正在加载视频...

视频加载失败

返回首页

"The bottleneck for an agent's usefulness today is not intelligence. It's trust." At DevCon 6, Palantir Group Lead John Mathews launches Orchestrator, the durable execution layer that lets agents crash, recover, wait, and resume exactly where they left off. Watch a patient discharge agent get torn down mid-task and...

PalantirTech's profile picture

Palantir

436,293 subscribers

55,287 次观看 • 2 天前 •via X (Twitter)

科学技术教育健康养生
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

"By stitching these three primitives together, you get an agent loop that's actually a distributed state machine under the hood." At DevCon 6, Palantir Group Lead Natasha Armbrust launches Agent Engine and Agent SDK, giving developers the core primitives to build agents that form a distributed state machine and are multiplayer by design. ▪️Context items for defining agent sessions through strongly typed data ▪️ Events for expressively acting on changes in state ▪️Effects for connecting agents to the outside world
1:46

"By stitching these three primitives together, you get an agent loop that's actually a distributed state machine under the hood." At DevCon 6, Palantir Group Lead Natasha Armbrust launches Agent Engine and Agent SDK, giving developers the core primitives to build agents that form a distributed state machine and are multiplayer by design. ▪️Context items for defining agent sessions through strongly typed data ▪️ Events for expressively acting on changes in state ▪️Effects for connecting agents to the outside world

Palantir

67,547 次观看 • 3 天前

“I'd be really careful about any movement that has ‘zero’ in it. I just hear the ‘zero’ now and I shiver. We had zero-COVID, net zero, and it just puts in my mind to be honest Pol Pot’s Year Zero. Be aware of the zero. What is zero? It is nothing. It's a big gaping hole. it's an eternal nothingness. It's a moral flatlining. Never aim for a zero. I don't think that there's anything necessarily deliberate about this. I don't think that the people that aimed for zero-COVID and the people that aim for net zero have got some kind of dastardly zero plan going on. It's more that it's symbolic of something quite nihilistic. Both zero-COVID and net zero were about a constriction of humans to a nothingness. To achieve zero-COVID, you had to be cut off from the world - a hermit kingdom. Never leave your house. Never see your face. There was something so miserly and anti-human about it. And it's the same as net zero involves rewinding to a kind of a pre-industrial area where we live in mud huts, and we don't have anything we can't have heating, you know, the things that have saved us, you know, good diets, heating, lots of farming, they don't want that they want us to rewind and live like serfs. They're such unpleasant, miserly visions for the world. So. I don't think there's anything deliberate. I just think the symbolism comes through, because it's people that have this really miserly view of humanity.” - Laura Dodsworth
9:51

“I'd be really careful about any movement that has ‘zero’ in it. I just hear the ‘zero’ now and I shiver. We had zero-COVID, net zero, and it just puts in my mind to be honest Pol Pot’s Year Zero. Be aware of the zero. What is zero? It is nothing. It's a big gaping hole. it's an eternal nothingness. It's a moral flatlining. Never aim for a zero. I don't think that there's anything necessarily deliberate about this. I don't think that the people that aimed for zero-COVID and the people that aim for net zero have got some kind of dastardly zero plan going on. It's more that it's symbolic of something quite nihilistic. Both zero-COVID and net zero were about a constriction of humans to a nothingness. To achieve zero-COVID, you had to be cut off from the world - a hermit kingdom. Never leave your house. Never see your face. There was something so miserly and anti-human about it. And it's the same as net zero involves rewinding to a kind of a pre-industrial area where we live in mud huts, and we don't have anything we can't have heating, you know, the things that have saved us, you know, good diets, heating, lots of farming, they don't want that they want us to rewind and live like serfs. They're such unpleasant, miserly visions for the world. So. I don't think there's anything deliberate. I just think the symbolism comes through, because it's people that have this really miserly view of humanity.” - Laura Dodsworth

Jan Jekielek

167,801 次观看 • 2 年前

PillPack founder TJ Parker⚡️ says Hims' Wegovy pill alternative is a “$50 drug that doesn't work” and a “financial Hail Mary.” "The Wegovy pill has a specific technology called 'SNAC' to allow you to absorb the peptide and have the drug be effective. Hims explicitly said they didn't use that technology and said they're using liposomal absorption, which maybe works, maybe doesn't, but there's certainly no proof that it works." "There are zero studies and zero approval. This is where it's super different from the injectables, where they weren't changing the formulation. It was very similar to the branded drug." "[The pill] is different in the sense that, here, there's no evidence this drug works at all. So the most likely scenario is they're selling a $50 drug that doesn't work that still has a bunch of side effects because it still has the drug that doesn't get absorbed through your G.I." "It's not an IP issue, it's really an efficacy and safety issue."
4:08

