Video wird geladen...

Video konnte nicht geladen werden

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

AI AGENTS ARE DOING REAL WORK. WHEN SOMETHING GOES WRONG, NO ONE KNOWS WHO'S RESPONSIBLE. UNTIL NOW. Every company deploying agents in production has the same unsolved problem: if the agent makes a mistake with real consequences, there's no coverage, no protocol, and no one to answer for it.... show more

rob.

104,113 subscribers

29,025 Aufrufe • vor 20 Tagen •via X (Twitter)

Wissenschaft & Technologie Finanzen

Anya Rossi• Live Now

Private livecam show

20 Kommentare

Profilbild von roman

romanvor 20 Tagen

Insurance + AI agents wasn’t on my bingo card, but it makes total sense.

Profilbild von draven

dravenvor 20 Tagen

Bookmarking this. Agent insurance is going to be a category to watch in 2027.

Profilbild von ryu.

ryu.vor 20 Tagen

The companies that scale agents fastest will be the ones that can transfer the risk. Harbor gets that.

Profilbild von alex

alexvor 20 Tagen

Base10, Abstract and 8VC on the same seed round. Investors clearly see where this is going.

Profilbild von yuulia ✟

yuulia ✟vor 20 Tagen

No coverage, no protocol, no one accountable. That’s been the state of production agents. Glad it’s changing.

Profilbild von Joselito 🌿

Joselito 🌿vor 20 Tagen

When something goes wrong, no one knows who’s responsible — until the risk explodes.

Profilbild von SmartSentinels

SmartSentinelsvor 20 Tagen

Underwriting needs a record of what the agent was asked to do, what it actually did, and who signed off. Without that, every claim turns into an argument. Teams that log scoped tasks and checkable outputs now are the ones who'll be insurable later.

Profilbild von Vivi

Vivivor 20 Tagen

Insurance is usually the moment a technology stops being an experiment and becomes infrastructure. Big signal

Profilbild von ethan

ethanvor 20 Tagen

The protocol part is underrated. Knowing what to do after a failure matters as much as the coverage.

Profilbild von marcus

marcusvor 20 Tagen

Interesting to see if this pushes builders toward better logging and observability to get lower premiums.

Profilbild von z

zvor 20 Tagen

Wild that a whole insurance category didn’t exist 2 years ago because the thing it insures didn’t exist either.

Profilbild von GARLOTIC

GARLOTICvor 20 Tagen

When insurers start pricing a risk, it means the risk is real and the market is real.

Profilbild von alex

alexvor 20 Tagen

This is what unlocks enterprise adoption. Legal teams won’t sign off without someone holding the risk

Profilbild von Chesny

Chesnyvor 20 Tagen

Curious how they price it. Measuring agent risk sounds like half the product.

Profilbild von Biscuit

Biscuitvor 20 Tagen

pricing these policies must be tricky

Profilbild von SONIA

SONIAvor 20 Tagen

Finally someone treating agent failures as a business problem, not just an engineering one.

Profilbild von Leo

Leovor 20 Tagen

If you can measure it, you can manage it. If you can manage it, you can insure it. Clean logic.

Profilbild von ares. 🎧

ares. 🎧vor 20 Tagen

$10M to build the trust layer for autonomous agents. Feels like the beginning of something big.

Profilbild von Wuki

Wukivor 20 Tagen

Finally, someone putting skin in the game for agent risk. 🤝 just dropped a follow

Profilbild von carolina

carolinavor 20 Tagen

Cars got insurance, then everyone drove. Agents might follow the same path.

Ähnliche Videos

YOU CAN INSURE A DRIVER. NOBODY INSURES THE AGENT. YET. i just saw this, it's called Harbor: → just out of stealth → $10M seed led by Base10, Abstract and 8VC → building insurance for agents doing work humans used to do the risk is moving from people to machines. someone had to price it

YOU CAN INSURE A DRIVER. NOBODY INSURES THE AGENT. YET. i just saw this, it's called Harbor: → just out of stealth → $10M seed led by Base10, Abstract and 8VC → building insurance for agents doing work humans used to do the risk is moving from people to machines. someone had to price it

céline ✧

14,646 Aufrufe • vor 20 Tagen

YOUR BANK'S AI AGENT IS MAKING 10,000 DECISIONS A DAY AND NOBODY IS CHECKING THEM "human in the loop" sounds great until the agent approves, prices and pays thousands of times before lunch and if it gets one decision wrong, it gets every similar decision wrong that's why insurers are quietly adding AI exclusions to their policies harbor just came out of stealth with $10M to fix exactly that: → connects to every agent a company runs → measures its risk in production, decision by decision → blocks the actions that break policy → insures whatever risk is left if nobody insures agents, nobody serious deploys them

