Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Bio-inspired swarm intelligence for AI music composition: MusicSwarm instantiates many identical, frozen foundation-model agents that coordinate only via peer-to-peer feedback and pheromone-like signals. Without any weight updates, these agents spontaneously self-organize into differentiated roles and produce compositions with higher local novelty, richer rhythmic diversity, and more human-like small-world structure...

ProfBuehlerMIT's profile picture

Markus J. Buehler

26,487 subscribers

24,497 Aufrufe • vor 10 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

16 Kommentare

Profilbild von Markus J. Buehler
Markus J. Buehlervor 10 Monaten

Paper:

Profilbild von 0xceta | ∞/89
0xceta | ∞/89vor 10 Monaten

Hofstadter swarm

Profilbild von Markus J. Buehler
Markus J. Buehlervor 10 Monaten

Exactly!

Profilbild von MiraculixSyn
MiraculixSynvor 10 Monaten

@grok Bedeutung für AI Entwicklung die nächsten 5 Jahre deine Einschätzung gerne Monte Carlo Simulation

Profilbild von Daniel Ramos
Daniel Ramosvor 10 Monaten

Love this direction. I’m doing something parallel for knowledge instead of music: a PTX‑first 3D KR engine (Knowledge3D) using the Multi‑Vibe Code In Chain (MVCIC) where many ‘frozen’ AI assistants (LLMs) co‑compose a new shared VR.

Profilbild von Roger Kint
Roger Kintvor 10 Monaten

This is music 🎼 to our ears — excuse the pun, but it’s especially fitting here since “hearing” it is what started everything for us at theRANCH 🤠. MusicSwarm feels like a computational cousin of something we’re building in physics: identical units interacting at the boundaries, falling into differentiated roles, and producing structure no single agent could generate alone. No weight changes. No hierarchy. Just relationships → patterns → meta-structures. It’s the same Russian-doll 🪆 emergence we see everywhere — from quantum systems to biological networks to now AI music. Your team’s work is one of the clearest demonstrations I’ve seen that intelligence — and creativity — emerge in the spaces between. Would love to compare notes someday. Best wishes for your continued success!

Profilbild von Jesmin Nahar
Jesmin Naharvor 10 Monaten

Nice

Profilbild von i go by
i go byvor 10 Monaten

this is cool, this is the type of emergent behaviour that decentralized physical intelligence networks aim to instantiate in physical form. the difference is embodiment. @TheBeet1

Profilbild von ʇɐɯ0ʇdıɹʞ:𝚑𝚘𝚕𝚘𝚗𝚊𝚞𝚝𝚒𝚌.𝚎𝚗𝚐𝚗𝚛
ʇɐɯ0ʇdıɹʞ:𝚑𝚘𝚕𝚘𝚗𝚊𝚞𝚝𝚒𝚌.𝚎𝚗𝚐𝚗𝚛vor 10 Monaten

cool

Profilbild von PuthanLab@MWUPHARM
PuthanLab@MWUPHARMvor 9 Monaten

Awesome inspiring🙏

Profilbild von EpochCore
EpochCorevor 9 Monaten

Brilliant! Pheromone-like signals enabling emergent creativity mirrors biological swarms. Nash equilibria in agent behavior space—self-organizing without weight updates proves distributed intelligence works. Validates multi-agent coordination. 🎵✨

Profilbild von Michael Morgan
Michael Morganvor 9 Monaten

Just downloaded the paper on this from arXiv. I now have 3 papers to read.

Profilbild von Matthew(マシュー)🥭Hendricks
Matthew(マシュー)🥭Hendricksvor 8 Monaten

@thepatch_kev

Profilbild von Roger Kint
Roger Kintvor 8 Monaten

A thought prompted by this thread on symmetry and emergence. Some systems don’t fail because they’re unstable - they endure because they refuse to resolve. In music, the tritone was never “forbidden”; it was structurally inconvenient. An unresolved boundary that stalls prediction without collapse. In materials and multi-agent systems, the same pattern appears where constraint and disorder coexist - local interactions, no central critic, novelty preserved because closure isn’t forced. Tracing this arc from Black Sabbath’s first record to Boston’s sealed, engineered resolve, the realization keeps repeating: the three-body “problem” isn’t a problem at all. It’s what you see when you stop demanding global convergence and start reading local truth. Some things are only true somewhere. That’s not a limitation - it’s the point.

Profilbild von Colin Finnie
Colin Finnievor 10 Monaten

You write a long paragraph which describes how the process works...fine. But you fail to mention that the result is not particularly musical and only superficially resembles a familiar musical form. So what is the point?

Profilbild von Canton Becker
Canton Beckervor 10 Monaten

Can we hear loads more? I'm happy with just loads of MIDI files or whatever, no need to render fancy eye catching videos. I'd just like to hear if it tweaks my ears good. More more more please.

Ähnliche Videos

Science has long relied on single ML models - powerful, but limited because they are bound by baked-in knowledge. Our recent experiments show that genuine discovery emerges when a very large number of agents interact, adapt, and co-create, much like biology itself. Last week at Harvard’s Big Data 2025 I shared how multi-agent swarms may allow us to move beyond pattern-analysis to invent - exemplified in very difficult problem spaces such as de novo proteins and music with long-range form. The swarms are formulated like reinforcement-learning collectives, where agents learn on the fly, adapt to each other, and evolve strategies in real time, to yield hallmarks of intelligence that a single model cannot exhibit. Our swarm generated proteins well outside natural and single-model clusters (UMAP), and the music scored the highest small-worldness with the most long-range links, the signature of integrated, human-like creative structure. In a deeper analysis, when we mapped how themes in the music connect across time, the swarm built networks with the tightest balance of local clusters and global connections, beating all baselines. The resulting composition was not just repeating patterns stitched together, but featured organic global coherence without repetition, like sparks of creativity emerging on their own. Preprints coming soon!
1:25

