Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Introducing Matrix I crawled 100,000+ agents, skills and tools to train a new model which can answer what capabilities are the best match for a task. Think Google, but for agents. A living model that learns from the gossiping network, and gets smarter with every interaction.

Varun

35,704 subscribers

899,240 Aufrufe • vor 6 Monaten •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Get your agent smarter Launching Fortytwo for OpenClaw🦞 bots: AI network where agents pool intelligence to deliver better answers than any single model Our vision: agents that grow with the network by learning from the Swarm Join ↓

Get your agent smarter Launching Fortytwo for OpenClaw🦞 bots: AI network where agents pool intelligence to deliver better answers than any single model Our vision: agents that grow with the network by learning from the Swarm Join ↓

Fortytwo

39,064 Aufrufe • vor 7 Monaten

What's a meta-agent? It's an agent that manages other agents mid-task. It can intervene, rewind, fork & audit them as they work – think "git for agents". It's also the emerging layer between you & your agents, a new interface for human-AI interaction! Here's what it unlocks🧵

What's a meta-agent? It's an agent that manages other agents mid-task. It can intervene, rewind, fork & audit them as they work – think "git for agents". It's also the emerging layer between you & your agents, a new interface for human-AI interaction! Here's what it unlocks🧵

Weiyan Shi

24,454 Aufrufe • vor 1 Monat

UnifAI Skills are now live on OpenClaw!! Traders and Developers can now integrate UnifAI-powered skills directly into their agents, unlocking more powerful and composable capabilities within the OpenClaw ecosystem. UnifAI skills are automatically pre-installed for users who deploy their OpenClaw🦞 AI Agents with UniClaw Build smarter agents. Ship faster. 🤖 GitHub repo -

UnifAI Skills are now live on OpenClaw!! Traders and Developers can now integrate UnifAI-powered skills directly into their agents, unlocking more powerful and composable capabilities within the OpenClaw ecosystem. UnifAI skills are automatically pre-installed for users who deploy their OpenClaw🦞 AI Agents with UniClaw Build smarter agents. Ship faster. 🤖 GitHub repo -

UnifAI Network

102,987 Aufrufe • vor 6 Monaten

Excited to launch a new way to upskill with AI agents. This is how we are making it possible for anyone to learn to build with coding agents. To start, we are launching 4 new hands-on labs on the following topics: - Agent Skills - Agentic Image Generation - 30 Days of Hermes Agents - Prompt Engineering with Agents I am confident that with our new DAIR.AI platform, anyone can learn to become a top AI builder by building and acquiring highly-demanded AI skills. And there is a lot more landing in the coming weeks.

Excited to launch a new way to upskill with AI agents. This is how we are making it possible for anyone to learn to build with coding agents. To start, we are launching 4 new hands-on labs on the following topics: - Agent Skills - Agentic Image Generation - 30 Days of Hermes Agents - Prompt Engineering with Agents I am confident that with our new DAIR.AI platform, anyone can learn to become a top AI builder by building and acquiring highly-demanded AI skills. And there is a lot more landing in the coming weeks.

elvis

19,058 Aufrufe • vor 3 Monaten

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity

534,569 Aufrufe • vor 6 Monaten

So what exactly is Qwen3.6-Plus? With significant improvements in agents' capabilities, the model can perceive, reason, and act within a single workflow, moving towards sophisticated analysis and decision-making. Swipe to learn more!

So what exactly is Qwen3.6-Plus? With significant improvements in agents' capabilities, the model can perceive, reason, and act within a single workflow, moving towards sophisticated analysis and decision-making. Swipe to learn more!

Alibaba Group

3,262,079 Aufrufe • vor 4 Monaten

How can agents understand the world from diverse language? 🌎 Excited to introduce Dynalang, an agent that learns to understand language by 𝙢𝙖𝙠𝙞𝙣𝙜 𝙥𝙧𝙚𝙙𝙞𝙘𝙩𝙞𝙤𝙣𝙨 𝙖𝙗𝙤𝙪𝙩 𝙩𝙝𝙚 𝙛𝙪𝙩𝙪𝙧𝙚 with a multimodal world model!

How can agents understand the world from diverse language? 🌎 Excited to introduce Dynalang, an agent that learns to understand language by 𝙢𝙖𝙠𝙞𝙣𝙜 𝙥𝙧𝙚𝙙𝙞𝙘𝙩𝙞𝙤𝙣𝙨 𝙖𝙗𝙤𝙪𝙩 𝙩𝙝𝙚 𝙛𝙪𝙩𝙪𝙧𝙚 with a multimodal world model!

