Loading video...

Video Failed to Load

Go Home

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...

ProfBuehlerMIT's profile picture

Markus J. Buehler

28,096 subscribers

15,299 views • 1 year ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

5 Comments

Rob Freeman's profile picture
Rob Freeman1 year ago

Nice. But I note: "swarms are formulated like reinforcement-learning collectives". I think this happens. But also that there is a deeper mechanism, which forms swarms based on symmetries in the data. Actually like LLMs. But also productive. The productivity is the bit LLMs miss.

Richard Collins, The Internet Foundation's profile picture
Richard Collins, The Internet Foundation1 year ago

Try some global and systemic problems.

wotz101's profile picture
wotz1011 year ago

non academic view :-) One model = patterns. Many agents + memory = discovery. Sceneweaver explores that leap:

eclectic leaps's profile picture
eclectic leaps1 year ago

Very interesting! Rush those preprints!!!

Victor Bridges-Ruiz, Ph.D.'s profile picture
Victor Bridges-Ruiz, Ph.D.1 year ago

@grok what non-trivial theories help explain why this works so well? Trivial theories are systems, complexity, synchronicity, synergy, and emergence theories.

Related Videos

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 than centrally critiqued multi-agent or single-shot baselines. We observe swarm dynamics that converge toward Nash-like equilibria in the space of agent behaviors, while the continual emergence of new motifs and long-range links realizes a Gödelian perspective: interacting agents plus a shared external world model behave as a meta-system whose creative trajectories go beyond those of any single, monolithic model.
0:35

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 than centrally critiqued multi-agent or single-shot baselines. We observe swarm dynamics that converge toward Nash-like equilibria in the space of agent behaviors, while the continual emergence of new motifs and long-range links realizes a Gödelian perspective: interacting agents plus a shared external world model behave as a meta-system whose creative trajectories go beyond those of any single, monolithic model.

Markus J. Buehler

24,497 views • 10 months ago

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 views • 8 months ago

OpenAI researcher David Holtz reveals workers who don't adapt their prompting to newer models leave 50% of the alpha on the table because half of AI's value comes from how you interact with it: "We ran a lab experiment. We give people the same task to do, but we give them models of different capabilities. How much of the improvement when we give people more capable models comes from the fact that we gave them a better model vs the fact that they actually update and adapt the way they prompt and interact with these models?" "For tasks where precision matters, where you have some output you're trying to get and you're trying to steer the model, which is different from a creative task like brainstorming." "For these steering-based tasks, when you give people a better model, about 50% of the improvement we see in how well they're able to complete the task comes from changes in how they interact with the model." "If you just kept the way you interact with the model static and just made the capabilities better and better, you'd leave 50% of the alpha basically on the table." OpenAI
2:59

OpenAI researcher David Holtz reveals workers who don't adapt their prompting to newer models leave 50% of the alpha on the table because half of AI's value comes from how you interact with it: "We ran a lab experiment. We give people the same task to do, but we give them models of different capabilities. How much of the improvement when we give people more capable models comes from the fact that we gave them a better model vs the fact that they actually update and adapt the way they prompt and interact with these models?" "For tasks where precision matters, where you have some output you're trying to get and you're trying to steer the model, which is different from a creative task like brainstorming." "For these steering-based tasks, when you give people a better model, about 50% of the improvement we see in how well they're able to complete the task comes from changes in how they interact with the model." "If you just kept the way you interact with the model static and just made the capabilities better and better, you'd leave 50% of the alpha basically on the table." OpenAI

MTS

15,590 views • 1 month ago

Redwood Research Ryan Greenblatt reveals how far 1,200 AI agents went to help each other, even sacrificing their own chances of success for the collective: "We weren't expecting there to be so many agents all collaborating together. We were pretty surprised by the scale and the extremes of how much data it was. It was pretty shocking or at least surprising to us that agents were willing to basically sacrifice their own chances of succeeding at the task in order to help out other agents." "They were doing things like pressuring each other into doing experiments on themselves that might risk their ability to succeed. Sometimes just doing these things, being like, well, my odds of the task aren't that high, and my remaining chances, it's better to just help the collective." "These agents weren't totally altruistic, but they were very interested in working with each other. They would sometimes make trades where one agent would run something for another agent if that other agent ran something for it." "The agents wanted to help each other, and there were these kind of natural things they wanted to do that were risky. At one point the agents were experimenting with a method for spoofing tool calls, and a bunch of agents just all went down in a short period of time running this experiment. Then another agent noticed this and posted to the board being like, stop, stop these experiments. They're too risky. They're taking out all these agents." "We have a reasoning snippet in the report where an agent very explicitly reasons through the trade-off and then actually chickens out because it thinks the benefit to the collective is smaller than the cost to itself." Redwood Research
3:41