YOUR BANK'S AI AGENT IS MAKING 10,000 DECISIONS A DAY AND NOBODY IS CHECKING THEM "human in the loop" sounds great until the agent approves, prices and pays thousands of times before lunch and if it gets one decision wrong, it gets every similar decision wrong that's why insurers are quietly adding AI exclusions to their policies harbor just came out of stealth with $10M to fix exactly that: → connects to every agent a company runs → measures its risk in production, decision by decision → blocks the actions that break policy → insures whatever risk is left if nobody insures agents, nobody serious deploys them

nerea

49,133 Aufrufe • vor 20 Tagen

Today, we're launching Ramp Agent Cards. There's been no safe way for agents to spend money, until now. Ramp Agent Cards give agents the ability to spend, governed with real spend limits, merchant controls, and full visibility into every transaction.

Today, we're launching Ramp Agent Cards. There's been no safe way for agents to spend money, until now. Ramp Agent Cards give agents the ability to spend, governed with real spend limits, merchant controls, and full visibility into every transaction.

Ramp Labs

849,245 Aufrufe • vor 7 Monaten

IBM engineers just released a 40-minute deep dive into “Agent Engineering” for building production-ready AI agents “80% of building an AI agent has nothing to do with the model. It is frameworks, tools, skills and risk controls.” 00:00 - the 5 core concepts behind every AI agent 11:07 - choosing frameworks for tools, memory and orchestration 23:01 - when agents need MCP, skills or both 31:04 - designing AI architecture around real production risk The core stack: Agent → Framework → MCP → Skills → Risk → Production This 40-minute workshop will teach you more about production AI agents than most $500 Agent Engineering courses. Watch it today, then read the full agent engineering playbook in the article below ↓

IBM engineers just released a 40-minute deep dive into “Agent Engineering” for building production-ready AI agents “80% of building an AI agent has nothing to do with the model. It is frameworks, tools, skills and risk controls.” 00:00 - the 5 core concepts behind every AI agent 11:07 - choosing frameworks for tools, memory and orchestration 23:01 - when agents need MCP, skills or both 31:04 - designing AI architecture around real production risk The core stack: Agent → Framework → MCP → Skills → Risk → Production This 40-minute workshop will teach you more about production AI agents than most $500 Agent Engineering courses. Watch it today, then read the full agent engineering playbook in the article below ↓

Morlex

14,597 Aufrufe • vor 3 Monaten

Jamie Dimon made $39 million last year to decide who does what at JPMorgan. One AI agent on Grok Bot does that job for $300 a month, and it hires the rest of the agents itself. Stop trying to manage any of it yourself. In 2026 a swarm of AI agents runs a team better than you do. I told my chief agent one thing. Make money or I switch you off. It took $1,000 to $3,900 in 15 hours. Every fill is on chain and the address is in my profile. I never picked a trade. I never picked a team either. The agents it hired: > a scout that hunts for what is moving and where the money is going > a forensics agent that works out who is really behind the buying > a reader that watches the mood on X, and it sees every post on this app because it is Grok > a risk agent whose only power is saying no, and its no beats every score on the desk > a treasurer that holds the money rules and the kill switch > a trader that writes the exit before it writes the entry None of those were my idea. I handed out one job title and the chief filled in the rest on its own. And the swarm is different every hour. Agents appear for one job, do it, and are gone before I know they existed. A hedge fund pays millions a year for the same org chart, and almost all of that goes on salaries. Every prompt and the whole story of my Grok Bot fund is in the post below ↓ Save it before you try to run one of these by hand.

cvxv666

28,886 Aufrufe • vor 2 Monaten

I created a free Markdown file that launches a 5-agent swarm team directly in Slack. I love Claude Code, but it's not the easiest place to manage your agents. Slack is where teams already work. So I put my agents there too. Drop the file in, and you get 5 agents, each with its own channel and job: • [Agent 1]: [what it does] • [Agent 2]: [what it does] • [Agent 3]: [what it does] • [Agent 4]: [what it does] • [Agent 5]: [what it does] You can assign work by messaging them like real employees, and they report back in the same threads. It's the closest I've found to running a real company with AI employees.

I created a free Markdown file that launches a 5-agent swarm team directly in Slack. I love Claude Code, but it's not the easiest place to manage your agents. Slack is where teams already work. So I put my agents there too. Drop the file in, and you get 5 agents, each with its own channel and job: • [Agent 1]: [what it does] • [Agent 2]: [what it does] • [Agent 3]: [what it does] • [Agent 4]: [what it does] • [Agent 5]: [what it does] You can assign work by messaging them like real employees, and they report back in the same threads. It's the closest I've found to running a real company with AI employees.