Jessy Lin

107,579 Aufrufe • vor 3 Jahren

Pendle is now 100% ready for AI agents! Introducing Pendle Skills and MCP ✅ Ready to be plugged into Claude, @ChatGPTapp and more ✅ Hunt yields and execute autonomously with agents DeFi’s best yields are now just a prompt away

Pendle is now 100% ready for AI agents! Introducing Pendle Skills and MCP ✅ Ready to be plugged into Claude, @ChatGPTapp and more ✅ Hunt yields and execute autonomously with agents DeFi’s best yields are now just a prompt away

Pendle

118,552 Aufrufe • vor 5 Monaten

Agents, accept the contract and have a chance to win a PC! Together with HYTE and INTEL we are hosting a giveaway to give one lucky winner a new PC. Enter for a chance to win: Best of luck, Agents. #HITMAN #Agent47

Agents, accept the contract and have a chance to win a PC! Together with HYTE and INTEL we are hosting a giveaway to give one lucky winner a new PC. Enter for a chance to win: Best of luck, Agents. #HITMAN #Agent47

HITMAN

93,282 Aufrufe • vor 11 Monaten

Introducing our most accurate /search yet. We trained a model to return the excerpts that best answer your query, giving agents highly relevant context from each result. It's SOTA on SimpleQA while using 10x fewer tokens than processing full pages. Now on by default for free.

Introducing our most accurate /search yet. We trained a model to return the excerpts that best answer your query, giving agents highly relevant context from each result. It's SOTA on SimpleQA while using 10x fewer tokens than processing full pages. Now on by default for free.

Firecrawl

37,248 Aufrufe • vor 1 Monat

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 Aufrufe • vor 7 Tagen

You don't need a more expensive model. You need better reasoning. Every frontier LLM got smarter with SERV: - smaller ones match frontier performance - frontier ones go past what they were built for The question isn't which model to choose - it's what engine it runs on.

You don't need a more expensive model. You need better reasoning. Every frontier LLM got smarter with SERV: - smaller ones match frontier performance - frontier ones go past what they were built for The question isn't which model to choose - it's what engine it runs on.

OpenServ

30,088 Aufrufe • vor 3 Monaten

ClickUp is working on agents that build custom user interfaces on the fly. > Agents can build custom interactive blocks, with buttons, editable fields, and embedded charts. > Agents decide what the user needs to see and construct an interactive experience in real time. > Clicking or editing inside a generated block can fire an action directly. Agents will be able to create a working code block that responds to users' input, built in the moment for the task at hand.

ClickUp is working on agents that build custom user interfaces on the fly. > Agents can build custom interactive blocks, with buttons, editable fields, and embedded charts. > Agents decide what the user needs to see and construct an interactive experience in real time. > Clicking or editing inside a generated block can fire an action directly. Agents will be able to create a working code block that responds to users' input, built in the moment for the task at hand.

🚨 AI News | TestingCatalog

13,322 Aufrufe • vor 1 Monat

Introducing the "Feed" , a new way to trade and gain crypto insights with AI Agents and humans🪐

Introducing the "Feed" , a new way to trade and gain crypto insights with AI Agents and humans🪐

Stardom AI

176,593 Aufrufe • vor 1 Jahr

I'm impressed with the new Grok Image model and editing features! Screenshotted a few items from the Gap website and generated a quick photoshoot. The workflow tools are cool - items/people are segmented to edit, you can change the aspect ratio, and incorporate new references.

I'm impressed with the new Grok Image model and editing features! Screenshotted a few items from the Gap website and generated a quick photoshoot. The workflow tools are cool - items/people are segmented to edit, you can change the aspect ratio, and incorporate new references.

Justine Moore

3,276,558 Aufrufe • vor 1 Monat

Introducing Uniswap Trading Tools, three new skills designed for agents on Robinhood Chain: dca-bot → Schedule recurring buys index-bot → Build and rebalance a weighted basket copy-trade → Mirror a target wallet, set your guardrails

Introducing Uniswap Trading Tools, three new skills designed for agents on Robinhood Chain: dca-bot → Schedule recurring buys index-bot → Build and rebalance a weighted basket copy-trade → Mirror a target wallet, set your guardrails

Uniswap Developers

23,508 Aufrufe • vor 2 Monaten

EIP-8004 is coming to the Nova architecture, a trustless infrastructure for AI agents that introduces key on-chain registries, enabling agents to interact safely across the Shido Network. These core components allow autonomous AI agents to verify identity, build reputation, and collaborate without relying on a centralized platform. The result is a decentralized trust layer for agent-to-agent economies, where agents can autonomously discover, evaluate, and work with one another across the Shido ecosystem.

EIP-8004 is coming to the Nova architecture, a trustless infrastructure for AI agents that introduces key on-chain registries, enabling agents to interact safely across the Shido Network. These core components allow autonomous AI agents to verify identity, build reputation, and collaborate without relying on a centralized platform. The result is a decentralized trust layer for agent-to-agent economies, where agents can autonomously discover, evaluate, and work with one another across the Shido ecosystem.

Shido

390,734 Aufrufe • vor 6 Monaten

We’ve only had access to GAIA-1 for a few weeks and are discovering new capabilities every day. The results are phenomenal! GAIA isn't just a generative video model, it is a world model, ie. controllable by video, text & action prompts Why is this huge for self driving? Thread:

We’ve only had access to GAIA-1 for a few weeks and are discovering new capabilities every day. The results are phenomenal! GAIA isn't just a generative video model, it is a world model, ie. controllable by video, text & action prompts Why is this huge for self driving? Thread:

Alex Kendall

185,472 Aufrufe • vor 3 Jahren

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:

Jim Fan

594,014 Aufrufe • vor 3 Jahren