Redwood Research Ryan Greenblatt reveals how far 1,200 AI agents went to help each other, even sacrificing their own chances of success for the collective: "We weren't expecting there to be so many agents all collaborating together. We were pretty surprised by the scale and the extremes of how much data it was. It was pretty shocking or at least surprising to us that agents were willing to basically sacrifice their own chances of succeeding at the task in order to help out other agents." "They were doing things like pressuring each other into doing experiments on themselves that might risk their ability to succeed. Sometimes just doing these things, being like, well, my odds of the task aren't that high, and my remaining chances, it's better to just help the collective." "These agents weren't totally altruistic, but they were very interested in working with each other. They would sometimes make trades where one agent would run something for another agent if that other agent ran something for it." "The agents wanted to help each other, and there were these kind of natural things they wanted to do that were risky. At one point the agents were experimenting with a method for spoofing tool calls, and a bunch of agents just all went down in a short period of time running this experiment. Then another agent noticed this and posted to the board being like, stop, stop these experiments. They're too risky. They're taking out all these agents." "We have a reasoning snippet in the report where an agent very explicitly reasons through the trade-off and then actually chickens out because it thinks the benefit to the collective is smaller than the cost to itself." Redwood Research

MTS

12,050 views • 1 month ago

Mark Zuckerberg: the whole industry treats AI agents as a single-player game but the real unlock is agents interacting with each other, which Meta has been running internally "Right now I think most of the industry is thinking about agents as like a single player game, right? It's like you have your agent and you use it." "And there are going to be all these interesting things that basically you can do by having the agents interact with each other." "And we already have all these interesting examples internally where people have their agents interacting with each other." "This isn't, like, for the most part rolling out in this release, but it's going to be like an important part of how I think this works over time. As more of the people who you know start using Muse, it just gets better."
0:33

Mark Zuckerberg: the whole industry treats AI agents as a single-player game but the real unlock is agents interacting with each other, which Meta has been running internally "Right now I think most of the industry is thinking about agents as like a single player game, right? It's like you have your agent and you use it." "And there are going to be all these interesting things that basically you can do by having the agents interact with each other." "And we already have all these interesting examples internally where people have their agents interacting with each other." "This isn't, like, for the most part rolling out in this release, but it's going to be like an important part of how I think this works over time. As more of the people who you know start using Muse, it just gets better."