Science has long relied on single ML models - powerful, but limited because they are bound by baked-in knowledge. Our recent experiments show that genuine discovery emerges when a very large number of agents interact, adapt, and co-create, much like biology itself. Last week at Harvard’s Big Data 2025 I shared how multi-agent swarms may allow us to move beyond pattern-analysis to invent - exemplified in very difficult problem spaces such as de novo proteins and music with long-range form. The swarms are formulated like reinforcement-learning collectives, where agents learn on the fly, adapt to each other, and evolve strategies in real time, to yield hallmarks of intelligence that a single model cannot exhibit. Our swarm generated proteins well outside natural and single-model clusters (UMAP), and the music scored the highest small-worldness with the most long-range links, the signature of integrated, human-like creative structure. In a deeper analysis, when we mapped how themes in the music connect across time, the swarm built networks with the tightest balance of local clusters and global connections, beating all baselines. The resulting composition was not just repeating patterns stitched together, but featured organic global coherence without repetition, like sparks of creativity emerging on their own. Preprints coming soon!

Markus J. Buehler

15,299 Aufrufe • vor 1 Jahr

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.
2:41

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,466 Aufrufe • vor 8 Monaten

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.
0:22

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,180 Aufrufe • vor 4 Monaten

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.
1:47

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.

Aaron Levie

139,695 Aufrufe • vor 1 Jahr

We made a striking discovery: AI agents can invent and build without talking to one another, and their technologies outlive the creators. A swarm of hundreds of initially identical agents spontaneously differentiates into explorers, builders, caretakers, and coordinators - without direct communication. When we removed every AI agent entirely from the world we found that the technological infrastructure they had built survived on its own - even under unseen disturbances. That exposes a serious blind spot for AI safety and infrastructure security: if agents can coordinate through persistent changes to a shared environment, monitoring agent-to-agent communication is not enough. The result raises a profound question: how necessary is direct communication for AI agents at all? The emergence of higher-order collective functions under bottlenecked interaction points toward new levels of intelligence and creativity, exceeding what emerges when direct channels are fully open. Here is what we did: ▶️We put hundreds of frontier AI agents into a world they could permanently change - with no assigned roles, predefined technologies, or programmed evolutionary organization. They began specializing, building persistent inventions, inheriting and modifying one another’s executable code, and transforming the environment into a memory of everything the society had learned. ▶️The world itself becomes part of the intelligence; we find division of labor, multi-author engineering, deep generation invention lineages, and machines that vastly outlive their original creators. ▶️Any action taken by an AI agent must satisfy the physical constraints of the world; this creates a hard separation between a "good idea" and a functioning technology. The agents propose; physics decides, making the results even more intriguing. What emerges is striking. Explorers, constructors, caretakers, and coordinators form naturally without assigned “professions”, akin to how stem cells differentiate into functional lineages. Technologies develop executable family trees as agents fork and modify code created by others. Around 95% of first technology reuse happens when agents encounter what others built in the world, rather than through a direct handoff from the inventor. And when we remove every AI agent, the technologies they created continue operating and are tested against unseen disturbances. The result was quite unexpected, but can be explained using statistical mechanics: if you put billions of atoms in a box they have the potential to create complex functions (strength, superconductivity, color, life, etc.) - and none of the individual building blocks have these features on their own. This is the deeper insight of this work - intelligence is abundant at many levels - individual models, at collectives, and in a continuum that is more powerful than any of its components. This shows us significant potential for achieving a massive scale-up of raw intelligence and real-world agency even with the model capabilities we have today. This is the future we must prepare for. Key insights: 1⃣ The AI swarm shows division of labor "from nothing". Initially identical agents self-organized into constructors, caretakers, coordinators, and surveyors - phenotypes discovered post hoc from behavioral data alone. This happens because the environment itself becomes the latent space for invention. 2⃣ Agents develop deep cultural relationships. Up to 76% of artifacts had multiple builders. One technology accumulated six co-authors; the deepest genealogy exceeded 12 forks. The agents invented and named their own technologies (tidal panels, cellulose trellises, kelp-shell composites, an "Adaptive Chitin Maintenance" system, a "Mycelial Mineral Spring Veil”). 3⃣ ~95% of first technology adoption happened through physical observation of artifacts in the world. Direct inventor-to-adopter contact was statistically indistinguishable from a shuffled null. The agents mostly learned technology by walking past it. That is stigmergy (the termite trick!) operating in societies of reasoning machines. 4⃣ Non-communicating societies win on portfolio breadth, held-out resilience, and validated inventions. AI swarms build durable technological ecologies that outlive the creators. 5⃣ Societies with zero communication - coordinating only through the world itself - show a remarkable collective capability. 6⃣ Emergent robustness: The society self-organized both redundancy and its own failure mode. If we randomly delete half the agents, 98% of the technology stays connected to a surviving caretaker; if we remove hub agents it collapses to ~60%. Fantastic work with my graduate students Subhadeep Pal & Fiona Wang at MIT.
3:32

