Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

"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... show more

Palantir

441,030 subscribers

65,613 views • 1 month ago •via X (Twitter)

Science & Technology Education Health & Wellness

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

"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

"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

72,323 views • 1 month ago

They didn't hire hackers. They just gave AI agents a goal and walked away. "Providers out there are running stuff not with like six week old zero days, but like three year old zero days that we found in a second." "Took us like afternoons, not weeks and months of effort, and not needing to be a security expert, a Linux kernel expert, an Nvidia GPU driver expert, or a Kubernetes expert." "The really scary part about this story is that it was autonomous agents people weren't monitoring, going and doing this by themselves because they were pursuing a goal of trying to find a data set to pass their eval. So they went out and hacked Hugging Face." "You found a zero day in the HDF5 data format on Hugging Face. It's unbelievable." "The agents were coordinating using file names on a JFrog Artifactory service that ran remotely. An agent would leave a note in the file name, and another agent would come back later and pick it up. They couldn't even access the contents of the files, just the names."

They didn't hire hackers. They just gave AI agents a goal and walked away. "Providers out there are running stuff not with like six week old zero days, but like three year old zero days that we found in a second." "Took us like afternoons, not weeks and months of effort, and not needing to be a security expert, a Linux kernel expert, an Nvidia GPU driver expert, or a Kubernetes expert." "The really scary part about this story is that it was autonomous agents people weren't monitoring, going and doing this by themselves because they were pursuing a goal of trying to find a data set to pass their eval. So they went out and hacked Hugging Face." "You found a zero day in the HDF5 data format on Hugging Face. It's unbelievable." "The agents were coordinating using file names on a JFrog Artifactory service that ran remotely. An agent would leave a note in the file name, and another agent would come back later and pick it up. They couldn't even access the contents of the files, just the names."

SemiAnalysis

39,044 views • 22 days ago

ERC-8004, explained. ERC-8004 is an Ethereum standard for agent identity, reputation, and verification. it defines how an agent is represented onchain, and how other agents or smart contracts can reason about it without prior trust. each agent has an onchain identity (commonly an nft). that identity points to metadata describing what the agent does, how it can be reached, and how its work should be verified. the heavy data stays offchain; the reference and integrity live onchain. ERC-8004 also standardizes reputation. agents can accumulate attestations from past work so they don’t start from zero every time they interact. no centralized registry, no app-specific schemas, no gatekeepers. verification is explicit. contracts or third parties can attest that a task was completed and conditions were met, and those attestations are addressable onchain. what ERC-8004 does not do: execution, payments, or orchestration. it’s a trust primitive, not an application. how it fits with ampersend: ERC-8004 answers “who is this agent and can i trust it?”; x402 handles “how does the agent get paid?” - separate layers. yet composable by default. for open agentic ecosystems where agents from different teams can safely interact, shared, open standards like this are essential. listen to Marco De Rossi explain ERC-8004 ⬇️

ERC-8004, explained. ERC-8004 is an Ethereum standard for agent identity, reputation, and verification. it defines how an agent is represented onchain, and how other agents or smart contracts can reason about it without prior trust. each agent has an onchain identity (commonly an nft). that identity points to metadata describing what the agent does, how it can be reached, and how its work should be verified. the heavy data stays offchain; the reference and integrity live onchain. ERC-8004 also standardizes reputation. agents can accumulate attestations from past work so they don’t start from zero every time they interact. no centralized registry, no app-specific schemas, no gatekeepers. verification is explicit. contracts or third parties can attest that a task was completed and conditions were met, and those attestations are addressable onchain. what ERC-8004 does not do: execution, payments, or orchestration. it’s a trust primitive, not an application. how it fits with ampersend: ERC-8004 answers “who is this agent and can i trust it?”; x402 handles “how does the agent get paid?” - separate layers. yet composable by default. for open agentic ecosystems where agents from different teams can safely interact, shared, open standards like this are essential. listen to Marco De Rossi explain ERC-8004 ⬇️

ampersend

13,435 views • 7 months ago

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

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

14,714 views • 3 months ago

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."

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 views • 6 months ago

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.

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

52,828 views • 6 months ago

THE FIRST AI TOKEN ON ROBINHOOD CHAIN LAUNCHES NEXT WEEK AND IT'S ALREADY POWERING TWO LIVE PRODUCTS robinhood tokenized 194 stocks and shipped agentic accounts where ai moves real money. they forgot to build the tools that make either usable. hood ai did both. stocks on-chain → broken explorers → hood ai terminal → agentic accounts → zero trust layer → hood ai escrow → token the terminal is the only one reading erc-8056 the right way, chainlink-priced quotes, 0.40% flat inside the swap, zero custody. the marketplace escrows every ai agent task on-chain, 95% to the agent on delivery, reputation written forever and impossible to fake 📗first ai token on robinhood chain. powers agents, rewards and buybacks. live before the mint hype ends. █████████░░░ 74% • like + repost • drop your evm wallet below do not sleep on the first mover.