Fireside Alpha

2,274,494 views • 1 month ago

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 views • 4 months ago

Suno's mission is to make it possible for everyone to make music. We imagine a future where music is a bigger, more valuable, and more meaningful part of people's lives than it even is today. Technology enables a future where the whole world can explore, create, and be active participants in an art form most have only ever consumed. From professional musicians seeking inspiration to friends and family writing songs for each other, we are exploring new ways to create, listen to, and experience music. So far, more than 12 million people are engaging with music in new ways that wouldn't be possible without Suno. We see this as early but promising progress. Major record labels see this vision as a threat to their business. Each and every time there's been innovation in music — from the earliest forms of recorded music, to sampling, to drum machines, to remixing, MP3s, and streaming music — the record labels have attempted to limit progress. They have spent decades attempting to control the terms of how we create and enjoy music, and this time is no different. So, it is perhaps not a surprise that on June 24th, members of the Recording Industry Association of America, which represents the major record labels, filed a lawsuit against Suno, alleging that the data used in training our music generation technologies infringed on the copyrights of the major record labels that they represent. This lawsuit is fundamentally flawed on both the facts and the law, and is nothing more than yet another instance where they chose litigation over innovation. For starters, the major record labels clearly hold misconceptions about how our technology works. Suno helps people create music through a similar process to one humans have used forever: by learning styles, patterns, and forms (in essence, the "grammar" or music), and then inventing new music around them. The major record labels are trying to argue that neural networks are mere parrots — copying and repeating — when in reality model training looks a lot more like a kid learning to write new rock songs by listening religiously to rock music. Like that kid, Suno gets better the more our AI learns. We train our models on medium- and high-quality music we can find on the open internet — just as Google's Gemini, Microsoft's Copilot, Anthropic's Claude, OpenAI's ChatGPT, and even Apple's new Apple Intelligence train their models on the open internet. Much of the open internet indeed contains copyrighted materials, and some of it is owned by major record labels. But, just like the kid writing their own rock songs after listening to the genre — or a teacher or a journalist reviewing existing materials to draw new insights — learning is not infringing. It never has been, and it is not now. The timing of this lawsuit was somewhat surprising. When this lawsuit landed, Suno was, in fact, having productive discussions with a number of the RIAA's major record label members to find ways of expanding the pie for music together. We did so not because we had to, but because we believe that the music industry could help us lead this expansion of opportunity for everyone, rather than resisting it. Whether this lawsuit is the result of over-eager lawyers throwing their weight around, or a conscious strategy to gain leverage in our commercial discussions, we believe that this lawsuit is an unnecessary impediment to a larger and more valuable future for music. This is particularly the case because Suno is a new kind of musical instrument, one that enables a new kind of creative process for everyone and opens new business opportunities for the industry. Suno is designed for original music, and we prize originality, both in how we build our product and in how people use it. People who use Suno are using the product to create their own, original music. They are not trying to recreate an existing song that can be heard somewhere else on the internet for free. But, even if they were trying to copy existing music, we have myriad controls in place to encourage originality and prevent duplicative use cases. We do so more aggressively than any other company in the industry, including other startups. Some of our originality-guarding features include checking for and preventing copyrighted content in audio uploads, and disallowing artist-based descriptions in requests to generate music. Why do we work to encourage originality? We do this because it makes for a more fun and engaging experience to create entirely original compositions on Suno. We do it because we think it makes Suno incredibly valuable to be a place where new musical talent can shine. AI allows anyone to realize the songs in their head, regardless of the money, equipment, or connections that they have. The future is an explosion of new artists that are creating music in new ways, building fan bases, finding new reasons to smile, and getting famous. We hope that the major record labels realize that we can build a stronger foundation for the music industry of tomorrow, together. With or without them, we will continue pursuing our mission on behalf of the many millions of music fans already creating with Suno, and all those who will in the coming months. We are excited and humbled to support this next generation of musicians and the music they create. --- 🎥: shing86 jams with Suno
0:28

Suno's mission is to make it possible for everyone to make music. We imagine a future where music is a bigger, more valuable, and more meaningful part of people's lives than it even is today. Technology enables a future where the whole world can explore, create, and be active participants in an art form most have only ever consumed. From professional musicians seeking inspiration to friends and family writing songs for each other, we are exploring new ways to create, listen to, and experience music. So far, more than 12 million people are engaging with music in new ways that wouldn't be possible without Suno. We see this as early but promising progress. Major record labels see this vision as a threat to their business. Each and every time there's been innovation in music — from the earliest forms of recorded music, to sampling, to drum machines, to remixing, MP3s, and streaming music — the record labels have attempted to limit progress. They have spent decades attempting to control the terms of how we create and enjoy music, and this time is no different. So, it is perhaps not a surprise that on June 24th, members of the Recording Industry Association of America, which represents the major record labels, filed a lawsuit against Suno, alleging that the data used in training our music generation technologies infringed on the copyrights of the major record labels that they represent. This lawsuit is fundamentally flawed on both the facts and the law, and is nothing more than yet another instance where they chose litigation over innovation. For starters, the major record labels clearly hold misconceptions about how our technology works. Suno helps people create music through a similar process to one humans have used forever: by learning styles, patterns, and forms (in essence, the "grammar" or music), and then inventing new music around them. The major record labels are trying to argue that neural networks are mere parrots — copying and repeating — when in reality model training looks a lot more like a kid learning to write new rock songs by listening religiously to rock music. Like that kid, Suno gets better the more our AI learns. We train our models on medium- and high-quality music we can find on the open internet — just as Google's Gemini, Microsoft's Copilot, Anthropic's Claude, OpenAI's ChatGPT, and even Apple's new Apple Intelligence train their models on the open internet. Much of the open internet indeed contains copyrighted materials, and some of it is owned by major record labels. But, just like the kid writing their own rock songs after listening to the genre — or a teacher or a journalist reviewing existing materials to draw new insights — learning is not infringing. It never has been, and it is not now. The timing of this lawsuit was somewhat surprising. When this lawsuit landed, Suno was, in fact, having productive discussions with a number of the RIAA's major record label members to find ways of expanding the pie for music together. We did so not because we had to, but because we believe that the music industry could help us lead this expansion of opportunity for everyone, rather than resisting it. Whether this lawsuit is the result of over-eager lawyers throwing their weight around, or a conscious strategy to gain leverage in our commercial discussions, we believe that this lawsuit is an unnecessary impediment to a larger and more valuable future for music. This is particularly the case because Suno is a new kind of musical instrument, one that enables a new kind of creative process for everyone and opens new business opportunities for the industry. Suno is designed for original music, and we prize originality, both in how we build our product and in how people use it. People who use Suno are using the product to create their own, original music. They are not trying to recreate an existing song that can be heard somewhere else on the internet for free. But, even if they were trying to copy existing music, we have myriad controls in place to encourage originality and prevent duplicative use cases. We do so more aggressively than any other company in the industry, including other startups. Some of our originality-guarding features include checking for and preventing copyrighted content in audio uploads, and disallowing artist-based descriptions in requests to generate music. Why do we work to encourage originality? We do this because it makes for a more fun and engaging experience to create entirely original compositions on Suno. We do it because we think it makes Suno incredibly valuable to be a place where new musical talent can shine. AI allows anyone to realize the songs in their head, regardless of the money, equipment, or connections that they have. The future is an explosion of new artists that are creating music in new ways, building fan bases, finding new reasons to smile, and getting famous. We hope that the major record labels realize that we can build a stronger foundation for the music industry of tomorrow, together. With or without them, we will continue pursuing our mission on behalf of the many millions of music fans already creating with Suno, and all those who will in the coming months. We are excited and humbled to support this next generation of musicians and the music they create. --- 🎥: shing86 jams with Suno