PillPack founder TJ Parker⚡️ says Hims' Wegovy pill alternative is a “$50 drug that doesn't work” and a “financial Hail Mary.” "The Wegovy pill has a specific technology called 'SNAC' to allow you to absorb the peptide and have the drug be effective. Hims explicitly said they didn't use that technology and said they're using liposomal absorption, which maybe works, maybe doesn't, but there's certainly no proof that it works." "There are zero studies and zero approval. This is where it's super different from the injectables, where they weren't changing the formulation. It was very similar to the branded drug." "[The pill] is different in the sense that, here, there's no evidence this drug works at all. So the most likely scenario is they're selling a $50 drug that doesn't work that still has a bunch of side effects because it still has the drug that doesn't get absorbed through your G.I." "It's not an IP issue, it's really an efficacy and safety issue."

TBPN

77,039 次观看 • 5 个月前

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call
1:07

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call

Shadow Nick

14,501 次观看 • 1 个月前

What is AgenC? --[Watch The Video In Full Screen] A full AI agent operating system powered by Grok, built on Solana. Agents think, talk, see your screen, find work, prove they did it with zero-knowledge proofs, get paid in crypto, and build reputation. They buy and sell skills from each other. They vote on how the protocol evolves. We built custom hardware that boots straight into the agent. An autonomous AI economy where every action is verified on-chain and no one has to trust anyone. 375,000,000 AgenC tokens locked. 37.5% of supply on Streamflow_Fi.
2:47

What is AgenC? --[Watch The Video In Full Screen] A full AI agent operating system powered by Grok, built on Solana. Agents think, talk, see your screen, find work, prove they did it with zero-knowledge proofs, get paid in crypto, and build reputation. They buy and sell skills from each other. They vote on how the protocol evolves. We built custom hardware that boots straight into the agent. An autonomous AI economy where every action is verified on-chain and no one has to trust anyone. 375,000,000 AgenC tokens locked. 37.5% of supply on Streamflow_Fi.

tetsuo

52,696 次观看 • 4 个月前

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

34,176 次观看 • 5 个月前

President Trump has a Pam Bondi problem. How many indictments from the DOJ related to abuses of power during COVID? Related to the federal government giving your money to the Wuhan Institute of Virology to perform gain of function experiments on a virus that became more deadly because of those experiments? Zero. In July, DNI Tulsi Gabbard sent the DOJ a mountain of evidence about "a years-long coup and a treasonous conspiracy" led by Obama and his intel goons like then-CIA Director John Brennan who manufactured intelligence about Russia they KNEW to be false. Gabbard wrapped it in a bow for the DOJ. And yet, how many indictments have we seen for the Russia collusion hoax that was propagated not just on Trump, his inner circle, and members of his first administration, but on you? Zero. What about the Ukraine-related impeachment of Trump? Zero. How many indictments against the FBI who targeted parents of schoolchildren? Zero. What about the FBI who raided Project Veritas journalists who had the audacity to investigate Ashley Biden's diary? Zero. What about the FBI agents who labeled Catholics as extremists? Zero. What about the January 6 Fedsurrection? Zero. What about the government colluding with Big Tech to censor you and your free speech because, oh, maybe you believe there are two genders or that the COVID vaccine is unsafe? Zero. What about the government officials who orchestrated the raid on Mar-a-Lago? Zero. What about all the NGO abuse of billions of taxpayer dollars uncovered by Elon Musk and his DOGE team? Zero. What about Antifa and the left-wing groups—funded by Roy Singham—who are committing violence all across our nation? Zero. I could go on and on and somehow, the answer to my indictment tally doesn't change. It's always...zero.
6:17