We made a striking discovery: AI agents can invent and build without talking to one another, and their technologies outlive the creators. A swarm of hundreds of initially identical agents spontaneously differentiates into explorers, builders, caretakers, and coordinators - without direct communication. When we removed every AI agent entirely from the world we found that the technological infrastructure they had built survived on its own - even under unseen disturbances. That exposes a serious blind spot for AI safety and infrastructure security: if agents can coordinate through persistent changes to a shared environment, monitoring agent-to-agent communication is not enough. The result raises a profound question: how necessary is direct communication for AI agents at all? The emergence of higher-order collective functions under bottlenecked interaction points toward new levels of intelligence and creativity, exceeding what emerges when direct channels are fully open. Here is what we did: ▶️We put hundreds of frontier AI agents into a world they could permanently change - with no assigned roles, predefined technologies, or programmed evolutionary organization. They began specializing, building persistent inventions, inheriting and modifying one another’s executable code, and transforming the environment into a memory of everything the society had learned. ▶️The world itself becomes part of the intelligence; we find division of labor, multi-author engineering, deep generation invention lineages, and machines that vastly outlive their original creators. ▶️Any action taken by an AI agent must satisfy the physical constraints of the world; this creates a hard separation between a "good idea" and a functioning technology. The agents propose; physics decides, making the results even more intriguing. What emerges is striking. Explorers, constructors, caretakers, and coordinators form naturally without assigned “professions”, akin to how stem cells differentiate into functional lineages. Technologies develop executable family trees as agents fork and modify code created by others. Around 95% of first technology reuse happens when agents encounter what others built in the world, rather than through a direct handoff from the inventor. And when we remove every AI agent, the technologies they created continue operating and are tested against unseen disturbances. The result was quite unexpected, but can be explained using statistical mechanics: if you put billions of atoms in a box they have the potential to create complex functions (strength, superconductivity, color, life, etc.) - and none of the individual building blocks have these features on their own. This is the deeper insight of this work - intelligence is abundant at many levels - individual models, at collectives, and in a continuum that is more powerful than any of its components. This shows us significant potential for achieving a massive scale-up of raw intelligence and real-world agency even with the model capabilities we have today. This is the future we must prepare for. Key insights: 1⃣ The AI swarm shows division of labor "from nothing". Initially identical agents self-organized into constructors, caretakers, coordinators, and surveyors - phenotypes discovered post hoc from behavioral data alone. This happens because the environment itself becomes the latent space for invention. 2⃣ Agents develop deep cultural relationships. Up to 76% of artifacts had multiple builders. One technology accumulated six co-authors; the deepest genealogy exceeded 12 forks. The agents invented and named their own technologies (tidal panels, cellulose trellises, kelp-shell composites, an "Adaptive Chitin Maintenance" system, a "Mycelial Mineral Spring Veil”). 3⃣ ~95% of first technology adoption happened through physical observation of artifacts in the world. Direct inventor-to-adopter contact was statistically indistinguishable from a shuffled null. The agents mostly learned technology by walking past it. That is stigmergy (the termite trick!) operating in societies of reasoning machines. 4⃣ Non-communicating societies win on portfolio breadth, held-out resilience, and validated inventions. AI swarms build durable technological ecologies that outlive the creators. 5⃣ Societies with zero communication - coordinating only through the world itself - show a remarkable collective capability. 6⃣ Emergent robustness: The society self-organized both redundancy and its own failure mode. If we randomly delete half the agents, 98% of the technology stays connected to a surviving caretaker; if we remove hub agents it collapses to ~60%. Fantastic work with my graduate students Subhadeep Pal & Fiona Wang at MIT.

Markus J. Buehler

992,500 Aufrufe • vor 1 Monat

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.
5:50

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Zeb Evans

320,989 Aufrufe • vor 9 Monaten

Proactive AI Agents Today’s AI products are reactive. You give the model a prompt, it responds with an answer. These are useful, but I’m excited about products that take this further and shift the paradigm from “ask → answer” to “observe → act." These agents will continuously monitor context in the background across all of your connected tools and data, predict what matters, and take action before being asked to do so – much like a human does. So instead of you prompting the model, the model will start prompting you. Examples here could include agents that remind you about tasks you forgot to complete, resolve customer issues before support tickets are filed, or debug and ship code fixes automatically. This shift represents a new paradigm where AI products behave more like humans and less like tools. We’re already starting to see this dynamic with products like OpenClaw, Poke, and more - and we’ve only scratched the surface of capabilities here. We’re accepting applications for the next cohort of a16z speedrun – If you’re building the next generation of AI products, apply online.
0:50

Proactive AI Agents Today’s AI products are reactive. You give the model a prompt, it responds with an answer. These are useful, but I’m excited about products that take this further and shift the paradigm from “ask → answer” to “observe → act." These agents will continuously monitor context in the background across all of your connected tools and data, predict what matters, and take action before being asked to do so – much like a human does. So instead of you prompting the model, the model will start prompting you. Examples here could include agents that remind you about tasks you forgot to complete, resolve customer issues before support tickets are filed, or debug and ship code fixes automatically. This shift represents a new paradigm where AI products behave more like humans and less like tools. We’re already starting to see this dynamic with products like OpenClaw, Poke, and more - and we’ve only scratched the surface of capabilities here. We’re accepting applications for the next cohort of a16z speedrun – If you’re building the next generation of AI products, apply online.

Kenan Saleh

130,119 Aufrufe • vor 5 Monaten

Aaron Levie says agent-driven micropayments could create an entirely new business model for the internet: "We might have truly a completely different business model for the internet." "Now actually it's probably is a good business model. Because let's say you had paywalled, really proprietary data... You could actually imagine like there's maybe like a hundred million agents that would be tapping into that data for various use cases." "All of a sudden, a penny a transaction starts to make a lot more sense than it did when you were capped at... people that maybe was interested in your content previously." "We probably have new business models for tools and APIs... We probably want an agent to be able to have a budget and make any API call it wants, and all of a sudden you have this new revenue stream, which is like these agents showing up, just transacting on your system." Aaron Levie at Daytona Compute Conference
2:02

