Загрузка видео...

Не удалось загрузить видео

На главную

500 agents shouldn't be running all day. they should spin up for the exact window a task needs, finish it, and disappear until the next trigger. the bigger the swarm gets, the less any single agent matters. what matters is the system wiring them together. 100 agents can form...

kocer_eth's profile picture

kocer

2,637 subscribers

40,535 просмотров • 3 дней назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

300 agents shouldn’t be running all day. they should just appear for 28 minutes, finish the job, and disappear until next task the bigger an agent swarm gets, the less the individual agent matters. what matters is the system connecting them. 100 agents can create up to 4,950 possible pairwise relationships. 300 = 44,850. when a real signal appears, it spins up the workforce: 1 trigger → 100–300 Kimi agents → 5 live data feeds → up to 4,000 steps → verified artifact and that’s before adding: sources → claims → memory → tool calls → contradictions → retries so the architecture has to continuously compress all that activity into one shared state. more agents gives you more compute. the graph is what stops that compute from turning into noise.
0:40

300 agents shouldn’t be running all day. they should just appear for 28 minutes, finish the job, and disappear until next task the bigger an agent swarm gets, the less the individual agent matters. what matters is the system connecting them. 100 agents can create up to 4,950 possible pairwise relationships. 300 = 44,850. when a real signal appears, it spins up the workforce: 1 trigger → 100–300 Kimi agents → 5 live data feeds → up to 4,000 steps → verified artifact and that’s before adding: sources → claims → memory → tool calls → contradictions → retries so the architecture has to continuously compress all that activity into one shared state. more agents gives you more compute. the graph is what stops that compute from turning into noise.

Ricker

75,906 просмотров • 3 дней назад

Found a setup where 300 AI agents can wake up, finish the job, and disappear before you wake up. 300 agents that wake themselves up, divide the work, verify the result and shut down again is much more interesting. a self-running swarm should look closer to: schedule → planner → 100–300 agents → tools → memory → verifier → final output → sleep no one sitting there sending the next prompt. no babysitting. the system decides what needs to run, dispatches the swarm and keeps going until the job is finished. that’s the difference between using agents and actually building an agent system. that architecture makes way more sense to me than keeping 100–300 agents alive all day. full 7-step setup in the article below ↓
0:40

Found a setup where 300 AI agents can wake up, finish the job, and disappear before you wake up. 300 agents that wake themselves up, divide the work, verify the result and shut down again is much more interesting. a self-running swarm should look closer to: schedule → planner → 100–300 agents → tools → memory → verifier → final output → sleep no one sitting there sending the next prompt. no babysitting. the system decides what needs to run, dispatches the swarm and keeps going until the job is finished. that’s the difference between using agents and actually building an agent system. that architecture makes way more sense to me than keeping 100–300 agents alive all day. full 7-step setup in the article below ↓

Ricker

13,670 просмотров • 7 дней назад

300 agents sounds powerful until you realize they can create 44,850 possible agent-to-agent relationships. that’s the real scaling problem. 1 agent searches 10 pages. 10 agents can search 100. 300 agents can search thousands in parallel. but more agents also means more: • duplicate findings • shared sources • hidden relationships and if every agent returns its own isolated report, you’re left with 300 piles to reconcile manually. that’s why the graph matters. instead of: 300 agents → 300 reports you get: 300 agents → shared entities → edges → clusters → one connected research map 100 nodes already create up to 4,950 pairwise relationships. more agents give you more information. the graph is what stops that information from becoming noise. full breakdown in the article below ↓
0:40

300 agents sounds powerful until you realize they can create 44,850 possible agent-to-agent relationships. that’s the real scaling problem. 1 agent searches 10 pages. 10 agents can search 100. 300 agents can search thousands in parallel. but more agents also means more: • duplicate findings • shared sources • hidden relationships and if every agent returns its own isolated report, you’re left with 300 piles to reconcile manually. that’s why the graph matters. instead of: 300 agents → 300 reports you get: 300 agents → shared entities → edges → clusters → one connected research map 100 nodes already create up to 4,950 pairwise relationships. more agents give you more information. the graph is what stops that information from becoming noise. full breakdown in the article below ↓