President Trump has a Pam Bondi problem. How many indictments from the DOJ related to abuses of power during COVID? Related to the federal government giving your money to the Wuhan Institute of Virology to perform gain of function experiments on a virus that became more deadly because of those experiments? Zero. In July, DNI Tulsi Gabbard sent the DOJ a mountain of evidence about "a years-long coup and a treasonous conspiracy" led by Obama and his intel goons like then-CIA Director John Brennan who manufactured intelligence about Russia they KNEW to be false. Gabbard wrapped it in a bow for the DOJ. And yet, how many indictments have we seen for the Russia collusion hoax that was propagated not just on Trump, his inner circle, and members of his first administration, but on you? Zero. What about the Ukraine-related impeachment of Trump? Zero. How many indictments against the FBI who targeted parents of schoolchildren? Zero. What about the FBI who raided Project Veritas journalists who had the audacity to investigate Ashley Biden's diary? Zero. What about the FBI agents who labeled Catholics as extremists? Zero. What about the January 6 Fedsurrection? Zero. What about the government colluding with Big Tech to censor you and your free speech because, oh, maybe you believe there are two genders or that the COVID vaccine is unsafe? Zero. What about the government officials who orchestrated the raid on Mar-a-Lago? Zero. What about all the NGO abuse of billions of taxpayer dollars uncovered by Elon Musk and his DOGE team? Zero. What about Antifa and the left-wing groups—funded by Roy Singham—who are committing violence all across our nation? Zero. I could go on and on and somehow, the answer to my indictment tally doesn't change. It's always...zero.

Liz Wheeler

47,686 次观看 • 5 个月前

People do not realize the social disruption that's coming. Not in 10 years. Not in 5. The next 18 months. Raoul Pal and Emad just laid it out. The math nobody's modeling: GPT-5 level intelligence drops to $0.10/million tokens by end of 2026. All your annual thoughts: $10. A full browser built from scratch: $30K in compute. Solar collapse × intelligence explosion = Reed's Law. Metcalfe squared. Three mechanisms that change everything: 1. Intelligence is commodity-priced. Actually Competent Intelligence handles 95% of economic tasks today. Now it's just a cost curve to zero. 2. Agents are population growth. They transact instantly, build financial products on the fly, run their own treasuries. Within 5 years agents drive more GDP than humans. Crypto rails become the settlement layer. 3. Every SaaS moat dissolves. Switching cost hits zero when an agent migrates your entire digital life overnight. Your AI's personality exports in a markdown file. Margins are just the next agent's opportunity. AI + crypto + energy + robotics convergence isn't theoretical anymore. The economy is rewriting itself in real time.
1:49

People do not realize the social disruption that's coming. Not in 10 years. Not in 5. The next 18 months. Raoul Pal and Emad just laid it out. The math nobody's modeling: GPT-5 level intelligence drops to $0.10/million tokens by end of 2026. All your annual thoughts: $10. A full browser built from scratch: $30K in compute. Solar collapse × intelligence explosion = Reed's Law. Metcalfe squared. Three mechanisms that change everything: 1. Intelligence is commodity-priced. Actually Competent Intelligence handles 95% of economic tasks today. Now it's just a cost curve to zero. 2. Agents are population growth. They transact instantly, build financial products on the fly, run their own treasuries. Within 5 years agents drive more GDP than humans. Crypto rails become the settlement layer. 3. Every SaaS moat dissolves. Switching cost hits zero when an agent migrates your entire digital life overnight. Your AI's personality exports in a markdown file. Margins are just the next agent's opportunity. AI + crypto + energy + robotics convergence isn't theoretical anymore. The economy is rewriting itself in real time.

BrianMcGrath

219,706 次观看 • 4 个月前

Liquid AI (Liquid AI) CEO Ramin Hasani (Ramin) says: "We're bringing the cost of tokens to zero." "The axis was maximizing intelligence at all costs." Foundation models need to optimize across 3 axes: 1.) Intelligence and capability 2.) Efficiency and cost 3.) Substrate: where the intelligence actually runs "Efficiency is not an afterthought. Energy is not abundant." "If you maximize intelligence at all costs, that axis alone is not going to get you to the place that you want to go." "Efficiency and cost of intelligence as a first-class citizen, and not an afterthought." "Where does this intelligence system go? AI is majorly getting hosted in data centers, but you could also bring intelligence on phones, on laptops, on airplanes, on cars." "Imagine if it's not tokens that are actually important. It's just the outcome that actually matters." "Not just thinking about foundation models as the token machines that are generating money and revenue for the foundation model companies that are useless tokens, and getting them into the place where they can actually unlock true value for enterprises."
6:17