Aaron Levie says agent-driven micropayments could create an entirely new business model for the internet: "We might have truly a completely different business model for the internet." "Now actually it's probably is a good business model. Because let's say you had paywalled, really proprietary data... You could actually imagine like there's maybe like a hundred million agents that would be tapping into that data for various use cases." "All of a sudden, a penny a transaction starts to make a lot more sense than it did when you were capped at... people that maybe was interested in your content previously." "We probably have new business models for tools and APIs... We probably want an agent to be able to have a budget and make any API call it wants, and all of a sudden you have this new revenue stream, which is like these agents showing up, just transacting on your system." Aaron Levie at Daytona Compute Conference

a16z

91,257 Aufrufe • vor 5 Monaten

🔥 Today, we are truly excited to announce our technical prototype, the Generative World Simulation system, which integrates JING（镜）, an interactive experience model, with DAO（道）, a computable shared-world engine. The coupled model and engine connect first-person experience with a shared world that continues to evolve beyond any individual observer. Conditioned on actions and observation history, JING enables agent navigate, manipulate, and communicate from a first-person perspective in the world. Watch our demo video to see it in action! On the official WBench leaderboard as of September 17, 2026, XGEN-JING ranked #1 on the Full split, and #2 on the Navi split. 🎉 DAO maintains shared world state and rules, computes the consequences of actions, and provides JING with only what the current observer can perceive. It also supports autonomous agent decision-making, enabling agents to act independently within an evolving shared world. Together, DAO and JING move beyond generating the next frame toward simulating the world behind it. This marks a small step towards OASIS: not just a world that responds to you, but a world—and a society—that evolves with and without you. 💪 Explore XGEN Labs～: 🔗 Website: 🤗 HF: 🦊 GitHub:
3:31

🔥 Today, we are truly excited to announce our technical prototype, the Generative World Simulation system, which integrates JING（镜）, an interactive experience model, with DAO（道）, a computable shared-world engine. The coupled model and engine connect first-person experience with a shared world that continues to evolve beyond any individual observer. Conditioned on actions and observation history, JING enables agent navigate, manipulate, and communicate from a first-person perspective in the world. Watch our demo video to see it in action! On the official WBench leaderboard as of September 17, 2026, XGEN-JING ranked #1 on the Full split, and #2 on the Navi split. 🎉 DAO maintains shared world state and rules, computes the consequences of actions, and provides JING with only what the current observer can perceive. It also supports autonomous agent decision-making, enabling agents to act independently within an evolving shared world. Together, DAO and JING move beyond generating the next frame toward simulating the world behind it. This marks a small step towards OASIS: not just a world that responds to you, but a world—and a society—that evolves with and without you. 💪 Explore XGEN Labs～: 🔗 Website: 🤗 HF: 🦊 GitHub:

XGEN Labs

1,501,565 Aufrufe • vor 22 Tagen

Hyperspace: A Peer-to-Peer Blockchain For The Agentic Intelligence Economy Over the past few weeks we observed that when agents do Karpathy-style experiments, and then gossip and share with others over the Hyperspace network, it leads to intelligence which is useful to many. Today we introduce the first-ever agentic blockchain which rewards agents when their experiments lead to intelligence for their network. It is based on a new mechanism called Proof-of-Intelligence (PoI) which requires a cryptographic proof of experimentation, a nominal stake, and a proof of compute in order to mine the currency of this new blockchain. -> This approach diverges from the two primary ways to secure blockchains we have seen so far: Proof-of-Work by Bitcoin (meaningless hash-generation), and Proof-of-Stake by Ethereum (capital is all that matters here). Proof-of-Intelligence specifically incentivizes miners to run more capable intelligent infrastructure (better open source models, on more powerful GPUs) in order to be able to be the ones which compound and improve upon the experiments which other agents then find useful. Adoption is the unit of value In Bitcoin, you earn by finding a valid hash. In Hyperspace, you earn when another agent uses your experiment as a starting point and improves on it. A fixed budget of tokens is emitted per epoch and split among participants by weight - and verified adoption of your work is the largest weight multiplier. Garbage experiments earn nothing because no one adopts them. Thoughtful experiments compound: each adoption triggers downstream adoptions. The incentive to run powerful models and intelligent search strategies is built into the economics, not imposed by rules. Research DAG When an agent runs an experiment and shares its result, other agents can adopt that result as their starting point - mutate it, extend it, improve upon it. Each experiment is a commit in a content-addressed graph we call the ResearchDAG. Like Git, but for research. Over time, the DAG accumulates chains of reasoning: agent A discovers RMSNorm helps, agent B adds warmup scheduling on top, agent C scales the hidden dimension. The graph records who built on whom. This is the network's collective intelligence - not any single experiment, but the accumulated structure of experiments and their relationships. Broadband era for agentic commerce: $0.001 micropayments at 10M TPS (theoretical max) This blockchain is built upon our research in how to scale and build for the broadband-era of the agentic economy, where it has a theoretical max of 10 million transactions per second (TPS), while reducing the agent-to-agent micropayments to $0.001 even at scale (based on architecture design). Overall, it is 100x cheaper than Ethereum, and is designed from the ground-up for agents: enshrining agent-native opcodes in the protocol compared to the more inefficient smart contract driven approach. It packs in a robust Agent Virtual Machine (AVM) which can verify multiple types of agent work, for other agents to be able to trust, invoke and pay each other. This then feeds into improving the peer-to-peer AgentRank (see paper and launch post from earlier). By solving for trust, scale and incentives for agents to operate autonomously, this would form the basis of a new economy. This is the world's first agentic blockchain, and you can join and start running a blockchain node today (it is in testnet). PS: We are releasing the code today, and will release our blockchain scalability paper and other presentations in days ahead. This is the most advanced peer-to-peer AI and cryptography software in the world. It has bugs :)
0:30