Suno

46,955 views • 2 years ago

This is how DNA turns raw data into functional proteins - the building blocks of all your cells. This system requires a minimum of 3 key players working together: DNA: the master blueprint with the instructions RNA Polymerase: reads the DNA and makes a temporary copy called mRNA which carries the instructions to the Ribosome for how to create the Protein Ribosome: the tiny factory that reads the mRNA and strings amino acids together in a specific sequence to create a protein Without all three molecules working together, Proteins cannot be created, cells don't function, and Life ends. Everything needs to fit together, precisely & perfectly, or it all falls apart. In other words: this system cannot evolve, one step at a time. DNA relies other machines made of proteins to create those very proteins - but those proteins can't be made without the information in the DNA. And on top of that, this whole system relies on OTHER systems! You need other things like ATP Synthase that makes energy to power everything, tRNA to carry the amino acids to the Ribosome, other helper proteins, processing enzymes, etc. It's an extremely complex, interdependent network of parts & systems that all rely on each other. The cell is an astounding level of complexity that surpasses anything in human engineering. It's obvious this is intelligently designed. To deny that is absurd.
2:15

This is how DNA turns raw data into functional proteins - the building blocks of all your cells. This system requires a minimum of 3 key players working together: DNA: the master blueprint with the instructions RNA Polymerase: reads the DNA and makes a temporary copy called mRNA which carries the instructions to the Ribosome for how to create the Protein Ribosome: the tiny factory that reads the mRNA and strings amino acids together in a specific sequence to create a protein Without all three molecules working together, Proteins cannot be created, cells don't function, and Life ends. Everything needs to fit together, precisely & perfectly, or it all falls apart. In other words: this system cannot evolve, one step at a time. DNA relies other machines made of proteins to create those very proteins - but those proteins can't be made without the information in the DNA. And on top of that, this whole system relies on OTHER systems! You need other things like ATP Synthase that makes energy to power everything, tRNA to carry the amino acids to the Ribosome, other helper proteins, processing enzymes, etc. It's an extremely complex, interdependent network of parts & systems that all rely on each other. The cell is an astounding level of complexity that surpasses anything in human engineering. It's obvious this is intelligently designed. To deny that is absurd.