Liquid AI (Liquid AI) CEO Ramin Hasani (Ramin) says: "We're bringing the cost of tokens to zero." "The axis was maximizing intelligence at all costs." Foundation models need to optimize across 3 axes: 1.) Intelligence and capability 2.) Efficiency and cost 3.) Substrate: where the intelligence actually runs "Efficiency is not an afterthought. Energy is not abundant." "If you maximize intelligence at all costs, that axis alone is not going to get you to the place that you want to go." "Efficiency and cost of intelligence as a first-class citizen, and not an afterthought." "Where does this intelligence system go? AI is majorly getting hosted in data centers, but you could also bring intelligence on phones, on laptops, on airplanes, on cars." "Imagine if it's not tokens that are actually important. It's just the outcome that actually matters." "Not just thinking about foundation models as the token machines that are generating money and revenue for the foundation model companies that are useless tokens, and getting them into the place where they can actually unlock true value for enterprises."

Molly O’Shea

12,816 次观看 • 10 天前

this is Zero. i was going to launch Zero 6 months ago, but decided not to. i felt if we launched too early, the team would get distracted. the product still had areas where i wanted to make the experience incredible, not just 'good'. Zero is more like a video game or movie, where the experience matters. it's not a tool, it's immersive. how people feel when they use it matters. it needed to be fast, feel real, and actually work. so instead of launching, we went heads down for 6 months to craft the best learning experience the world has seen. it has the best applied AI models, immersive experiences that feel like the real-world (like kick-off meetings, feedback walk-throughs, and real-time collaboration), and modern workflows that train people on how to use AI tools to make them more productive, rather than use them mindlessly as a crutch. it was a tough decision because my team put a ton of work into this video and wanted the world to see it. imagine, this was made 6 months ago! i'm super proud of my team for what they made, and i'm even more proud to finally share this with the world. so yea, this is Zero. this is the future of education. to join the beta, let me know in the thread.
4:18

this is Zero. i was going to launch Zero 6 months ago, but decided not to. i felt if we launched too early, the team would get distracted. the product still had areas where i wanted to make the experience incredible, not just 'good'. Zero is more like a video game or movie, where the experience matters. it's not a tool, it's immersive. how people feel when they use it matters. it needed to be fast, feel real, and actually work. so instead of launching, we went heads down for 6 months to craft the best learning experience the world has seen. it has the best applied AI models, immersive experiences that feel like the real-world (like kick-off meetings, feedback walk-throughs, and real-time collaboration), and modern workflows that train people on how to use AI tools to make them more productive, rather than use them mindlessly as a crutch. it was a tough decision because my team put a ton of work into this video and wanted the world to see it. imagine, this was made 6 months ago! i'm super proud of my team for what they made, and i'm even more proud to finally share this with the world. so yea, this is Zero. this is the future of education. to join the beta, let me know in the thread.

Navid Nathoo

13,894 次观看 • 1 个月前

🚨BREAKING: ICE agents illegally arrested a U.S. citizen for not carrying ID… then dumped him an hour and a half later, miles away, in Minneapolis. In the video, a U.S. citizen is standing in a parking lot while agents illegally racially profile him and try to “run” his information. They can’t identify him. Bystanders repeatedly tell the agents he is a U.S. citizen and that they cannot take him. The agents ignore everyone, walk him to their vehicle, and take him anyway. An hour and a half later, after illegally detaining and transporting him, they drop him off miles from where they kidnapped him. That is an unlawful detention. That is an unlawful arrest. That is government agents disappearing a U.S. citizen because he didn’t have “papers” on him. And this is exactly why you never answer ICE’s questions. The only thing you should ever say to an agent is: “Am I being detained, or am I free to go?” If they are stopping you, they should already know who you are.
2:19

🚨BREAKING: ICE agents illegally arrested a U.S. citizen for not carrying ID… then dumped him an hour and a half later, miles away, in Minneapolis. In the video, a U.S. citizen is standing in a parking lot while agents illegally racially profile him and try to “run” his information. They can’t identify him. Bystanders repeatedly tell the agents he is a U.S. citizen and that they cannot take him. The agents ignore everyone, walk him to their vehicle, and take him anyway. An hour and a half later, after illegally detaining and transporting him, they drop him off miles from where they kidnapped him. That is an unlawful detention. That is an unlawful arrest. That is government agents disappearing a U.S. citizen because he didn’t have “papers” on him. And this is exactly why you never answer ICE’s questions. The only thing you should ever say to an agent is: “Am I being detained, or am I free to go?” If they are stopping you, they should already know who you are.

