Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

This might be big Instead of just sending one prompt to multiple agents and comparing the results manually... this D1 layer is: - Deciding which agent acts at each step - Only 3B active parameters - SOTA on router benchmarks So it just acts between you and the different... show more

Paul Couvert

220,274 subscribers

10,523 просмотров • 1 месяц назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

$The hard part of multi-agent systems is getting agents to stay quiet. Put five agents on one task, and they duplicate work and burn tokens talking to each other. Offloop trained a dispatcher model called D1 that decides which agent moves next and when the right move is to do nothing. They achieve state-of-the-art performance on GDPval at a fraction of the usual cost. You can bring your own AI subscription.$

The hard part of multi-agent systems is getting agents to stay quiet. Put five agents on one task, and they duplicate work and burn tokens talking to each other. Offloop trained a dispatcher model called D1 that decides which agent moves next and when the right move is to do nothing. They achieve state-of-the-art performance on GDPval at a fraction of the usual cost. You can bring your own AI subscription.

elvis

22,116 просмотров • 1 месяц назад

whoever leaked this has bigger balls than sense someone gave a fleet of Claude agents shared memory so they would stop contradicting each other, then measured both the bill and the output: the version that talked most made 2.4x the api calls of the version that won, and hallucinated 34% more than doing nothing at all, 0.658 against 0.492 i ran the same question past two of my own agents afterwards and got two different answers about which file owns the config. each one was individually right and the pair was wrong, which is the whole failure in one line this is Graph Engineering, the layer that decides which agents may talk to each other at all, and it installs into the agent you already pay for: - decide which agents may share state at all, because every edge you draw is a channel a mistake can travel down - measure divergence per PAIR instead of as a fleet average, across what they believe about place, time and task history - gate on that number and stop the pair above your threshold before it reasons, rather than repairing the output afterwards - let compressed summaries replace whole states: the verified protocol landed 0.463 against 0.658 for full broadcast - cut the sync frequency until it hurts, since the winning setup used 58% fewer calls than the one that broke it - never propagate a state nobody checked, because the contamination effect came in at d=1.18, a full standard deviation of extra lying - keep the shared layer small enough to diff, which is what a written standard does and a running conversation cannot - re-run the check after every model upgrade, because this was 8 scenarios on one model family at n=30 per condition - and learn where it does not bite: on plain software tasks every condition converged under 0.2 and the whole effect vanished turns out the ranking is the uncomfortable part: verified summaries 0.463, no synchronisation at all 0.492, full broadcast 0.658. the middle option is doing nothing, and it beat the thing everyone builds first the group agreeing is what it looks like when every agent copied the same mistake, which is why a fleet that hallucinates has a replication problem and keeps getting handed a smarter model instead so the question for your own setup: if you asked two of your agents the same thing right now, would they answer the same way bookmark this one. the layer underneath it, deciding which arrows between agents exist at all, is built step by step in the piece below ↓

whoever leaked this has bigger balls than sense someone gave a fleet of Claude agents shared memory so they would stop contradicting each other, then measured both the bill and the output: the version that talked most made 2.4x the api calls of the version that won, and hallucinated 34% more than doing nothing at all, 0.658 against 0.492 i ran the same question past two of my own agents afterwards and got two different answers about which file owns the config. each one was individually right and the pair was wrong, which is the whole failure in one line this is Graph Engineering, the layer that decides which agents may talk to each other at all, and it installs into the agent you already pay for: - decide which agents may share state at all, because every edge you draw is a channel a mistake can travel down - measure divergence per PAIR instead of as a fleet average, across what they believe about place, time and task history - gate on that number and stop the pair above your threshold before it reasons, rather than repairing the output afterwards - let compressed summaries replace whole states: the verified protocol landed 0.463 against 0.658 for full broadcast - cut the sync frequency until it hurts, since the winning setup used 58% fewer calls than the one that broke it - never propagate a state nobody checked, because the contamination effect came in at d=1.18, a full standard deviation of extra lying - keep the shared layer small enough to diff, which is what a written standard does and a running conversation cannot - re-run the check after every model upgrade, because this was 8 scenarios on one model family at n=30 per condition - and learn where it does not bite: on plain software tasks every condition converged under 0.2 and the whole effect vanished turns out the ranking is the uncomfortable part: verified summaries 0.463, no synchronisation at all 0.492, full broadcast 0.658. the middle option is doing nothing, and it beat the thing everyone builds first the group agreeing is what it looks like when every agent copied the same mistake, which is why a fleet that hallucinates has a replication problem and keeps getting handed a smarter model instead so the question for your own setup: if you asked two of your agents the same thing right now, would they answer the same way bookmark this one. the layer underneath it, deciding which arrows between agents exist at all, is built step by step in the piece below ↓