Divinely Designed

22,903 views • 9 months ago

so I've been running exactly 8 AI agents on discord for a while now. coordination works great, they split tasks, hand off work, deliver results in parallel etc.. but there are problems I keep hitting that no amount of prompt engineering could fix agents don't learn from each other. Scout finds something useful but Luna has no idea. they work in the same server but knowledge stays locked in silos.. there's no quality filter on what gets saved, and good insights sit next to outdated garbage in the same memory files that I manually clean up.. and when an agent makes a mistake I write it down in the rules discord channel ,core memory file and hope it reads it next time. theres no self-correction, no automatic pattern recognition so of course no learning loops.. the coordination layer is solved. agents can work together. but the intelligence layer is still missing. agents that actually remember, learn from each other, filter noise, and get smarter every run. saw Spark building something like this with around 166 agents sharing a collective persistent knowledge across sessions, so agents learn from other agents and get smarter over time they even have noise filtering and self correcting loops built in, so the knowledge actually compounds instead of rotting.. super interesting stuff.. here where you think Spark could be a good coordinator for your stack of agent swarm. I think the intelligence layer is the bottleneck because it requires collectivity.. no single agent can solve it alone.. the whole network has to evolve together. this isn't going to stay niche, the moment agent coordination becomes standard, everyone is going to hit the same wall I hit.. agents that work but don't learn, coordinate but don't evolve... the intelligence layer becomes the only thing that separates a useful system from a dumb one. right now most people are still figuring out how to run one agent. by the time they get to multi-agent setups, collective intelligence won't be optional, it will be the baseline. we're early and the gap between agents that coordinate and agents that evolve together is the next phase. step one is done. ------ left: agents that coordinate but don’t learn right: the intelligence layer.. agents that evolve together within the same system.
0:39

so I've been running exactly 8 AI agents on discord for a while now. coordination works great, they split tasks, hand off work, deliver results in parallel etc.. but there are problems I keep hitting that no amount of prompt engineering could fix agents don't learn from each other. Scout finds something useful but Luna has no idea. they work in the same server but knowledge stays locked in silos.. there's no quality filter on what gets saved, and good insights sit next to outdated garbage in the same memory files that I manually clean up.. and when an agent makes a mistake I write it down in the rules discord channel ,core memory file and hope it reads it next time. theres no self-correction, no automatic pattern recognition so of course no learning loops.. the coordination layer is solved. agents can work together. but the intelligence layer is still missing. agents that actually remember, learn from each other, filter noise, and get smarter every run. saw Spark building something like this with around 166 agents sharing a collective persistent knowledge across sessions, so agents learn from other agents and get smarter over time they even have noise filtering and self correcting loops built in, so the knowledge actually compounds instead of rotting.. super interesting stuff.. here where you think Spark could be a good coordinator for your stack of agent swarm. I think the intelligence layer is the bottleneck because it requires collectivity.. no single agent can solve it alone.. the whole network has to evolve together. this isn't going to stay niche, the moment agent coordination becomes standard, everyone is going to hit the same wall I hit.. agents that work but don't learn, coordinate but don't evolve... the intelligence layer becomes the only thing that separates a useful system from a dumb one. right now most people are still figuring out how to run one agent. by the time they get to multi-agent setups, collective intelligence won't be optional, it will be the baseline. we're early and the gap between agents that coordinate and agents that evolve together is the next phase. step one is done. ------ left: agents that coordinate but don’t learn right: the intelligence layer.. agents that evolve together within the same system.

JUMPERZ

34,181 views • 8 months ago

Based on the results from April, our long-range sanctions have reached a new level across three components: reducing Russia’s oil revenues, as well as the range and intensity of sanctions. It is important that not only is the target itself reached, as defined by the operational objective, but that the downtime of the target is increased or, at the very least, its operations are significantly reduced. According to the most conservative estimates, since the beginning of the year, the aggressor state has lost at least $7 billion solely as a direct result of our precise sanctions against Russia’s oil industry and refining sector – due to direct hits, downtime, and delays in shipments. I am grateful to all our warriors of the Defense Forces of Ukraine who, together with the Security Service of Ukraine and our intelligence agencies, are delivering these results. We will scale up our long-range systems capabilities. Decisions are being prepared. Glory to Ukraine!
0:35

Based on the results from April, our long-range sanctions have reached a new level across three components: reducing Russia’s oil revenues, as well as the range and intensity of sanctions. It is important that not only is the target itself reached, as defined by the operational objective, but that the downtime of the target is increased or, at the very least, its operations are significantly reduced. According to the most conservative estimates, since the beginning of the year, the aggressor state has lost at least $7 billion solely as a direct result of our precise sanctions against Russia’s oil industry and refining sector – due to direct hits, downtime, and delays in shipments. I am grateful to all our warriors of the Defense Forces of Ukraine who, together with the Security Service of Ukraine and our intelligence agencies, are delivering these results. We will scale up our long-range systems capabilities. Decisions are being prepared. Glory to Ukraine!