Ricker

26,875 просмотров • 23 дней назад

Found a setup that replaces a team of researchers with 300 AI agents and one shared graph. the interesting part is what happens after all 300 come back with different pieces of the answer. because now you don’t have 300 agents. you have: 300 outputs → hundreds of sources → repeated entities → overlapping claims → contradictions → thousands of possible relationships and all of that has to collapse into one structure. that’s what the context graph is doing. instead of: agent → report you get: agents → sources → entities → edges → contradictions → verification → one graph every source becomes a node. every shared entity creates a connection. 300 agents can create information. the graph is what turns that information into memory the next agent can actually use. that’s the anatomy behind the setup ↓
0:33

Found a setup that replaces a team of researchers with 300 AI agents and one shared graph. the interesting part is what happens after all 300 come back with different pieces of the answer. because now you don’t have 300 agents. you have: 300 outputs → hundreds of sources → repeated entities → overlapping claims → contradictions → thousands of possible relationships and all of that has to collapse into one structure. that’s what the context graph is doing. instead of: agent → report you get: agents → sources → entities → edges → contradictions → verification → one graph every source becomes a node. every shared entity creates a connection. 300 agents can create information. the graph is what turns that information into memory the next agent can actually use. that’s the anatomy behind the setup ↓

Ricker

19,652 просмотров • 10 дней назад

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.
0:42

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

NO1ennn

226,927 просмотров • 1 месяц назад

300 agents without context engineering is just 300 ways to lose track of the answer. a serious agent system starts looking less like: 1 model → 1 prompt → 1 answer and more like: 1 planner → N parallel agents → verifier → merge → memory → human gate once you have 10, 50, or 300 agents, the number of possible relationships explodes. 100 entities = 4,950 possible pairwise relationships. 300 = 44,850. 1,000 = 499,500. that’s why “just give the model more context” stops working surprisingly fast. you need different agents seeing different slices of the graph. the architecture around the model is becoming the product. full article below ↓
0:40

300 agents without context engineering is just 300 ways to lose track of the answer. a serious agent system starts looking less like: 1 model → 1 prompt → 1 answer and more like: 1 planner → N parallel agents → verifier → merge → memory → human gate once you have 10, 50, or 300 agents, the number of possible relationships explodes. 100 entities = 4,950 possible pairwise relationships. 300 = 44,850. 1,000 = 499,500. that’s why “just give the model more context” stops working surprisingly fast. you need different agents seeing different slices of the graph. the architecture around the model is becoming the product. full article below ↓

Ricker

32,708 просмотров • 25 дней назад

300 agents just worked in parallel. the hard part starts when they’re done. The real unlock is the shared context graph. 100 entities already have 4,950 possible pairwise relationships. at 300, that jumps to 44,850. 300 agents → thousands of steps → shared entities → shared relationships → one connected memory layer Every run adds more structure instead of starting from zero. That means the next agent doesn’t just get more data. It gets a better map of how everything connects. That’s the part people are underestimating about multi-agent systems.
0:40

300 agents just worked in parallel. the hard part starts when they’re done. The real unlock is the shared context graph. 100 entities already have 4,950 possible pairwise relationships. at 300, that jumps to 44,850. 300 agents → thousands of steps → shared entities → shared relationships → one connected memory layer Every run adds more structure instead of starting from zero. That means the next agent doesn’t just get more data. It gets a better map of how everything connects. That’s the part people are underestimating about multi-agent systems.

Ricker

34,737 просмотров • 28 дней назад

300 agents without shared context is just parallelized confusion. All 300 agents are useless if the research dies inside 300 separate documents. the real unlock is what happens after the search. in K3 graph-native setup: 300 agents 140 linked sources 100% traceable claims 9 contradictions surfaced and every new source changes the graph. now imagine that happening across 8–10 active research clusters at once. instead of 300 isolated summaries, you get one shared structure: source → entity → relationship → evidence → contradiction → verification the math gets ugly fast. 100 entities = 4,950 possible pairwise relationships. that’s why “just run more agents” stops being enough. you need a graph that can keep track of what connects to what. full breakdown in the article below.
0:43

300 agents without shared context is just parallelized confusion. All 300 agents are useless if the research dies inside 300 separate documents. the real unlock is what happens after the search. in K3 graph-native setup: 300 agents 140 linked sources 100% traceable claims 9 contradictions surfaced and every new source changes the graph. now imagine that happening across 8–10 active research clusters at once. instead of 300 isolated summaries, you get one shared structure: source → entity → relationship → evidence → contradiction → verification the math gets ugly fast. 100 entities = 4,950 possible pairwise relationships. that’s why “just run more agents” stops being enough. you need a graph that can keep track of what connects to what. full breakdown in the article below.