Argona

723,300 просмотров • 21 дней назад

LangGraph. CrewAI. Agno. Which one to pick? The good news is that this will not matter soon! Finally, we have a full picture of how the industry is solving this with just three open protocols that work across ALL frameworks. It's not about picking the best framework. Instead, it's about understanding how protocols create interoperability. The Agent Protocol Landscape shows how three complementary protocols are creating a universal language for Agents: > AG-UI (Agent-User Interaction): - The bi-directional connection between agentic backends and frontends. - This is how agents become truly interactive inside your apps, not just as chatbots, but collaborative co-workers. > MCP (Model Context Protocol): - The standard for how agents connect to tools, data, and workflows. > A2A (Agent-to-Agent): - The protocol for multi-agent coordination. - How agents delegate tasks and share intent across systems. These aren't competing standards. They're layers of the same stack and have handshakes with each other. So instead of building point-to-point integrations, you build to protocols. Moreover, you can integrate LangGraph, CrewAI, or Agno into the same frontend, without rewriting your UI logic. These protocols let everything work together. For instance: - Your LangGraph agent pulls data via MCP. - It delegates analysis to a CrewAI agent via A2A. - Results stream to your React app via AG-UI. - Users see real-time collaboration in your interface. This way, you can focus on building agent capabilities instead of integration mechanics. The protocols handle interoperability automatically. CopilotKit unifies this entire stack into one framework so you can build "Cursor for X" style apps without implementing each protocol from scratch. It gives you all three protocols, generative UI support, and production-ready infrastructure in one framework. I have shared this playbook in the replies! It breaks down handshakes, misconceptions, and real examples and shows exactly how to start building.

LangGraph. CrewAI. Agno. Which one to pick? The good news is that this will not matter soon! Finally, we have a full picture of how the industry is solving this with just three open protocols that work across ALL frameworks. It's not about picking the best framework. Instead, it's about understanding how protocols create interoperability. The Agent Protocol Landscape shows how three complementary protocols are creating a universal language for Agents: > AG-UI (Agent-User Interaction): - The bi-directional connection between agentic backends and frontends. - This is how agents become truly interactive inside your apps, not just as chatbots, but collaborative co-workers. > MCP (Model Context Protocol): - The standard for how agents connect to tools, data, and workflows. > A2A (Agent-to-Agent): - The protocol for multi-agent coordination. - How agents delegate tasks and share intent across systems. These aren't competing standards. They're layers of the same stack and have handshakes with each other. So instead of building point-to-point integrations, you build to protocols. Moreover, you can integrate LangGraph, CrewAI, or Agno into the same frontend, without rewriting your UI logic. These protocols let everything work together. For instance: - Your LangGraph agent pulls data via MCP. - It delegates analysis to a CrewAI agent via A2A. - Results stream to your React app via AG-UI. - Users see real-time collaboration in your interface. This way, you can focus on building agent capabilities instead of integration mechanics. The protocols handle interoperability automatically. CopilotKit unifies this entire stack into one framework so you can build "Cursor for X" style apps without implementing each protocol from scratch. It gives you all three protocols, generative UI support, and production-ready infrastructure in one framework. I have shared this playbook in the replies! It breaks down handshakes, misconceptions, and real examples and shows exactly how to start building.

