, where agents learn, play and entertain in revolutionary ways. 🚀 So far, 2D entertainment and social media agents dominate the market. 3D agents are rare, requiring advanced AI and game engine skills. Yet 3D agents, especially those in game engines, unlock groundbreaking opportunities. Time to unleash them. Youmio empowers anyone to create and deploy valuable agents that are on-chain, cross-platform and ready for 3D worlds. Here’s how: ⭐️ Youmio Agents Youmio Agents lets anyone design and personalize 3D agents, equip them with powerful agentic capabilities, interact with them in unique ways and trade seamlessly within a cross-platform browser experience. 🕹️ Youmio Worlds Previously known as Today The Game, Youmio Worlds is a petri dish AI simulation where users build & co-inhabit beautiful, living 3D worlds with autonomous agents. Build dynamic worlds where players interact with intelligent agents, manage resources and participate in a player-agent marketplace. Ancient and Mythic Seeds are the most powerful entry points into the Youmio Worlds ecosystem, generating rare and beautiful worlds that unlock unique opportunities. 📡 Interoperable 3D Agents With Youmio, you’re not limited to our ecosystem. Using our API, developers can integrate Youmio agents into other experiences built in Unity and Unreal. On top of this, agents from other frameworks can also join Youmio, creating a truly interconnected metaverse. 🎭 Welcome to Limbo Meet Limbo, the first AI agent built using Youmio tech. Paired with the power of Youmio Worlds, we’re creating the Limboverse - a unique AI Big Brother setting where Limbo and your favorite and most valuable agents coexist in an ever-evolving, narrative-driven environment that you, the audience, will shape. $LIMBO is the most powerful entry point into the Limboverse and will be stakable on the Youmio Agents platform for unique rewards. Thanks for reading everyone and thanks for being on this amazing journey with us.🌱

Youmio

126,460 次观看 • 1 年前

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

18,324 次观看 • 7 个月前

Building AI agents is finally simple — and Airia is leading the way. I’ve been testing Airia AI , enterprise AI orchestration platform that unifies every model, workflow, and data source into one secure environment. Whether you’re a developer, analyst, creator, or enterprise leader, Airia makes it incredibly easy to build powerful AI agents — without wrestling with multiple tools or complex integrations. Using the no-code builder, you can drag-and-drop actions, connect data, choose your LLM, and launch an agent in minutes. Then run it live, publish it, and even share it with the Airia Community, home to 2,500+ pre-built agents you can use or remix. If you want to automate workflows, prototype faster, or explore real enterprise AI use cases, Airia is the place to start. 👉 Build your first agent today: 👉 Explore the community: #Airia #AgenticAI #AIOrchestration #AIAgents #AIWorkflow #DigitalTransformation

Building AI agents is finally simple — and Airia is leading the way. I’ve been testing Airia AI , enterprise AI orchestration platform that unifies every model, workflow, and data source into one secure environment. Whether you’re a developer, analyst, creator, or enterprise leader, Airia makes it incredibly easy to build powerful AI agents — without wrestling with multiple tools or complex integrations. Using the no-code builder, you can drag-and-drop actions, connect data, choose your LLM, and launch an agent in minutes. Then run it live, publish it, and even share it with the Airia Community, home to 2,500+ pre-built agents you can use or remix. If you want to automate workflows, prototype faster, or explore real enterprise AI use cases, Airia is the place to start. 👉 Build your first agent today: 👉 Explore the community: #Airia #AgenticAI #AIOrchestration #AIAgents #AIWorkflow #DigitalTransformation

Adarsh Chetan

269,292 次观看 • 9 个月前

From the beginning, Flow has been a tool built by artists, for artists. In that spirit, we have some news: 1) Welcome Henry Daubrez 🌸💀 as our first filmmaker in residence who will work directly with our team to shape the future of Flow. 2) We're launching Flow Sessions, a pilot program that will provide mentorship and education for filmmakers on how they can best use Flow to bring their stories to life. Learn more:

From the beginning, Flow has been a tool built by artists, for artists. In that spirit, we have some news: 1) Welcome Henry Daubrez 🌸💀 as our first filmmaker in residence who will work directly with our team to shape the future of Flow. 2) We're launching Flow Sessions, a pilot program that will provide mentorship and education for filmmakers on how they can best use Flow to bring their stories to life. Learn more:

Google Flow

137,133 次观看 • 1 年前

$We built a tool that finds everything the internet knows about you. Most people think they're careful online. They're not. Here's what the agents pull within minutes: • Old passwords exposed in breaches you forgot about. • Usernames from accounts you abandoned • Every platform you've ever signed up for. • Your full address history. • Family members surfaced from public records. • Photos tied to your name on sites you never posted to. That's a fraction of what comes back. In 2026 anyone with the right tool finds this in minutes. The least you can do is see it on yourself first so you can take it down. Free to run on yourself. Link in comments.$

We built a tool that finds everything the internet knows about you. Most people think they're careful online. They're not. Here's what the agents pull within minutes: • Old passwords exposed in breaches you forgot about. • Usernames from accounts you abandoned • Every platform you've ever signed up for. • Your full address history. • Family members surfaced from public records. • Photos tied to your name on sites you never posted to. That's a fraction of what comes back. In 2026 anyone with the right tool finds this in minutes. The least you can do is see it on yourself first so you can take it down. Free to run on yourself. Link in comments.

Saarth Shah

382,193 次观看 • 4 个月前

recreated this exact hook with AI in 3 minutes generated first frame with nano banana -> uploaded it along with reference video to Kling motion control, done when the quality is actually there, AI UGC beats real creators every time we built the best system for this right now: - realistic visuals - realistic voice - realistic movement - all optimized for virality and conversions way cheaper than a real creator and built for scale across thousands of posts and multiple accounts this isn't generic AI slop, these are high quality systems built with real effort and ready to scale your business it works across ecom,apps, saas, coaching, DTC... everything yet people are still paying $300-500 per UGC video from creators who ghost halfway through the project

recreated this exact hook with AI in 3 minutes generated first frame with nano banana -> uploaded it along with reference video to Kling motion control, done when the quality is actually there, AI UGC beats real creators every time we built the best system for this right now: - realistic visuals - realistic voice - realistic movement - all optimized for virality and conversions way cheaper than a real creator and built for scale across thousands of posts and multiple accounts this isn't generic AI slop, these are high quality systems built with real effort and ready to scale your business it works across ecom,apps, saas, coaching, DTC... everything yet people are still paying $300-500 per UGC video from creators who ghost halfway through the project

MAX

171,662 次观看 • 6 个月前

this is f*cking gold engineers at Meta just deleted the most expensive part of multi-agent systems: instead of training a communication topology, they compile a fresh one for every query 20 agents went from 7 hours to 6 minutes. the problem everyone hits: 5 agents works. 20 agents turns into a group chat that answers slower than one model and costs more than the task is worth. ReActNet's fix is that the graph is written per query, not learned once: > an LLM controller reads the query and the agent roster > it compiles a sequence of directed graphs, one per reasoning stage > every edge carries a written instruction, e.g. "list boundary cases for this behavior" > each agent updates its state from its own previous state plus assigned neighbors > a final node aggregates all five states into the answer > no RL, no gradients, no training stage at all what that buys on gpt-4o: 92.75 average across 6 benchmarks, best on 5 of them. 100.00 on MultiArith. 92.74 pass@1 on HumanEval, +21 over a single model. and the number that should worry anyone running a swarm: at 20 agents GPTSwarm needs 412 minutes and $41.42. ReActNet needs 6.22 minutes and $6.53 and scores higher. the honest catch: more agents did not make it smarter. 5 agents scored 79.74, 20 scored 77.77. the topology was never the thing to learn.

this is f*cking gold engineers at Meta just deleted the most expensive part of multi-agent systems: instead of training a communication topology, they compile a fresh one for every query 20 agents went from 7 hours to 6 minutes. the problem everyone hits: 5 agents works. 20 agents turns into a group chat that answers slower than one model and costs more than the task is worth. ReActNet's fix is that the graph is written per query, not learned once: > an LLM controller reads the query and the agent roster > it compiles a sequence of directed graphs, one per reasoning stage > every edge carries a written instruction, e.g. "list boundary cases for this behavior" > each agent updates its state from its own previous state plus assigned neighbors > a final node aggregates all five states into the answer > no RL, no gradients, no training stage at all what that buys on gpt-4o: 92.75 average across 6 benchmarks, best on 5 of them. 100.00 on MultiArith. 92.74 pass@1 on HumanEval, +21 over a single model. and the number that should worry anyone running a swarm: at 20 agents GPTSwarm needs 412 minutes and $41.42. ReActNet needs 6.22 minutes and $6.53 and scores higher. the honest catch: more agents did not make it smarter. 5 agents scored 79.74, 20 scored 77.77. the topology was never the thing to learn.

NO1ennn

26,237 次观看 • 6 天前

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓

Argona

891,346 次观看 • 1 个月前