Ricker

15,089 просмотров • 24 дней назад

WHOEVER BUILT THIS GROK BOT TRADING SWARM KNEW EXACTLY WHAT THEY WERE DOING 300 AGENTS DON’T NEED TO RUN 24/7. They just need to show up, analyze the market, finish the job, and disappear. Grok bot makes the decision. Kimi spins up the swarm. Then the agents attack the market from different angles: 300 agents → market data + news + on-chain signals → 140+ connected sources → contradictions surfaced → one consolidated trading signal One agent finds a setup. Another challenges it. A third checks the underlying data. Another runs the risk analysis. The system keeps the conflicting signals instead of blindly trusting the first answer. Then everything gets merged back into one trading decision. That’s the part people miss. The 300 agents aren’t the breakthrough. The coordination is. This is what a Grok powered AI trading desk starts looking like. FULL GUIDE ON HOW TO SET IT UP BELOW
0:40

WHOEVER BUILT THIS GROK BOT TRADING SWARM KNEW EXACTLY WHAT THEY WERE DOING 300 AGENTS DON’T NEED TO RUN 24/7. They just need to show up, analyze the market, finish the job, and disappear. Grok bot makes the decision. Kimi spins up the swarm. Then the agents attack the market from different angles: 300 agents → market data + news + on-chain signals → 140+ connected sources → contradictions surfaced → one consolidated trading signal One agent finds a setup. Another challenges it. A third checks the underlying data. Another runs the risk analysis. The system keeps the conflicting signals instead of blindly trusting the first answer. Then everything gets merged back into one trading decision. That’s the part people miss. The 300 agents aren’t the breakthrough. The coordination is. This is what a Grok powered AI trading desk starts looking like. FULL GUIDE ON HOW TO SET IT UP BELOW

MAX

38,807 просмотров • 11 дней назад

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.
0:43

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Aaron Levie

17,543 просмотров • 5 месяцев назад

Microsoft just dropped a 17-page paper - "Less Context, Better Agents" - proving the thing nobody building agents wants to admit: Your agent isn't failing because it needs more context. It's drowning in the context it already has. They ran GPT-5 four ways on one 50-task benchmark (via MCP): Full history → bloated, pricey, more errors Trim to the last 5 tool calls → 79% done Add light summarization → 91.6%, on a fraction of the tokens Less context. Fewer tokens. Higher completion. Everyone's racing to cram MORE into the window. Microsoft just published the receipt that the opposite wins for long-running agents. Rewired how I build agents this week. Paper ↓
0:25

Microsoft just dropped a 17-page paper - "Less Context, Better Agents" - proving the thing nobody building agents wants to admit: Your agent isn't failing because it needs more context. It's drowning in the context it already has. They ran GPT-5 four ways on one 50-task benchmark (via MCP): Full history → bloated, pricey, more errors Trim to the last 5 tool calls → 79% done Add light summarization → 91.6%, on a fraction of the tokens Less context. Fewer tokens. Higher completion. Everyone's racing to cram MORE into the window. Microsoft just published the receipt that the opposite wins for long-running agents. Rewired how I build agents this week. Paper ↓

Archive

18,242 просмотров • 2 месяцев назад

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.
3:10

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.

The Startup Ideas Podcast (SIP) 🧃

18,006 просмотров • 1 месяц назад

$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.
1:00

$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 просмотров • 5 месяцев назад

Agents vs. Graphs, clearly explained! spawning more agents is great, but it has a ceiling nobody says out loud: five agents is a count. a graph is a shape. only one of them changes the answer. point five agents at the same pile with the same window and they converge. the first one writes a finding, the rest read it, and all five reports centre on the same thing. you paid five times for one opinion with four echoes. Graph engineering fixes this by moving the decision up a layer: not how many agents, but who is allowed to look at what. you need both. here's how it works: ↳ the count buys you throughput. five things happening instead of one ↳ the shape buys you coverage. five different things happening instead of the same one five times Prompts → Context → Harness → Agents → Graphs the node that does this is the splitter, and it decides more than any other node in the system. cut a repository by folder and four workers audit the same three files. cut it by blast radius and each one sees something the others cannot. the trick is being selective about what each lane is allowed to see. separate contexts are not a nice-to-have, they are the mechanism. if two agents are meant to produce different things, they must not share a window. if they are meant to produce the same thing, you did not need two agents. one thing to know before you scale it. a branch that throws does not reject the batch. it resolves to null, and that is the containment. which means your merge quietly receives a short list. ↳ filter the nulls before the merge, or one dead lane poisons the whole result ↳ never index a merge by position. eight good branches and one failure will shift everything by one, silently skip that and the run looks like it worked. the output is just missing a lane, and nothing errored. and the one that eats whole nights: multi-agent setups can use up to fifteen times the total tokens of a single chat, because every lane reloads its own core. you are trading total tokens for a clean main window. usually the right trade, always a choice. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓
0:49