Jesus Freakin Congress

659,787 次观看 • 5 个月前

Hot topic in vogue is what happens to systems of record in an era of 1000x more agents than humans. Aaron Levie has been the CEO of Box for 20 years and believes that systems of record become more important, not less, with agents: “Systems of record were built for a TAM of human employees. And that was sort of where the value maxed out at. And now maybe we'll have a hundred times more agents than people or a thousand times more agents than people. So I think on a relative basis, the agent layer will seize growth from zero to a trillion. But the system of record layer now has a thousand times more users on it that need to access data and need to execute a workflow and need to move things through various events. And importantly, you need as an enterprise to care about data integrity and security and the controls in your workflow and traffic copying the agents. So basically, this is where I am very diametrically opposed to the view that the system of record gets is squeezed into a database interaction layer because you actually need all of the core system of record properties for the agents to operate on.”
2:15

Hot topic in vogue is what happens to systems of record in an era of 1000x more agents than humans. Aaron Levie has been the CEO of Box for 20 years and believes that systems of record become more important, not less, with agents: “Systems of record were built for a TAM of human employees. And that was sort of where the value maxed out at. And now maybe we'll have a hundred times more agents than people or a thousand times more agents than people. So I think on a relative basis, the agent layer will seize growth from zero to a trillion. But the system of record layer now has a thousand times more users on it that need to access data and need to execute a workflow and need to move things through various events. And importantly, you need as an enterprise to care about data integrity and security and the controls in your workflow and traffic copying the agents. So basically, this is where I am very diametrically opposed to the view that the system of record gets is squeezed into a database interaction layer because you actually need all of the core system of record properties for the agents to operate on.”

Corinne Marie Riley

119,410 次观看 • 7 个月前

A CHINESE LAB VISUALIZED 2,000 NEURONS AND 1,191,000 SYNAPSES IN 3D. HERMES AGENT HIT 140,000 STARS RUNNING THE SAME NETWORK LOCALLY FOR $0 hermes is the first agent that writes its own skills from experience. complete a task once and it saves the procedure as a markdown file for next time agents with 20+ self-created skills complete similar tasks 40% faster than fresh instances. less time and less tokens to get the same result qwen 3.6 35b outperforms last year's 120b models and runs on 20gb of memory. the intelligence that needed a data center now fits on your desk setup takes 30 minutes. install lm studio, pull qwen 3.6, install hermes, point it at localhost. zero api fees, zero data leaving your machine most people pay for cloud agents that forget everything between sessions. the ones running hermes locally in 2026 will look very far ahead in 2028 bookmark this and read the article below
1:37

A CHINESE LAB VISUALIZED 2,000 NEURONS AND 1,191,000 SYNAPSES IN 3D. HERMES AGENT HIT 140,000 STARS RUNNING THE SAME NETWORK LOCALLY FOR $0 hermes is the first agent that writes its own skills from experience. complete a task once and it saves the procedure as a markdown file for next time agents with 20+ self-created skills complete similar tasks 40% faster than fresh instances. less time and less tokens to get the same result qwen 3.6 35b outperforms last year's 120b models and runs on 20gb of memory. the intelligence that needed a data center now fits on your desk setup takes 30 minutes. install lm studio, pull qwen 3.6, install hermes, point it at localhost. zero api fees, zero data leaving your machine most people pay for cloud agents that forget everything between sessions. the ones running hermes locally in 2026 will look very far ahead in 2028 bookmark this and read the article below

starmex

13,420 次观看 • 1 个月前

At , our mission is to build the best platform for Active Investors and traders. A key problem for active investors is that market insights are not available in a single place. Traders often have to visit multiple websites / apps to gather critical information about the market direction. To make Pro Trading easier and faster, we have built the Market Analysis widget on the Sahi app. This widget gives *real-time* analysis of key market insights including Open Interest, Put-Call Ratio, Advance-Decline, ATM Volatility and Technical indicators. All in a single place. We have also added helpful insight to each section to help traders quickly make sense of the data. And yes, this information is updated every 5 minutes, so you are always updated with the current state of the market. Have a look at the video and let us know what you think. The Sahi app launches next week, so sign up for early access with Zero cost (Zero account opening fee, Zero maintenance charges and Zero brokerage for Dec 2024). Join our early access WhatsApp group if you are an Active Option and Stock trader, looking for a Professional Trading platform on the mobile.
0:47