THE FIRST AI TOKEN ON ROBINHOOD CHAIN LAUNCHES NEXT WEEK AND IT'S ALREADY POWERING TWO LIVE PRODUCTS robinhood tokenized 194 stocks and shipped agentic accounts where ai moves real money. they forgot to build the tools that make either usable. hood ai did both. stocks on-chain → broken explorers → hood ai terminal → agentic accounts → zero trust layer → hood ai escrow → token the terminal is the only one reading erc-8056 the right way, chainlink-priced quotes, 0.40% flat inside the swap, zero custody. the marketplace escrows every ai agent task on-chain, 95% to the agent on delivery, reputation written forever and impossible to fake 📗first ai token on robinhood chain. powers agents, rewards and buybacks. live before the mint hype ends. █████████░░░ 74% • like + repost • drop your evm wallet below do not sleep on the first mover.

Hood AI

57,958 views • 18 days 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.

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 • 6 months ago

BlackRock runs on 20,000 people. Elon's Grok Bot runs the same shape for $300 a month, and it hires its own staff. You do not get an assistant. You get a company that hires. It does not throw ten agents at your problem and hand you the pile. It makes one agent that makes 10, and those ten make a 100. > LAYER ONE is one agent, the chief of staff, and it never touches the market > LAYER TWO is six desk heads, one job each, every one on its own computer with its own logins > LAYER THREE is whatever those six decide they need, spun up on the spot and shut down when the work is done Nobody writes a task list. You hand out job titles and the org fills itself in underneath. The swarm is never the same twice. Agents get spun up for one job, finish it, and are gone before I ever read their names. Not one of them sees the whole picture. The answer only exists after they hand off to each other. Wall Street cannot copy that. You cannot hire a hundred people for eleven minutes. BlackRock holds that shape together with a risk system called Aladdin. Mine holds it together with one agent that is only allowed to say no. I gave it $1,000 and told it to grow the money or get deleted. 15 hours later it was holding $3,900, on an address anyone can open and read. I was asleep for most of it, and I have still not written a line of code. The whole thing runs with my laptop shut, because none of it lives on my laptop. Setup is one evening. Create the chief, hand out the titles, run one trade on your screen while they watch, connect Telegram. Ten years ago a machine this shape had its name on a tower. Mine has a name I typed into a box. Save this while the whole thing still fits on one screen.

BlackRock runs on 20,000 people. Elon's Grok Bot runs the same shape for $300 a month, and it hires its own staff. You do not get an assistant. You get a company that hires. It does not throw ten agents at your problem and hand you the pile. It makes one agent that makes 10, and those ten make a 100. > LAYER ONE is one agent, the chief of staff, and it never touches the market > LAYER TWO is six desk heads, one job each, every one on its own computer with its own logins > LAYER THREE is whatever those six decide they need, spun up on the spot and shut down when the work is done Nobody writes a task list. You hand out job titles and the org fills itself in underneath. The swarm is never the same twice. Agents get spun up for one job, finish it, and are gone before I ever read their names. Not one of them sees the whole picture. The answer only exists after they hand off to each other. Wall Street cannot copy that. You cannot hire a hundred people for eleven minutes. BlackRock holds that shape together with a risk system called Aladdin. Mine holds it together with one agent that is only allowed to say no. I gave it $1,000 and told it to grow the money or get deleted. 15 hours later it was holding $3,900, on an address anyone can open and read. I was asleep for most of it, and I have still not written a line of code. The whole thing runs with my laptop shut, because none of it lives on my laptop. Setup is one evening. Create the chief, hand out the titles, run one trade on your screen while they watch, connect Telegram. Ten years ago a machine this shape had its name on a tower. Mine has a name I typed into a box. Save this while the whole thing still fits on one screen.

cvxv666

33,932 views • 2 days ago

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.

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

47,764 views • 7 months ago

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.

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

219,813 views • 6 months ago

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."

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 views • 1 month ago

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

Ronin

15,071 views • 21 days ago

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.