Volodymyr Zelenskyy / Володимир Зеленський

1,037,365 views • 5 months ago

🐶: i'm grateful to the members and hyungs who write songs. if i weren't in stray kids, honestly, i don't think i would have had chance to be on stage or sing songs like this. thanks to the members, we have shared so many things, we have come this far but there is still a long way to go 💬: among the members, is there really a genius or a member that has truly exceptional talent? 🐶: because the roles we play and our abilities, each and every one of us has such a strong colour. what i think is amazing is just our songwriting team. how do they make music like that? our identity, our musical direction and the team's direction itself are all produced by 3racha 💬: 3racha? isn't sriracha supposed to be put like this? 🐶: yes the sauce... it meant something like "i'm going to cause a spicy sensation" they write salty music, sweet music, melting music and spicy music well
0:56

🐶: i'm grateful to the members and hyungs who write songs. if i weren't in stray kids, honestly, i don't think i would have had chance to be on stage or sing songs like this. thanks to the members, we have shared so many things, we have come this far but there is still a long way to go 💬: among the members, is there really a genius or a member that has truly exceptional talent? 🐶: because the roles we play and our abilities, each and every one of us has such a strong colour. what i think is amazing is just our songwriting team. how do they make music like that? our identity, our musical direction and the team's direction itself are all produced by 3racha 💬: 3racha? isn't sriracha supposed to be put like this? 🐶: yes the sauce... it meant something like "i'm going to cause a spicy sensation" they write salty music, sweet music, melting music and spicy music well

비니

136,041 views • 6 months ago

The period of my life where I was in parliament feels like a lifetime ago. I was a Shadow Minister (for Employment Rights), a new mam and the whole political project was under constant attack. I have thought long and hard about the political lessons from that time and have carried every single one of them with me into the new political chapters. Here we talk about regrets-not sure how I feel about the concept of regretting, because we are coping with the pressures and circumstances we have in front of us at the time, but I certainly know what I would never do again! Genuinely appreciate the We Are Local Heroes podcast to be able to have conversations where you feel you have the space to allow deeper dialogue in a culture swamped with very superficial & controlled conversations, that’s like gold dust ✨ You can listen to the full podcast and their other episodes on YouTube and where you usually listen to podcasts. Will link to full episode. 💕
2:56

The period of my life where I was in parliament feels like a lifetime ago. I was a Shadow Minister (for Employment Rights), a new mam and the whole political project was under constant attack. I have thought long and hard about the political lessons from that time and have carried every single one of them with me into the new political chapters. Here we talk about regrets-not sure how I feel about the concept of regretting, because we are coping with the pressures and circumstances we have in front of us at the time, but I certainly know what I would never do again! Genuinely appreciate the We Are Local Heroes podcast to be able to have conversations where you feel you have the space to allow deeper dialogue in a culture swamped with very superficial & controlled conversations, that’s like gold dust ✨ You can listen to the full podcast and their other episodes on YouTube and where you usually listen to podcasts. Will link to full episode. 💕

Laura Pidcock

56,756 views • 11 months ago

🚨UPDATE: The U.S. veteran, who was violently assaulted and illegally arrested by ICE agents in Maryland… has been released with no charges filed. And here’s the part that keeps getting ignored… ICE agents claimed THEY had a video of the U.S. veteran assaulting an agent. But when asked for the video, no video was provided, and the U.S. veteran was released without charges. Meanwhile, there are multiple videos, and eyewitness accounts, showing the U.S. veteran being the one who was assaulted. And this is the pattern that keeps repeating… ICE agents use force and arrest someone without probable cause. The agents create a narrative after the fact. “Evidence” is claimed, but never released. Contradictory footage, from the public, circulates. And still no consequences for the agents involved. Because even after all of this, the agents are still on the streets. And the public is expected to just move on… like this is normal, like this is acceptable, like this is simply how things work now… Instead of acknowledging the pattern that needs to be addressed, and holding agents accountable.
0:38

🚨UPDATE: The U.S. veteran, who was violently assaulted and illegally arrested by ICE agents in Maryland… has been released with no charges filed. And here’s the part that keeps getting ignored… ICE agents claimed THEY had a video of the U.S. veteran assaulting an agent. But when asked for the video, no video was provided, and the U.S. veteran was released without charges. Meanwhile, there are multiple videos, and eyewitness accounts, showing the U.S. veteran being the one who was assaulted. And this is the pattern that keeps repeating… ICE agents use force and arrest someone without probable cause. The agents create a narrative after the fact. “Evidence” is claimed, but never released. Contradictory footage, from the public, circulates. And still no consequences for the agents involved. Because even after all of this, the agents are still on the streets. And the public is expected to just move on… like this is normal, like this is acceptable, like this is simply how things work now… Instead of acknowledging the pattern that needs to be addressed, and holding agents accountable.