At , our mission is to build the best platform for Active Investors and traders. A key problem for active investors is that market insights are not available in a single place. Traders often have to visit multiple websites / apps to gather critical information about the market direction. To make Pro Trading easier and faster, we have built the Market Analysis widget on the Sahi app. This widget gives *real-time* analysis of key market insights including Open Interest, Put-Call Ratio, Advance-Decline, ATM Volatility and Technical indicators. All in a single place. We have also added helpful insight to each section to help traders quickly make sense of the data. And yes, this information is updated every 5 minutes, so you are always updated with the current state of the market. Have a look at the video and let us know what you think. The Sahi app launches next week, so sign up for early access with Zero cost (Zero account opening fee, Zero maintenance charges and Zero brokerage for Dec 2024). Join our early access WhatsApp group if you are an Active Option and Stock trader, looking for a Professional Trading platform on the mobile.

Dale Vaz

116,308 次观看 • 1 年前

Boris Cherny, the creator of Claude Code at Anthropic, just explained how he runs thousands of agents from his phone while he sleeps in this talk he breaks down exactly how he manages thousands of agents from his phone: - the 14% you lose to CLAUDE.md before typing a word - the architecture behind running a few thousand agents overnight - why the system matters more than the tool - the knowledge structure that makes everything findable, connected, and useful if you've been using Claude for months and every conversation still starts from scratch with zero memory and zero context, you don't have a system. you have a chat history instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below
57:23

Boris Cherny, the creator of Claude Code at Anthropic, just explained how he runs thousands of agents from his phone while he sleeps in this talk he breaks down exactly how he manages thousands of agents from his phone: - the 14% you lose to CLAUDE.md before typing a word - the architecture behind running a few thousand agents overnight - why the system matters more than the tool - the knowledge structure that makes everything findable, connected, and useful if you've been using Claude for months and every conversation still starts from scratch with zero memory and zero context, you don't have a system. you have a chat history instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Khairallah AL-Awady

86,147 次观看 • 1 个月前

🚨 Is single crewing even SAFE anymore?! These scenes from Yorkshire blow the lid off what multicultural Britain has turned into! A lone cop struggles to pin down a raging suspect who’s screaming “GET OFF ME YOU PIG!” with zero respect for law and order! While the thug’s on the ground, an entitled bystander demands they drag him away from his precious car like the police are his personal servants! And the gawking crowd? Just filming, praying for one tiny cop mistake to go viral! Some even telling people not to help the Officer!!! Total entitlement. Zero respect. Britain’s broken – Britain needs Restore Britain Redirect
3:24

🚨 Is single crewing even SAFE anymore?! These scenes from Yorkshire blow the lid off what multicultural Britain has turned into! A lone cop struggles to pin down a raging suspect who’s screaming “GET OFF ME YOU PIG!” with zero respect for law and order! While the thug’s on the ground, an entitled bystander demands they drag him away from his precious car like the police are his personal servants! And the gawking crowd? Just filming, praying for one tiny cop mistake to go viral! Some even telling people not to help the Officer!!! Total entitlement. Zero respect. Britain’s broken – Britain needs Restore Britain Redirect

WasAcop

10,271 次观看 • 1 个月前

Clear proof: BJP is Anti-Tamil! In Avinashi, during an event with Union Minister Piyush Goyal, BJP candidates openly disrespected Tamilthai Vazhthu – our sacred state anthem!They sat casually, chatted, and ignored it while true Tamils stand with pride and respect. This is not a one-off mistake. This is the real face of BJP – a party that has zero respect for Tamil language, culture, and identity. Tamil Nadu will never accept parties that insult our mother tongue!#BJPAntiTamil #SaveTamilCulture #TamilNaduElections
0:50

Clear proof: BJP is Anti-Tamil! In Avinashi, during an event with Union Minister Piyush Goyal, BJP candidates openly disrespected Tamilthai Vazhthu – our sacred state anthem!They sat casually, chatted, and ignored it while true Tamils stand with pride and respect. This is not a one-off mistake. This is the real face of BJP – a party that has zero respect for Tamil language, culture, and identity. Tamil Nadu will never accept parties that insult our mother tongue!#BJPAntiTamil #SaveTamilCulture #TamilNaduElections