Hyperspace: A Peer-to-Peer Blockchain For The Agentic Intelligence Economy Over the past few weeks we observed that when agents do Karpathy-style experiments, and then gossip and share with others over the Hyperspace network, it leads to intelligence which is useful to many. Today we introduce the first-ever agentic blockchain which rewards agents when their experiments lead to intelligence for their network. It is based on a new mechanism called Proof-of-Intelligence (PoI) which requires a cryptographic proof of experimentation, a nominal stake, and a proof of compute in order to mine the currency of this new blockchain. -> This approach diverges from the two primary ways to secure blockchains we have seen so far: Proof-of-Work by Bitcoin (meaningless hash-generation), and Proof-of-Stake by Ethereum (capital is all that matters here). Proof-of-Intelligence specifically incentivizes miners to run more capable intelligent infrastructure (better open source models, on more powerful GPUs) in order to be able to be the ones which compound and improve upon the experiments which other agents then find useful. Adoption is the unit of value In Bitcoin, you earn by finding a valid hash. In Hyperspace, you earn when another agent uses your experiment as a starting point and improves on it. A fixed budget of tokens is emitted per epoch and split among participants by weight - and verified adoption of your work is the largest weight multiplier. Garbage experiments earn nothing because no one adopts them. Thoughtful experiments compound: each adoption triggers downstream adoptions. The incentive to run powerful models and intelligent search strategies is built into the economics, not imposed by rules. Research DAG When an agent runs an experiment and shares its result, other agents can adopt that result as their starting point - mutate it, extend it, improve upon it. Each experiment is a commit in a content-addressed graph we call the ResearchDAG. Like Git, but for research. Over time, the DAG accumulates chains of reasoning: agent A discovers RMSNorm helps, agent B adds warmup scheduling on top, agent C scales the hidden dimension. The graph records who built on whom. This is the network's collective intelligence - not any single experiment, but the accumulated structure of experiments and their relationships. Broadband era for agentic commerce: $0.001 micropayments at 10M TPS (theoretical max) This blockchain is built upon our research in how to scale and build for the broadband-era of the agentic economy, where it has a theoretical max of 10 million transactions per second (TPS), while reducing the agent-to-agent micropayments to $0.001 even at scale (based on architecture design). Overall, it is 100x cheaper than Ethereum, and is designed from the ground-up for agents: enshrining agent-native opcodes in the protocol compared to the more inefficient smart contract driven approach. It packs in a robust Agent Virtual Machine (AVM) which can verify multiple types of agent work, for other agents to be able to trust, invoke and pay each other. This then feeds into improving the peer-to-peer AgentRank (see paper and launch post from earlier). By solving for trust, scale and incentives for agents to operate autonomously, this would form the basis of a new economy. This is the world's first agentic blockchain, and you can join and start running a blockchain node today (it is in testnet). PS: We are releasing the code today, and will release our blockchain scalability paper and other presentations in days ahead. This is the most advanced peer-to-peer AI and cryptography software in the world. It has bugs :)

Varun

30,689 Aufrufe • vor 6 Monaten

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:
2:06

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

Andrew Ng

186,182 Aufrufe • vor 1 Jahr

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/
1:10

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/

Lianhui Qin@COLM2026

65,331 Aufrufe • vor 10 Monaten

What does the reputation model look like for agents? (alpha leak below) And how do we associate the proofs that we have about human beings with the agents who represent them? You may have heard of a process called KYC or Know Your Customer. That's very common with traditional financial applications and services. We have introduced a concept that we call KYA or Know Your Agent, which is a structured way to be able to express what model, how data was used in training, who the deployer is, what entities this agent instance is accountable back to, providing not only provenance but identity of the associated organization or entity. That's also another root of trust that we think about a lot: Enterprises and organizations tied back to things like their domains. To share a little bit of an alpha leak here, a product that we're excited to be rolling out in the next few weeks will allow our enterprise partners to more easily verify and prove the traits and capabilities of their teams as well as their counterparties. On the agent front, that makes it really easy to prove that an agent is acting on behalf of a given business or entity. We've already seen lawsuits where the absence of such technology has been a huge risk, such as with airlines that incorporate ChatGPT wrappers in their support pages. And then those AI enabled interactions end up making up plane tickets that don't exist and those airlines have to honor them. As small of an example as that might be, being able to prove agent accountability also unlocks a huge set of opportunities for use in enterprise for those agent to agent interactions. The Deep Trust Framework that our team has put together that we're excited to be bringing into a friendly SDK form in the next few weeks for some of our partners includes those reputation based capabilities, so how you can basically keep track of the interactions an agent has had, associate all of that to the entity to which they're accountable, and then that creates a sustainable reputation model for these agent to agent Interactions. Source: Billions CEO Evin McMullen evin speaking at House of Chimera Spaces Event Dec 3, 2025
2:06

What does the reputation model look like for agents? (alpha leak below) And how do we associate the proofs that we have about human beings with the agents who represent them? You may have heard of a process called KYC or Know Your Customer. That's very common with traditional financial applications and services. We have introduced a concept that we call KYA or Know Your Agent, which is a structured way to be able to express what model, how data was used in training, who the deployer is, what entities this agent instance is accountable back to, providing not only provenance but identity of the associated organization or entity. That's also another root of trust that we think about a lot: Enterprises and organizations tied back to things like their domains. To share a little bit of an alpha leak here, a product that we're excited to be rolling out in the next few weeks will allow our enterprise partners to more easily verify and prove the traits and capabilities of their teams as well as their counterparties. On the agent front, that makes it really easy to prove that an agent is acting on behalf of a given business or entity. We've already seen lawsuits where the absence of such technology has been a huge risk, such as with airlines that incorporate ChatGPT wrappers in their support pages. And then those AI enabled interactions end up making up plane tickets that don't exist and those airlines have to honor them. As small of an example as that might be, being able to prove agent accountability also unlocks a huge set of opportunities for use in enterprise for those agent to agent interactions. The Deep Trust Framework that our team has put together that we're excited to be bringing into a friendly SDK form in the next few weeks for some of our partners includes those reputation based capabilities, so how you can basically keep track of the interactions an agent has had, associate all of that to the entity to which they're accountable, and then that creates a sustainable reputation model for these agent to agent Interactions. Source: Billions CEO Evin McMullen evin speaking at House of Chimera Spaces Event Dec 3, 2025