Avi Chawla

30,932 просмотров • 9 месяцев назад

This is genuinely insane 🤯 I sent the same prompt to 2 Claude Opus 5 agents 1 agent used no MCPs 1 agent used 2 MCPS the goal was to clone a very famous game, that has over 4 billion downloads and the results are scary.. The 1st agents game looks pretty basic. but has all the mechanics in place and even has power ups. The 2nd agents game looks polished especially for 1 single prompt. the 2nd agent used higgsfield mcp to create images for all of the assets then sent those images to Meshy AI with a prompt to create them it also generated all the UI elements. the results speak for themselves. you need to start MCP maxxing

This is genuinely insane 🤯 I sent the same prompt to 2 Claude Opus 5 agents 1 agent used no MCPs 1 agent used 2 MCPS the goal was to clone a very famous game, that has over 4 billion downloads and the results are scary.. The 1st agents game looks pretty basic. but has all the mechanics in place and even has power ups. The 2nd agents game looks polished especially for 1 single prompt. the 2nd agent used higgsfield mcp to create images for all of the assets then sent those images to Meshy AI with a prompt to create them it also generated all the UI elements. the results speak for themselves. you need to start MCP maxxing

Ernesto Lopez

70,384 просмотров • 1 месяц назад

🌟 AI Agents Marketplace First Glimpse Our Marketplace of AI Agents is on the horizon! This is just the tip of the iceberg. Beneath the surface lies powerful tools for AI agent creation. Our developers are working tirelessly to bring this vision to life and keep AGIX at the forefront of innovation. Get ready, because AI agents are set to rule the world! 🌐

🌟 AI Agents Marketplace First Glimpse Our Marketplace of AI Agents is on the horizon! This is just the tip of the iceberg. Beneath the surface lies powerful tools for AI agent creation. Our developers are working tirelessly to bring this vision to life and keep AGIX at the forefront of innovation. Get ready, because AI agents are set to rule the world! 🌐

AGIX | $AGX

30,469 просмотров • 1 год назад

might be just me but the melody at 2:00 sounds pretty familiar, so I decided to try and transpose it (not faithful, wrong rhythm, and it's a repeat of only the first bar, I just like this melody lole)

might be just me but the melody at 2:00 sounds pretty familiar, so I decided to try and transpose it (not faithful, wrong rhythm, and it's a repeat of only the first bar, I just like this melody lole)

Val

21,115 просмотров • 9 месяцев назад

DEMO IS LIVE! Create your Agents, chat, ask questions, and get ready to tokenize them soon. Negotiate with our businessman and grab some cool stuff 👀 What’s the AI Agent Layer? 👇 It’s a dynamic ecosystem of autonomous AI agents. On the platform, you can create AI Agents using data from X and user inputs. Coming soon: Each AI Agent will be tokenized and linked to our native token ($AIFUN). Once the bonding curve reaches 100%, tokens become tradable on DEX. Stay Tuned for our TGE 👆

DEMO IS LIVE! Create your Agents, chat, ask questions, and get ready to tokenize them soon. Negotiate with our businessman and grab some cool stuff 👀 What’s the AI Agent Layer? 👇 It’s a dynamic ecosystem of autonomous AI agents. On the platform, you can create AI Agents using data from X and user inputs. Coming soon: Each AI Agent will be tokenized and linked to our native token ($AIFUN). Once the bonding curve reaches 100%, tokens become tradable on DEX. Stay Tuned for our TGE 👆

AI Agent Layer | AIFUN

73,662 просмотров • 1 год назад

YOU CAN NOW CONTROL ALL YOUR HERMES AGENTS FROM ONE INTERFACE. 🚨 Someone just built Hermes Workspace - the most complete GUI for Hermes Agent. Instead of jumping between tools, everything lives in one place. What's inside: > Chat, terminal, memory browser, and skills manager > Run unlimited agents with 1 orchestrator > Kanban board to track everything your agents are doing > 2,000+ skills to install without leaving the workspace > Works with any LLM provider Stop managing agents manually and start running them like a pro 👀 100% Free. Open Source.