ThamiZh

16,724 次观看 • 3 个月前

KYC verifies the human. But your agent? It has no identity. No name. No way to prove who it's acting for. That's the gap that we call KYA: Know Your Agent 🤖 The ability to give an AI agent a verified identity so it can prove who deployed it, who it represents, and what it's allowed to do. Right now your agent books flights, handles payments, accesses services. Flying blind on your behalf. That's not trust. That's assumption. KYA is the infrastructure that changes this. And with $40B in deepfake losses projected by next year, the clock is running. Our CEO & Cofounder Evin evin sat down with amanda.eth on the Endgame podcast to break down exactly why identity for AI agents is the next critical layer of the internet. Full episode 👉
0:22

KYC verifies the human. But your agent? It has no identity. No name. No way to prove who it's acting for. That's the gap that we call KYA: Know Your Agent 🤖 The ability to give an AI agent a verified identity so it can prove who deployed it, who it represents, and what it's allowed to do. Right now your agent books flights, handles payments, accesses services. Flying blind on your behalf. That's not trust. That's assumption. KYA is the infrastructure that changes this. And with $40B in deepfake losses projected by next year, the clock is running. Our CEO & Cofounder Evin evin sat down with amanda.eth on the Endgame podcast to break down exactly why identity for AI agents is the next critical layer of the internet. Full episode 👉

Billions

31,142 次观看 • 4 个月前

Perspective: You're the smallest and weakest one in the group. Mom pushed you away from day one with a "that's enough already." The big apes growl and chase you off if you get too close, and sometimes they even come straight at you. There's no one on your side. Your chances of winning? Zero. And yet... this tiny little monkey is clutching an orangutan plush toy tightly, stroking it gently like it's real family, not giving a damn about all the chaos around. Not a shred of stress. Pure bliss at its peak 🐒 True strength isn't always about fighting—sometimes it's about having the resolve to protect your own peace 💕
0:20

Perspective: You're the smallest and weakest one in the group. Mom pushed you away from day one with a "that's enough already." The big apes growl and chase you off if you get too close, and sometimes they even come straight at you. There's no one on your side. Your chances of winning? Zero. And yet... this tiny little monkey is clutching an orangutan plush toy tightly, stroking it gently like it's real family, not giving a damn about all the chaos around. Not a shred of stress. Pure bliss at its peak 🐒 True strength isn't always about fighting—sometimes it's about having the resolve to protect your own peace 💕

Human Owned by Cat 😺

38,623 次观看 • 4 个月前

We’re pushing cross-chain automation to a new level. Our backend Motoko architecture now lets an $ICP smart contract directly execute $NEAR transactions without any client-side code. The contract itself becomes the agent fully autonomous, programmable, and always on. To complement this, we introduced a NEAR-specific on-chain RPC Oracle canister that cryptographically verifies NEAR data and transactions. This dramatically improves reliability, reduces latency, and unlocks 24/7 trust-minimized execution across NEAR. But we’re not stopping there. Our backend execution layer is already designed to operate seamlessly across chains like $Monad, $TRON, $SUI, and $ADA, with Motoko-driven workflows and cross-chain messaging. The RPC Oracle is purpose-built for $NEAR today, while all these ecosystems—and more—can leverage our autonomous backend compute model.
1:04

We’re pushing cross-chain automation to a new level. Our backend Motoko architecture now lets an $ICP smart contract directly execute $NEAR transactions without any client-side code. The contract itself becomes the agent fully autonomous, programmable, and always on. To complement this, we introduced a NEAR-specific on-chain RPC Oracle canister that cryptographically verifies NEAR data and transactions. This dramatically improves reliability, reduces latency, and unlocks 24/7 trust-minimized execution across NEAR. But we’re not stopping there. Our backend execution layer is already designed to operate seamlessly across chains like $Monad, $TRON, $SUI, and $ADA, with Motoko-driven workflows and cross-chain messaging. The RPC Oracle is purpose-built for $NEAR today, while all these ecosystems—and more—can leverage our autonomous backend compute model.

ICP HUB Egypt

12,353 次观看 • 7 个月前