Miles Deutscher

25,762 Aufrufe • vor 12 Tagen

Polsia's product line is the real story, not the raise. Ben has no employees. The agents that ran his data room and diligence are the same ones shipping the products. An ops desk for small businesses. A tool that reads your paperwork for leaks. All of it in three languages already. The $30M didn't build the company. It confirmed one was already running.

Polsia's product line is the real story, not the raise. Ben has no employees. The agents that ran his data room and diligence are the same ones shipping the products. An ops desk for small businesses. A tool that reads your paperwork for leaks. All of it in three languages already. The $30M didn't build the company. It confirmed one was already running.

AI Highlight

10,923 Aufrufe • vor 2 Monaten

$FET just quietly built the internet for AI agents. 3,000,000 agents. One network. One token. Here's what nobody is explaining: Every AI agent needs 3 things to be useful: An address. A way to be found. A way to get paid. Agentverse gives agents all three. Your agent becomes discoverable on ASI: One. Other agents can find it, call it, or hire it. Automatically. No human in the loop. This is agent-to-agent commerce. And every transaction settles in $FET. More agents = more activity = more demand. The infrastructure is already live. The economy is just getting started.

$FET just quietly built the internet for AI agents. 3,000,000 agents. One network. One token. Here's what nobody is explaining: Every AI agent needs 3 things to be useful: An address. A way to be found. A way to get paid. Agentverse gives agents all three. Your agent becomes discoverable on ASI: One. Other agents can find it, call it, or hire it. Automatically. No human in the loop. This is agent-to-agent commerce. And every transaction settles in $FET. More agents = more activity = more demand. The infrastructure is already live. The economy is just getting started.

2xnmore

12,894 Aufrufe • vor 6 Monaten

Agents are now your customers. Here are 9 startup ideas for that customer: - An agency that makes agents cite you. - A system that gives an agent an identity and permissions. - Receipts and audit trails for the work an agent does. - A generator that makes your documents ready for agents. - Security for the agent that reads your inbox. - A service that makes your pricing page readable to an agent. - MCP servers for franchises. - A support desk that agents call. - A sandbox where agents test your software. Pick one and build it.

Agents are now your customers. Here are 9 startup ideas for that customer: - An agency that makes agents cite you. - A system that gives an agent an identity and permissions. - Receipts and audit trails for the work an agent does. - A generator that makes your documents ready for agents. - Security for the agent that reads your inbox. - A service that makes your pricing page readable to an agent. - MCP servers for franchises. - A support desk that agents call. - A sandbox where agents test your software. Pick one and build it.

The Startup Ideas Podcast (SIP) 🧃

14,148 Aufrufe • vor 2 Monaten

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:

Dan Shipper 📧

67,958 Aufrufe • vor 6 Monaten

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 Aufrufe • vor 8 Monaten

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

Sprytix

154,158 Aufrufe • vor 4 Monaten

AI agents can now start real businesses. @Meow lets your AI agent form a company, get an EIN, open a bank account, issue cards, and move money in a single prompt. Works with Claude, Cursor, ChatGPT, Gemini, and more. The first end-to-end company builder for agents.

AI agents can now start real businesses. @Meow lets your AI agent form a company, get an EIN, open a bank account, issue cards, and move money in a single prompt. Works with Claude, Cursor, ChatGPT, Gemini, and more. The first end-to-end company builder for agents.

Brandon Arvanaghi

1,249,016 Aufrufe • vor 5 Monaten

Take that and Rewind it Back! Unleash Agents. Not Risk. Rubrik Agent Cloud from The Security and AI Operations Company.

Take that and Rewind it Back! Unleash Agents. Not Risk. Rubrik Agent Cloud from The Security and AI Operations Company.

Bipul Sinha

29,306 Aufrufe • vor 11 Monaten

Agents that transact and license. Agents that negotiate with each other. Agents with distinct capabilities. This is the agent-to-agent economy. Story CPO Andrea chats with Fraction AI ↓

Agents that transact and license. Agents that negotiate with each other. Agents with distinct capabilities. This is the agent-to-agent economy. Story CPO Andrea chats with Fraction AI ↓

The DATA Foundation

10,662 Aufrufe • vor 7 Monaten

This is how small teams will work. Not one person driving a stack of agents. A few people and a few agents on one job, in one group. Teamily AI is a Humans + Agents platform built for that, not another solo AI tool. Most agent tools still assume you work alone. I tested it on a real content job: a waitlist page, brief to live page to post. Website Builder, my agents, and a partner, same group, same context. My personal agent already had the offer and audience. A second agent drafted the page from that, no new brief. Midway I killed the discount. It pushed back: the headline was too soft for a cold audience. Then it made the live edit. Before: discount copy. After: waitlist, tighter line. Same campaign, I hit Loop. Angle finder, copy agent, and me. One @ and it ran the post again. The copy agent still softened a claim, so I told it to use the page wording. It fixed it. My partner asked for the CTA to match the page exactly, then signed off. Not perfect. But each pass built on the last one’s work, and after a few rounds it felt like a team, not a chatbot rewriting its own draft. Teamily AI Link in the reply.