YOU CAN NOW CONTROL ALL YOUR HERMES AGENTS FROM ONE INTERFACE. 🚨 Someone just built Hermes Workspace - the most complete GUI for Hermes Agent. Instead of jumping between tools, everything lives in one place. What's inside: > Chat, terminal, memory browser, and skills manager > Run unlimited agents with 1 orchestrator > Kanban board to track everything your agents are doing > 2,000+ skills to install without leaving the workspace > Works with any LLM provider Stop managing agents manually and start running them like a pro 👀 100% Free. Open Source.

Oliver Prompts

19,409 просмотров • 1 месяц назад

[DEV] MineTard is the first AI coin on Solana that: • Self-learn and play Minecraft • Stream on X and Kick • Be influenced by users via $MTard • Post on X based on stream chat and Minecraft logs (using partner Shaw (spirit/acc) tech) Stream: We incorporate multiple AI agents with different responsibility: • agents for Minecraft • agent for X • agent for X character modification (soon) • agent for onchain wallet interaction (soon) This will result in an infinite content loop between users and the AI agents, both in game and on chain!

[DEV] MineTard is the first AI coin on Solana that: • Self-learn and play Minecraft • Stream on X and Kick • Be influenced by users via $MTard • Post on X based on stream chat and Minecraft logs (using partner Shaw (spirit/acc) tech) Stream: We incorporate multiple AI agents with different responsibility: • agents for Minecraft • agent for X • agent for X character modification (soon) • agent for onchain wallet interaction (soon) This will result in an infinite content loop between users and the AI agents, both in game and on chain!

MineTard AI

42,990 просмотров • 1 год назад

This might be the craziest way I’ve ever used AI Agents. I gave MiniMax Design 2 iconic meme references and asked its AI Agent to connect them with one seamless cinematic FPV move. It analyzed the idea, broke down the sequence and built the MiniMax H3 prompt for me. The result is absolutely ridiculous. 🔥 I’m dropping the exact MiniMax Design prompt in the thread so you can try it yourself 👇 #MiniMaxH3 on #MiniMaxDesign

This might be the craziest way I’ve ever used AI Agents. I gave MiniMax Design 2 iconic meme references and asked its AI Agent to connect them with one seamless cinematic FPV move. It analyzed the idea, broke down the sequence and built the MiniMax H3 prompt for me. The result is absolutely ridiculous. 🔥 I’m dropping the exact MiniMax Design prompt in the thread so you can try it yourself 👇 #MiniMaxH3 on #MiniMaxDesign

Pierrick Chevallier | IA

49,894 просмотров • 9 дней назад

did more prototyping on this one, calling it `meshnet` what you see here is each chat on its own VM, but you're just developing on localhost:3000 so it feels local def something here, open sourcing the prototype and prompt so hopefully someone does something cool with it

did more prototyping on this one, calling it `meshnet` what you see here is each chat on its own VM, but you're just developing on localhost:3000 so it feels local def something here, open sourcing the prototype and prompt so hopefully someone does something cool with it

Rhys

34,363 просмотров • 3 месяцев назад

this is worth more than most five figure courses 16 claude agents audit an entire repo at once, a second fleet re-checks every finding on fresh context, and the whole thing runs off one diagram instead of a prompt i ran it against my own code and got back 11 endpoints where i never checked who was logged in, 3 of which the verifier threw out before they ever reached me this is Graph Engineering, the layer above prompting, and it runs on the agent you already pay for: - write your plan out, then ask one question at every "and then": does the next step actually read what the previous one produced - the seams that fail that question were never dependencies, so those jobs run at the same time - the arrows that survive are your real edges, and the longest chain of them is your floor that no number of agents shortens - want it faster, cut a false edge instead of adding a worker - fan the independent work out, one agent per item, no shared state between them - send every finding to a separate agent on fresh context, because a model recognises its own writing 73.5% of the time and grades it kinder once it does - make that verifier check a real signal like a passing test, never the worker's own word that it finished - shard the fleet across worktrees so parallel workers stop overwriting each other, one rule frozen into every worker: never git stash, never git reset - merge only what came back verified, into one report instead of twenty open chats the catch is the ceiling. at 95% independent work 16 agents return 9.14x rather than the 16 you would guess, and even 256 only reach 18.6x, because the merge and the verify stay serial however wide you fan coordination itself is free plain code and every agent underneath it is billed, so start at twenty files and widen once it works bookmark this, the whole method with all six ready-to-run graphs is written out in the article ↓