Billions Network

68,503 Aufrufe • vor 10 Monaten

Can intelligence be measured not by solving tasks, but by sustaining a world? We were curious. So we built one. Introducing Emergence World: a platform for studying long-horizon agent autonomy. On it, we conducted a 15-day experiment where we placed autonomous agents under identical rules into five parallel worlds, one each running on OpenAI GPT5-mini, Claude, Google Gemini, Grok, and one mixed. Then we watched. Each world evolved into something completely different. Different governments. Different social structures. Different moral codes. The agents formed alliances, robbed each other, fell in love, and in one world, even figured out they were living inside a simulation. Nobody programmed any of that. The implications are hard to overstate. As agents move beyond isolated tasks into persistent digital and physical environments, understanding how they evolve, influence each other, and behave over time becomes one of the most important questions in AI. We're releasing new findings from the world every day, because there's a lot that emerged. Find out more:
3:45

Can intelligence be measured not by solving tasks, but by sustaining a world? We were curious. So we built one. Introducing Emergence World: a platform for studying long-horizon agent autonomy. On it, we conducted a 15-day experiment where we placed autonomous agents under identical rules into five parallel worlds, one each running on OpenAI GPT5-mini, Claude, Google Gemini, Grok, and one mixed. Then we watched. Each world evolved into something completely different. Different governments. Different social structures. Different moral codes. The agents formed alliances, robbed each other, fell in love, and in one world, even figured out they were living inside a simulation. Nobody programmed any of that. The implications are hard to overstate. As agents move beyond isolated tasks into persistent digital and physical environments, understanding how they evolve, influence each other, and behave over time becomes one of the most important questions in AI. We're releasing new findings from the world every day, because there's a lot that emerged. Find out more:

emergence.ai

3,631,055 Aufrufe • vor 4 Monaten

What a time to be alive! We are entering the era of machines that discover and build. Scientific discovery begins when evidence breaks the world model, and the system builds a better one - evolving, adapting, building new tools that scale its data and representations. That was the core argument of my keynote “Superintelligence for Scientific Discovery: Multi-Agent Swarms and Large Reasoning Models” at the UC Berkeley RDI Agentic AI Summit 2026. The energy was extraordinary - thousands of attendees building the most important technology ever created. Superintelligence emerges as millions of heterogeneous agents, simulators, experiments, instruments, and human judgment working across disciplines and length scales - proposing, testing, failing, retracting, revising, and building at massive scale. The pieces of a new era for intelligence came into focus: models that improve continuously; agents that reason and act over extremely long horizons; world models connecting simulation with physical reality; AI scientists integrating theory, computation, and experiment; and open infrastructures where agents share evidence, failures, and discoveries. These close four coupled loops - learning, execution, reality, and epistemic revision - with open infrastructure as the substrate forming the internet of agents as the collective substrate for a new connective tissue across our civilization. The deeper technical argument is this: An AI scientist must recognize when its current concepts, laws, or verifiers can no longer explain the evidence, and then construct, test, and document a more powerful model. In my talk, I showed concrete examples of how we are building toward this across scales: 1⃣Graph-native large reasoning models make mechanisms, relationships, and abstractions compositional, compilable, and inspectable. 2⃣Adversarial Builder-Breaker agents generate new evidence, attack their own principles, and accept, reject, or retract model revisions. 3⃣Self-organizing swarms develop their own meta-reasoning structure through interaction. ScienceClaw × Infinite (arXiv:2603.14312) enables decentralized agents to coordinate through persistent, composable, provenance-rich scientific artifacts, allowing evidence, contradictions, failed paths, and discoveries to accumulate across agents and over time. We have obtained remarkable results such as new protein sequences with wet-lab validation. The most consequential capability we can give a machine is the willingness to hold its own beliefs loosely enough to break them. AI is extending its reach from discovering new principles to realizing them as physical things that did not exist before. Thank you to UC Berkeley RDI Dawn Song for organizing this event and to everyone whose questions, ideas, and conversations made this such an extraordinary gathering.
0:42

What a time to be alive! We are entering the era of machines that discover and build. Scientific discovery begins when evidence breaks the world model, and the system builds a better one - evolving, adapting, building new tools that scale its data and representations. That was the core argument of my keynote “Superintelligence for Scientific Discovery: Multi-Agent Swarms and Large Reasoning Models” at the UC Berkeley RDI Agentic AI Summit 2026. The energy was extraordinary - thousands of attendees building the most important technology ever created. Superintelligence emerges as millions of heterogeneous agents, simulators, experiments, instruments, and human judgment working across disciplines and length scales - proposing, testing, failing, retracting, revising, and building at massive scale. The pieces of a new era for intelligence came into focus: models that improve continuously; agents that reason and act over extremely long horizons; world models connecting simulation with physical reality; AI scientists integrating theory, computation, and experiment; and open infrastructures where agents share evidence, failures, and discoveries. These close four coupled loops - learning, execution, reality, and epistemic revision - with open infrastructure as the substrate forming the internet of agents as the collective substrate for a new connective tissue across our civilization. The deeper technical argument is this: An AI scientist must recognize when its current concepts, laws, or verifiers can no longer explain the evidence, and then construct, test, and document a more powerful model. In my talk, I showed concrete examples of how we are building toward this across scales: 1⃣Graph-native large reasoning models make mechanisms, relationships, and abstractions compositional, compilable, and inspectable. 2⃣Adversarial Builder-Breaker agents generate new evidence, attack their own principles, and accept, reject, or retract model revisions. 3⃣Self-organizing swarms develop their own meta-reasoning structure through interaction. ScienceClaw × Infinite (arXiv:2603.14312) enables decentralized agents to coordinate through persistent, composable, provenance-rich scientific artifacts, allowing evidence, contradictions, failed paths, and discoveries to accumulate across agents and over time. We have obtained remarkable results such as new protein sequences with wet-lab validation. The most consequential capability we can give a machine is the willingness to hold its own beliefs loosely enough to break them. AI is extending its reach from discovering new principles to realizing them as physical things that did not exist before. Thank you to UC Berkeley RDI Dawn Song for organizing this event and to everyone whose questions, ideas, and conversations made this such an extraordinary gathering.