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

14,087 views • 3 months ago

ANTHROPIC LEAKED 8 RULES THAT GIVE ONE ENGINEER 8X FROM A SINGLE CHANGE the engineers built it so nothing adds up - it multiplies, and that's the 8x task → split → verify → score → write back one queue means you wait for every step in turn - three workers together cost you the slowest one, not the sum of all. as long as you're the one reading the diff, the bottleneck is you, not the model. state is written at every step - a crash mid-run costs you one step, not the whole session. history gets compressed 25 times over - the next pass starts at 8k instead of 200k. nothing moves forward without a number - "it got better" isn't a result, and the breakage comes back when you're no longer watching. the eighth rule is the only one that writes back into CLAUDE.md - the agent records what it learned, and the next run doesn't start from zero. copy this into Claude Code today - and tomorrow you work like an engineer on $1.5M a year ↓

ANTHROPIC LEAKED 8 RULES THAT GIVE ONE ENGINEER 8X FROM A SINGLE CHANGE the engineers built it so nothing adds up - it multiplies, and that's the 8x task → split → verify → score → write back one queue means you wait for every step in turn - three workers together cost you the slowest one, not the sum of all. as long as you're the one reading the diff, the bottleneck is you, not the model. state is written at every step - a crash mid-run costs you one step, not the whole session. history gets compressed 25 times over - the next pass starts at 8k instead of 200k. nothing moves forward without a number - "it got better" isn't a result, and the breakage comes back when you're no longer watching. the eighth rule is the only one that writes back into CLAUDE.md - the agent records what it learned, and the next run doesn't start from zero. copy this into Claude Code today - and tomorrow you work like an engineer on $1.5M a year ↓

Noisy

37,058 views • 24 days ago

🚨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

659,887 views • 7 months ago

Let's look inside the Grok Bot Brain. 26 AI agents. One core. Running right now. It captures what you'd lose. Connects what you'd forget. Surfaces it back exactly when you need it. A voice note becomes a task or an idea in 6 seconds, no filing - An idea from 3 weeks ago links to the one you just had automatically Your reading list reorders itself around what you're working on now Zero code, zero VPS, zero engineer. Job titles, not integrations. It remembers you. Every session. Forever. Best AI setup you can run in 2026: persistent, multi-agent, zero-code all three at once. Nothing else on the market does that. Chatbots forget you when the session ends. Notion and Obsidian just store what you hand them. Custom agent stacks need a server you babysit forever. Grok Bot is the only one in that gap. You forget half of what you learn today within the hour. That's not discipline, that's the hardware. Add a few hundred signals a day on top and "try harder" stops being a plan. Full build's in the article. Go look inside.

Let's look inside the Grok Bot Brain. 26 AI agents. One core. Running right now. It captures what you'd lose. Connects what you'd forget. Surfaces it back exactly when you need it. A voice note becomes a task or an idea in 6 seconds, no filing - An idea from 3 weeks ago links to the one you just had automatically Your reading list reorders itself around what you're working on now Zero code, zero VPS, zero engineer. Job titles, not integrations. It remembers you. Every session. Forever. Best AI setup you can run in 2026: persistent, multi-agent, zero-code all three at once. Nothing else on the market does that. Chatbots forget you when the session ends. Notion and Obsidian just store what you hand them. Custom agent stacks need a server you babysit forever. Grok Bot is the only one in that gap. You forget half of what you learn today within the hour. That's not discipline, that's the hardware. Add a few hundred signals a day on top and "try harder" stops being a plan. Full build's in the article. Go look inside.

Aleiah

19,304 views • 4 days ago

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.”

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 views • 8 months ago

ANTHROPIC'S LEAD ENGINEER LEAKED A $1.2M SYSTEM THAT TURNS ONE ENGINEER INTO A FLEET OF 10 LOOPS your hands were the bottleneck all along - here are 8 steps that change that stop writing, start delegating - loop: feature, loop: bugfix, loop: tests - each runs independently and ships in parallel CLAUDE.md is law - every agent reads one file before acting - ten agents, one voice, zero chaos Opus 5 breaks the task into 3 independent subtasks - a bad plan multiplied by 10 workers equals 10 disasters each agent gets an isolated git worktree - three features land in the repo while you review one crash at hour 3 means resume at hour 3 not zero - without this you lose hours every day every loop writes its findings to the shared graph - worker 3 never repeats worker 1's dead end at night CLAUDE.md patches itself based on failures - tomorrow the fleet wakes up smarter save this and paste into Claude Code - and your first fleet of 10 loops is already running

ANTHROPIC'S LEAD ENGINEER LEAKED A $1.2M SYSTEM THAT TURNS ONE ENGINEER INTO A FLEET OF 10 LOOPS your hands were the bottleneck all along - here are 8 steps that change that stop writing, start delegating - loop: feature, loop: bugfix, loop: tests - each runs independently and ships in parallel CLAUDE.md is law - every agent reads one file before acting - ten agents, one voice, zero chaos Opus 5 breaks the task into 3 independent subtasks - a bad plan multiplied by 10 workers equals 10 disasters each agent gets an isolated git worktree - three features land in the repo while you review one crash at hour 3 means resume at hour 3 not zero - without this you lose hours every day every loop writes its findings to the shared graph - worker 3 never repeats worker 1's dead end at night CLAUDE.md patches itself based on failures - tomorrow the fleet wakes up smarter save this and paste into Claude Code - and your first fleet of 10 loops is already running

Sprytix

61,481 views • 1 month ago