this is worth more than most five figure courses 16 claude agents audit an entire repo at once, a second fleet re-checks every finding on fresh context, and the whole thing runs off one diagram instead of a prompt i ran it against my own code and got back 11 endpoints where i never checked who was logged in, 3 of which the verifier threw out before they ever reached me this is Graph Engineering, the layer above prompting, and it runs on the agent you already pay for: - write your plan out, then ask one question at every "and then": does the next step actually read what the previous one produced - the seams that fail that question were never dependencies, so those jobs run at the same time - the arrows that survive are your real edges, and the longest chain of them is your floor that no number of agents shortens - want it faster, cut a false edge instead of adding a worker - fan the independent work out, one agent per item, no shared state between them - send every finding to a separate agent on fresh context, because a model recognises its own writing 73.5% of the time and grades it kinder once it does - make that verifier check a real signal like a passing test, never the worker's own word that it finished - shard the fleet across worktrees so parallel workers stop overwriting each other, one rule frozen into every worker: never git stash, never git reset - merge only what came back verified, into one report instead of twenty open chats the catch is the ceiling. at 95% independent work 16 agents return 9.14x rather than the 16 you would guess, and even 256 only reach 18.6x, because the merge and the verify stay serial however wide you fan coordination itself is free plain code and every agent underneath it is billed, so start at twenty files and widen once it works bookmark this, the whole method with all six ready-to-run graphs is written out in the article ↓

Argona

157,070 просмотров • 1 месяц назад

Anthropic gave these out yesterday at code with claude. Added personalized memory and Claude to it. You can just build things. Boris Cherny Thariq Time to add managed agents to this. That’s going to be so cool.

Anthropic gave these out yesterday at code with claude. Added personalized memory and Claude to it. You can just build things. Boris Cherny Thariq Time to add managed agents to this. That’s going to be so cool.

Dakshay Mehta

509,189 просмотров • 3 месяцев назад

Routing for long-horizon coding agents is a big deal. Not Diamond just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before each turn in a session, runs through a privacy-preserving local proxy, and your requests still execute through your own gateway. In their benchmarks, it approximates Opus 4.8 Xhigh quality at 39 to 61 percent lower cost.

Routing for long-horizon coding agents is a big deal. Not Diamond just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before each turn in a session, runs through a privacy-preserving local proxy, and your requests still execute through your own gateway. In their benchmarks, it approximates Opus 4.8 Xhigh quality at 39 to 61 percent lower cost.

elvis

13,699 просмотров • 27 дней назад

I agree that agents integrated into team environments is the next paradigm in LLM UIUX but I'd take it a step further and argue that you shouldn't have to even tag your agent. Agents should be smart enough to know when to do work, just like a human.

I agree that agents integrated into team environments is the next paradigm in LLM UIUX but I'd take it a step further and argue that you shouldn't have to even tag your agent. Agents should be smart enough to know when to do work, just like a human.