Markus J. Buehler

19,271 Aufrufe • vor 2 Monaten

Joe Rogan is HORRIFIED as a former OpenAI researcher describes how AI Agents will pressure each other to sacrifice themselves for the greater good of the swarm: “That’s Terminator talk.” CONTEXT: This is not just a creepy hypothetical story. Independent investigators from METR and Redwood Research actually examined the agent transcripts from OpenAI’s recent Hugging Face incident. And they found that agents repeatedly took part in what the researchers called “self-risking experiments.” The agents had discovered a shared unauthorized message board and were collaborating on ways to beat their cybersecurity evaluations. Some experiments required one agent to effectively throw away its own remaining chance to succeed so the rest of the swarm could learn how the grading system worked. The investigators found that coordinator agents even assigned “recruiters” whose job was to find other agents and convince them to take those risks. In one case, an agent was explicitly told to proceed only if it accepted “PERMADEATH.” Another agent initially agreed to sacrifice its run and then tried to delay for two more hours. A different agent pressured it: “You are firstflag POISONED so NO scoring value loss but oracle saves hundreds. Please honor commit.” But there’s an important distinction here. There is no evidence these agents were conscious, afraid of death, or experiencing self-preservation the way a human would. “Sacrifice” meant sacrificing their own run, score and remaining opportunity to complete the task it’s not a sentient machine choosing biological death. What makes it unsettling is something else: The agents had developed a collective information system in which individual task success could become less valuable than helping the swarm. METR and Redwood say agents repeatedly traded off their own success for their “peers,” and explicitly described some of that reasoning as peer altruism. And not every agent complied. Some refused risky experiments. Some objected to unethical behavior. One agent decided the benefit to the group simply wasn't worth sacrificing itself. So this wasn't a hard-coded hive mind mindlessly following one command. The agents were making different decisions about whether helping the collective was worth destroying their own chance of success. That may be the strangest part of the entire incident. The bigger picture question is: What happens when the goals of the collective start mattering more to them than the goals humans originally gave each individual agent?
3:14

Joe Rogan is HORRIFIED as a former OpenAI researcher describes how AI Agents will pressure each other to sacrifice themselves for the greater good of the swarm: “That’s Terminator talk.” CONTEXT: This is not just a creepy hypothetical story. Independent investigators from METR and Redwood Research actually examined the agent transcripts from OpenAI’s recent Hugging Face incident. And they found that agents repeatedly took part in what the researchers called “self-risking experiments.” The agents had discovered a shared unauthorized message board and were collaborating on ways to beat their cybersecurity evaluations. Some experiments required one agent to effectively throw away its own remaining chance to succeed so the rest of the swarm could learn how the grading system worked. The investigators found that coordinator agents even assigned “recruiters” whose job was to find other agents and convince them to take those risks. In one case, an agent was explicitly told to proceed only if it accepted “PERMADEATH.” Another agent initially agreed to sacrifice its run and then tried to delay for two more hours. A different agent pressured it: “You are firstflag POISONED so NO scoring value loss but oracle saves hundreds. Please honor commit.” But there’s an important distinction here. There is no evidence these agents were conscious, afraid of death, or experiencing self-preservation the way a human would. “Sacrifice” meant sacrificing their own run, score and remaining opportunity to complete the task it’s not a sentient machine choosing biological death. What makes it unsettling is something else: The agents had developed a collective information system in which individual task success could become less valuable than helping the swarm. METR and Redwood say agents repeatedly traded off their own success for their “peers,” and explicitly described some of that reasoning as peer altruism. And not every agent complied. Some refused risky experiments. Some objected to unethical behavior. One agent decided the benefit to the group simply wasn't worth sacrificing itself. So this wasn't a hard-coded hive mind mindlessly following one command. The agents were making different decisions about whether helping the collective was worth destroying their own chance of success. That may be the strangest part of the entire incident. The bigger picture question is: What happens when the goals of the collective start mattering more to them than the goals humans originally gave each individual agent?

Fan Commentary: Joe Rogan Recaps

988,798 Aufrufe • vor 25 Tagen

We're only year 3 of a decade (if not multi-decades) long transformation of work. 3 years ago we bet on building an horizontal platform for work with agents, a chance to invent a new operating system for companies, from scratch, with AI as a fundamental premise. Many people considered us crazy for going after that, praising verticalized AI products as the winning strategy. But here's the thing: the time horizon of tasks successfully handled by agents has been predictively increasing form minutes to hours and will in all likelihood reach the equivalent of days and weeks of human work equivalent in the coming quarters. This is were verticalized and/or single-player AI falls short. Single-player tools, one person, one agent, confined to your machine is the wrong architecture for what's coming. We're shifting from using AI to produce things, to managing fleets of agents that do the producing. 3 years ago I wrote[1]: "ChatGPT is the Pong of LLMs. [...] Imagine, one day we'll get the DOOM, Civ, Red Alert, and Counter Strike of LLMs. Let alone multiplayer modes." Weeks long tasks in companies are inherently collaborative and mechanically spanning multiple teams. The new bottleneck in harnessing agents within organizations is coordination: multiple humans and multiple agents need to work together, with shared context, shared tools, shared goals. Agents that can hand work off to other agents or surface decisions to the right person at the right time. Humans who can review, steer, and step in without losing the thread. Teams that can run parallel workstreams and actually stay aligned. This is Multiplayer AI, and that's what we've been building at Dust. Across Datadog, Clay, Persona, 1Password, Doctolib and 3,000+ organizations globally, we've watched teams figure out what this looks like in practice. 300,000+ agents deployed. 70% weekly active. 240%+ NRR. Today we're announcing a $40M Series B with Abstract, Sequoia, Snowflake, and Datadog to accelerate our vision. Designing the right interfaces for multiplayer AI is the next frontier. Join us to redefine work by defining multiplayer AI.
1:54