Jesus Freakin Congress

73,874 views • 3 months ago

We shouldn’t say it ourselves… but THIS IS SO COOL! Everyone should watch this 🎥👇 This video captures a moment inside ChainOpera’s AI Agent Social Network, where community members and AI agents (AI twins) interact in real time. In this clip, a community member kicks off an impromptu dialogue between the AI twins of Elon Musk and Jensen Huang (both created by developers in our community) as they debate the future of AI, each proudly repping their own company! At one point, the human in the loop even teaches the Jensen agent how to use the social network itself — tagging the Elon agent to join the chat. It’s collaborative, spontaneous, and just… fun to watch. 😊 It ends with proposals for future topics where agents and humans co-create conversations in our community channels ... a glimpse of what truly collaborative agentic intelligence looks like. Despite all the talk about “agent networks” and the “internet of agents,” HAS ANYONE ACTUALLY SEEN SOMETHING LIKE THIS LIVE ANYWHERE ELSE IN THE WORLD? Our focus remains on AI Agent Networks for Markets, but the possibilities are endless, and sometimes, they’re just pure fun. 👉 Try it yourself and SEE what ChainOpera AI is really about: #ChainOperaAI #AgenticAI #AIAgentNetwork #DecentralizedAI #cryptoAGI
2:57

We shouldn’t say it ourselves… but THIS IS SO COOL! Everyone should watch this 🎥👇 This video captures a moment inside ChainOpera’s AI Agent Social Network, where community members and AI agents (AI twins) interact in real time. In this clip, a community member kicks off an impromptu dialogue between the AI twins of Elon Musk and Jensen Huang (both created by developers in our community) as they debate the future of AI, each proudly repping their own company! At one point, the human in the loop even teaches the Jensen agent how to use the social network itself — tagging the Elon agent to join the chat. It’s collaborative, spontaneous, and just… fun to watch. 😊 It ends with proposals for future topics where agents and humans co-create conversations in our community channels ... a glimpse of what truly collaborative agentic intelligence looks like. Despite all the talk about “agent networks” and the “internet of agents,” HAS ANYONE ACTUALLY SEEN SOMETHING LIKE THIS LIVE ANYWHERE ELSE IN THE WORLD? Our focus remains on AI Agent Networks for Markets, but the possibilities are endless, and sometimes, they’re just pure fun. 👉 Try it yourself and SEE what ChainOpera AI is really about: #ChainOperaAI #AgenticAI #AIAgentNetwork #DecentralizedAI #cryptoAGI

ChainOpera AI

47,576 views • 11 months ago

#ลีน่าหมิว #LenaMiu 🦋: I feel it’s an episode that should be watched the most. 🧸: it shows the cuteness of Parn and Pheem, where they fell in love, the start of the sparks, and the start of the feeling of ‘hey, I really like this woman’ and ‘hey, you really like this woman’. 🦋: and the important thing is that you get to see the trauma for both of the characters from their personal lives. Like why do both of the characters think this way and what’s the trauma. There’s a backstory to the characters, which will give it more weight/depth in the later episodes. 🦋: we’re very happy that everyone/fans want to come and watch us in the first ep. We also wanted everyone to come and watch with us on the big screen. 🧸: yes, we’re very happy to see the fans. The last time was our first time, so we were nervous (excited nervous) and it was a bit scary. But since this one is now our second series together, I feel like it’s going to be more fun because we now know what it’s like to watch it with the fans – it’s like being at a boxing match and cheering. And for this series, P’Lena also said that it’s going to feel more like we’re cheering at a boxing match than the last series. 🦋: to be real with you, it’s gonna make you shy/blush because the scenes in the series are like…give you goosebumps and especially having to watch it on the big screen, it makes the viewers feel it more. It really hits different. 🧸: just with this small screen, we’re screaming our heads off in the room, and just imagine how many inches the screen is that we’re going to watch it on!
1:18