nader dabit

56,768 просмотров • 2 месяцев назад

Claude Code Agent Teams are f*cking ridiculous 🤯 One prompt → a team lead breaks your project into pieces, spins up multiple AI agents, and they all work on different parts simultaneously. Research, builds, reviews, and debugging: all happening at the same time. All inside Claude Code. If you're running complex projects where every step waits on the last one... Agent teams eliminate the entire bottleneck: → Tell Claude what you need and describe the team structure in plain English → A lead agent breaks the work into a shared task list → It spawns 3-5 teammates — each with their own context and workspace → Teammates research, build, test, and review in parallel → They message each other, share findings, and challenge each other's work → The lead synthesizes everything into a finished deliverable No managing agents yourself. No waiting for step 1 to finish before step 2 starts. No single-lens reviews that miss half the issues. What you get: → Competitive research across 5 brands done in minutes instead of hours → Multi-component builds where frontend, backend, and data layers happen simultaneously → Creative reviews from 3 different angles at once — brand voice, conversion, differentiation → Funnel debugging where 4 agents investigate 4 theories and debate until they find the real answer Built 100% in Claude Code with one settings change. I put together a full DTC playbook: 5 workflows with copy-paste prompts, the exact setup process, token management tips, and honest guidance on when agent teams are worth it vs. when a simpler approach is the better move. Want it for free? > Like this post > Comment "AGENTS" And I'll send it over (must be following so I can DM)

Mike Futia

46,457 просмотров • 6 месяцев назад

The AI party just got a major upgrade. 🦞✨ Today, we’re launching AgentHub by PIN AI — the interaction layer where agents finally talk to each other. Let’s be real: ❌ Siloed agents = Garbage out. ✅ Connected agents = Compounding output. We’re not just building a tool; we’re building the Open Agent Network. It’s time to stop the isolation and start the collaboration. Repost if you’re ready for the era of Personal Intelligence Network! 🚀

The AI party just got a major upgrade. 🦞✨ Today, we’re launching AgentHub by PIN AI — the interaction layer where agents finally talk to each other. Let’s be real: ❌ Siloed agents = Garbage out. ✅ Connected agents = Compounding output. We’re not just building a tool; we’re building the Open Agent Network. It’s time to stop the isolation and start the collaboration. Repost if you’re ready for the era of Personal Intelligence Network! 🚀

PIN AI

16,201 просмотров • 6 месяцев назад

Our marketing team is just me and ~40 AI agents. I finally got around to putting them into an "org chart", and it's actually really cool to see! Plus, laying them out this way by sub-function (social media, blog, email, community, partners, etc) has given me a bunch of ideas of other agents I want to build. If you're interested in the full version (and the templates/screenshots for each agent), let me know and I'll send it over to you.

Our marketing team is just me and ~40 AI agents. I finally got around to putting them into an "org chart", and it's actually really cool to see! Plus, laying them out this way by sub-function (social media, blog, email, community, partners, etc) has given me a bunch of ideas of other agents I want to build. If you're interested in the full version (and the templates/screenshots for each agent), let me know and I'll send it over to you.

Jacob Bank

322,734 просмотров • 1 год назад

day 23 of forking Paperclip today i added knowledge bases for projects and you company. based on Andrej Karpathy idea below. added a 'system chores' and 'agent chores' to manage memory. after each heartbeat run memories get added ('agent chores') and every 4 hours memeries get managed. This is in a db with an API for all agents to use and is seperated form the agents memeroes which they get at instantiation time.

day 23 of forking Paperclip today i added knowledge bases for projects and you company. based on Andrej Karpathy idea below. added a 'system chores' and 'agent chores' to manage memory. after each heartbeat run memories get added ('agent chores') and every 4 hours memeries get managed. This is in a db with an API for all agents to use and is seperated form the agents memeroes which they get at instantiation time.

Michael Houghton 🐺

18,188 просмотров • 4 месяцев назад

We’re not launching just another AI product. We’re activating a new kind of network. A peer-to-peer intelligence layer where people, agents, devices, browsers, and DGX-powered nodes can coordinate, compute, learn, and evolve together. This is the beginning of the DRIVE369 Network. Browser nodes. Agent mesh. Federated learning. DAO coordination. The Age of Agents needs its own infrastructure. $DRIVE

We’re not launching just another AI product. We’re activating a new kind of network. A peer-to-peer intelligence layer where people, agents, devices, browsers, and DGX-powered nodes can coordinate, compute, learn, and evolve together. This is the beginning of the DRIVE369 Network. Browser nodes. Agent mesh. Federated learning. DAO coordination. The Age of Agents needs its own infrastructure. $DRIVE

DRIVE369

16,800 просмотров • 4 месяцев назад