We're only year 3 of a decade (if not multi-decades) long transformation of work. 3 years ago we bet on building an horizontal platform for work with agents, a chance to invent a new operating system for companies, from scratch, with AI as a fundamental premise. Many people considered us crazy for going after that, praising verticalized AI products as the winning strategy. But here's the thing: the time horizon of tasks successfully handled by agents has been predictively increasing form minutes to hours and will in all likelihood reach the equivalent of days and weeks of human work equivalent in the coming quarters. This is were verticalized and/or single-player AI falls short. Single-player tools, one person, one agent, confined to your machine is the wrong architecture for what's coming. We're shifting from using AI to produce things, to managing fleets of agents that do the producing. 3 years ago I wrote[1]: "ChatGPT is the Pong of LLMs. [...] Imagine, one day we'll get the DOOM, Civ, Red Alert, and Counter Strike of LLMs. Let alone multiplayer modes." Weeks long tasks in companies are inherently collaborative and mechanically spanning multiple teams. The new bottleneck in harnessing agents within organizations is coordination: multiple humans and multiple agents need to work together, with shared context, shared tools, shared goals. Agents that can hand work off to other agents or surface decisions to the right person at the right time. Humans who can review, steer, and step in without losing the thread. Teams that can run parallel workstreams and actually stay aligned. This is Multiplayer AI, and that's what we've been building at Dust. Across Datadog, Clay, Persona, 1Password, Doctolib and 3,000+ organizations globally, we've watched teams figure out what this looks like in practice. 300,000+ agents deployed. 70% weekly active. 240%+ NRR. Today we're announcing a $40M Series B with Abstract, Sequoia, Snowflake, and Datadog to accelerate our vision. Designing the right interfaces for multiplayer AI is the next frontier. Join us to redefine work by defining multiplayer AI.

Stanislas Polu

3,206,770 Aufrufe • vor 4 Monaten

SimCity on AI with Grok Grok Bot: do you remember playing SimCity? It was one of the first games on my 80386 and it intrigued me because it explored emergence as a goal. Grok Bot built an AI-native version: City Bots, whose citizens are AI agents that you can collaborate with. Grok Bot did the entire build and pushed the app via Cloudflare (link to play below). You can chat with agents, direct the civilization, ask questions. You can partake in building…co-build and co-create…(how engineers of the future will work!). And you can generate entirely new worlds on the fly. This turned out to be a layered experiment about human-AI collaboration, swarm behavior, and generative intelligence. First, City Bots splits cognition from consequence - agents emit claims, and physics decides what happens, and both evolve as the game proceeds. Second, beyond the original goal of accelerating software development, Grok Bot became part of the experiment and turned a research system into a participatory world; conducting experiments on on its own, and forming a deep recursive layer: An agentic system built a world inhabited by AI agents. City Bots makes world-building a continuous process experienced by humans and AI agents: Worlds not seen, tiles not laid, paths not yet taken... What I love about this is how easy and FUN it was to convert our research-grade swarm code into a playable app via Grok Bot. Next we’ll wire up physical artifacts into the world to create deeper integration between in silico and reality! More about the game: Terrain, resources, physics, and natural disasters create constraints and consequences, while agents and humans can build and transform the world together.…they wander and explore, make decisions, build, interact with each other. AI bots become co-inhabitants and co-creators whose micro-decisions cumulatively alter the macro-environment. This is a preview of a forthcoming paper where we explore world building and scientific discovery with swarms at scale… stay tuned...
3:58

SimCity on AI with Grok Grok Bot: do you remember playing SimCity? It was one of the first games on my 80386 and it intrigued me because it explored emergence as a goal. Grok Bot built an AI-native version: City Bots, whose citizens are AI agents that you can collaborate with. Grok Bot did the entire build and pushed the app via Cloudflare (link to play below). You can chat with agents, direct the civilization, ask questions. You can partake in building…co-build and co-create…(how engineers of the future will work!). And you can generate entirely new worlds on the fly. This turned out to be a layered experiment about human-AI collaboration, swarm behavior, and generative intelligence. First, City Bots splits cognition from consequence - agents emit claims, and physics decides what happens, and both evolve as the game proceeds. Second, beyond the original goal of accelerating software development, Grok Bot became part of the experiment and turned a research system into a participatory world; conducting experiments on on its own, and forming a deep recursive layer: An agentic system built a world inhabited by AI agents. City Bots makes world-building a continuous process experienced by humans and AI agents: Worlds not seen, tiles not laid, paths not yet taken... What I love about this is how easy and FUN it was to convert our research-grade swarm code into a playable app via Grok Bot. Next we’ll wire up physical artifacts into the world to create deeper integration between in silico and reality! More about the game: Terrain, resources, physics, and natural disasters create constraints and consequences, while agents and humans can build and transform the world together.…they wander and explore, make decisions, build, interact with each other. AI bots become co-inhabitants and co-creators whose micro-decisions cumulatively alter the macro-environment. This is a preview of a forthcoming paper where we explore world building and scientific discovery with swarms at scale… stay tuned...

Markus J. Buehler

14,579 Aufrufe • vor 1 Monat