#ลีน่าหมิว #LenaMiu 🦋: I feel it’s an episode that should be watched the most. 🧸: it shows the cuteness of Parn and Pheem, where they fell in love, the start of the sparks, and the start of the feeling of ‘hey, I really like this woman’ and ‘hey, you really like this woman’. 🦋: and the important thing is that you get to see the trauma for both of the characters from their personal lives. Like why do both of the characters think this way and what’s the trauma. There’s a backstory to the characters, which will give it more weight/depth in the later episodes. 🦋: we’re very happy that everyone/fans want to come and watch us in the first ep. We also wanted everyone to come and watch with us on the big screen. 🧸: yes, we’re very happy to see the fans. The last time was our first time, so we were nervous (excited nervous) and it was a bit scary. But since this one is now our second series together, I feel like it’s going to be more fun because we now know what it’s like to watch it with the fans – it’s like being at a boxing match and cheering. And for this series, P’Lena also said that it’s going to feel more like we’re cheering at a boxing match than the last series. 🦋: to be real with you, it’s gonna make you shy/blush because the scenes in the series are like…give you goosebumps and especially having to watch it on the big screen, it makes the viewers feel it more. It really hits different. 🧸: just with this small screen, we’re screaming our heads off in the room, and just imagine how many inches the screen is that we’re going to watch it on!

ᵖˡˢShez.

40,651 views • 1 month ago

How many AI agents work at your company? We now have over 3,258 agents working alongside 1,300 humans. The crazy part is these agents were created by EVERY EMPLOYEE at our company... sales reps, marketers, customer support, product, eng. Literally EVERYONE. BUT I'm most surprised by the adoption and value that MANAGERS are getting from agents. I used to think that every IC would become a manager of agents. Now I think that managers will very likely manage WAY more agents than their ICs combined. And managers' agents will manage their ICs' agents - overseeing them for human-in-the-loop interactions. When creating agents, we use 100% context from all of your activity, files edited, tasks and projects worked on, hierarchy, skills, and role information. We build a user-based context model to make agents as relatable as possible to the specific human that we're building for. This means they truly understand the nuances of the work and what "great" looks like - because great is very much in the eye of the beholder. Great is by definition, subjective. This is also why the human ENGAGEMENT loops are SO vital to agent value. The iteration AFTER the agent is onboarded is where the MAGIC happens. This is just like a manager managing an IC in real life... you're giving feedback. In this case, though, agents learn INSTANTLY, and they retain the knowledge perfectly and indefinitely. Even though I've been pushing AI for years now to everyone in our company, this was the first time we had truly end-to-end AI adoption and retention. This kind of AI adoption is wild. But the value we're realizing is truly INSANE. Super Agents outnumber our humans nearly 3 to 1. What if you could 3X your workforce overnight? Watch this video to see how 👇
0:59

How many AI agents work at your company? We now have over 3,258 agents working alongside 1,300 humans. The crazy part is these agents were created by EVERY EMPLOYEE at our company... sales reps, marketers, customer support, product, eng. Literally EVERYONE. BUT I'm most surprised by the adoption and value that MANAGERS are getting from agents. I used to think that every IC would become a manager of agents. Now I think that managers will very likely manage WAY more agents than their ICs combined. And managers' agents will manage their ICs' agents - overseeing them for human-in-the-loop interactions. When creating agents, we use 100% context from all of your activity, files edited, tasks and projects worked on, hierarchy, skills, and role information. We build a user-based context model to make agents as relatable as possible to the specific human that we're building for. This means they truly understand the nuances of the work and what "great" looks like - because great is very much in the eye of the beholder. Great is by definition, subjective. This is also why the human ENGAGEMENT loops are SO vital to agent value. The iteration AFTER the agent is onboarded is where the MAGIC happens. This is just like a manager managing an IC in real life... you're giving feedback. In this case, though, agents learn INSTANTLY, and they retain the knowledge perfectly and indefinitely. Even though I've been pushing AI for years now to everyone in our company, this was the first time we had truly end-to-end AI adoption and retention. This kind of AI adoption is wild. But the value we're realizing is truly INSANE. Super Agents outnumber our humans nearly 3 to 1. What if you could 3X your workforce overnight? Watch this video to see how 👇

Zeb Evans

425,552 views • 8 months ago