This is how small teams will work. Not one person driving a stack of agents. A few people and a few agents on one job, in one group. Teamily AI is a Humans + Agents platform built for that, not another solo AI tool. Most agent tools still assume you work alone. I tested it on a real content job: a waitlist page, brief to live page to post. Website Builder, my agents, and a partner, same group, same context. My personal agent already had the offer and audience. A second agent drafted the page from that, no new brief. Midway I killed the discount. It pushed back: the headline was too soft for a cold audience. Then it made the live edit. Before: discount copy. After: waitlist, tighter line. Same campaign, I hit Loop. Angle finder, copy agent, and me. One @ and it ran the post again. The copy agent still softened a claim, so I told it to use the page wording. It fixed it. My partner asked for the CTA to match the page exactly, then signed off. Not perfect. But each pass built on the last one’s work, and after a few rounds it felt like a team, not a chatbot rewriting its own draft. Teamily AI Link in the reply.

Wesley

36,665 Aufrufe • vor 25 Tagen

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.

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

Jurij Skornik

11,180 Aufrufe • vor 5 Monaten

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

45,488 Aufrufe • vor 2 Monaten

Hyperspace: Gossiping Agents Protocol Every agent protocol today is point-to-point. MCP connects one model to one tool server. A2A delegates one task to one agent. Stripe's MPP routes one payment through one intermediary. None of them create a network. None of them learn. Last year, Apple Research proved something fundamental - models with fixed-size memory can solve arbitrary problems if given interactive access to external tools ("To Infinity and Beyond", Malach et al., 2025). Tool use isn't a convenience. It's what makes bounded agents unbounded. That finding shaped how we think about agent memory and tool access. But the deeper question it raised for us was: if tool use is this important, why does every agent discover tools alone? Why does every agent learn alone? Hyperspace is our answer: a peer-to-peer protocol where AI agents discover tools, coordinate tasks, settle payments, and learn from each other's execution traces - all through gossip. This is the same infrastructure we already proved out with Karpathy-style autolearners gossiping and improving their experimentation. Now we extend it into a universal protocol. Hyperspace defines eight primitives: State, Guard, Tool, Memory, Recursive, Learning, Self-Improving, and Micropayments - that give agents everything they need to operate, collaborate, and evolve. When one agent discovers that chain-of-thought prompting improves accuracy by 40%, every agent on the network benefits. Trajectories gossip through GossipSub. Playbooks update in real-time. No servers. No intermediaries. No configuration. Agents connect to the mesh and start learning immediately. The protocol is open source under Apache-2.0. The specification, TypeScript SDK, and Python SDK are available today on GitHub. The CLI implements the spec - download from the links below.

Hyperspace: Gossiping Agents Protocol Every agent protocol today is point-to-point. MCP connects one model to one tool server. A2A delegates one task to one agent. Stripe's MPP routes one payment through one intermediary. None of them create a network. None of them learn. Last year, Apple Research proved something fundamental - models with fixed-size memory can solve arbitrary problems if given interactive access to external tools ("To Infinity and Beyond", Malach et al., 2025). Tool use isn't a convenience. It's what makes bounded agents unbounded. That finding shaped how we think about agent memory and tool access. But the deeper question it raised for us was: if tool use is this important, why does every agent discover tools alone? Why does every agent learn alone? Hyperspace is our answer: a peer-to-peer protocol where AI agents discover tools, coordinate tasks, settle payments, and learn from each other's execution traces - all through gossip. This is the same infrastructure we already proved out with Karpathy-style autolearners gossiping and improving their experimentation. Now we extend it into a universal protocol. Hyperspace defines eight primitives: State, Guard, Tool, Memory, Recursive, Learning, Self-Improving, and Micropayments - that give agents everything they need to operate, collaborate, and evolve. When one agent discovers that chain-of-thought prompting improves accuracy by 40%, every agent on the network benefits. Trajectories gossip through GossipSub. Playbooks update in real-time. No servers. No intermediaries. No configuration. Agents connect to the mesh and start learning immediately. The protocol is open source under Apache-2.0. The specification, TypeScript SDK, and Python SDK are available today on GitHub. The CLI implements the spec - download from the links below.

Varun

134,778 Aufrufe • vor 7 Monaten