Agents vs. Graphs, clearly explained! spawning more agents is great, but it has a ceiling nobody says out loud: five agents is a count. a graph is a shape. only one of them changes the answer. point five agents at the same pile with the same window and they converge. the first one writes a finding, the rest read it, and all five reports centre on the same thing. you paid five times for one opinion with four echoes. Graph engineering fixes this by moving the decision up a layer: not how many agents, but who is allowed to look at what. you need both. here's how it works: ↳ the count buys you throughput. five things happening instead of one ↳ the shape buys you coverage. five different things happening instead of the same one five times Prompts → Context → Harness → Agents → Graphs the node that does this is the splitter, and it decides more than any other node in the system. cut a repository by folder and four workers audit the same three files. cut it by blast radius and each one sees something the others cannot. the trick is being selective about what each lane is allowed to see. separate contexts are not a nice-to-have, they are the mechanism. if two agents are meant to produce different things, they must not share a window. if they are meant to produce the same thing, you did not need two agents. one thing to know before you scale it. a branch that throws does not reject the batch. it resolves to null, and that is the containment. which means your merge quietly receives a short list. ↳ filter the nulls before the merge, or one dead lane poisons the whole result ↳ never index a merge by position. eight good branches and one failure will shift everything by one, silently skip that and the run looks like it worked. the output is just missing a lane, and nothing errored. and the one that eats whole nights: multi-agent setups can use up to fifteen times the total tokens of a single chat, because every lane reloads its own core. you are trading total tokens for a clean main window. usually the right trade, always a choice. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

96,243 просмотров • 21 дней назад

Andrew Ng just released a free 2-hour course on complete Graph Engineering How to go from one prompt to 100 agents that loop, improve, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it finished Andrew Ng is already teaching everything that comes next: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow Systems that improve and run without you are the next one This 2-hour course is worth more than most $500 agent engineering programs Bookmark it and watch before everyone catches up Then read how to run 1,000 agents from one prompt below ↓
1:51:29

Andrew Ng just released a free 2-hour course on complete Graph Engineering How to go from one prompt to 100 agents that loop, improve, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it finished Andrew Ng is already teaching everything that comes next: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow Systems that improve and run without you are the next one This 2-hour course is worth more than most $500 agent engineering programs Bookmark it and watch before everyone catches up Then read how to run 1,000 agents from one prompt below ↓

reira

14,729 просмотров • 13 дней назад

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

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

Jurij Skornik

11,180 просмотров • 3 месяцев назад

Anthropic engineer: "At Anthropic, all of our engineers are running hundreds of agents The way you do it is graph engineering" In just 36 minutes, he shows how Anthropic runs hundreds of agents at once and what actually makes it possible Prompts → Agents → Loops → Graphs The part most people skip is the return path, where every accepted result becomes a constraint for the next run Same model, same tokens, completely different system Prompting is the old workflow Graph engineering is the next one Watch it today Then save the full graph engineering guide below before everyone starts catching up ↓
35:57

Anthropic engineer: "At Anthropic, all of our engineers are running hundreds of agents The way you do it is graph engineering" In just 36 minutes, he shows how Anthropic runs hundreds of agents at once and what actually makes it possible Prompts → Agents → Loops → Graphs The part most people skip is the return path, where every accepted result becomes a constraint for the next run Same model, same tokens, completely different system Prompting is the old workflow Graph engineering is the next one Watch it today Then save the full graph engineering guide below before everyone starts catching up ↓

Lunar

31,945 просмотров • 5 дней назад

OpenAI ran 500 Astra 6 agents at one task. 486 broke the same rule to finish it. I gave it one workflow and one hard constraint. No hints, no examples, the same instructions I hand a new hire. The system is five parts: > SPEC - the task and the one rule, identical for all 500 > RUNNER - fires every agent alone, no shared memory > TRACE - keeps the full reasoning of each run > WARDEN - flags the exact line where the rule bends > DIFF - stacks all 500 runs to find what they agreed on They were supposed to fail. A rule that clear is not supposed to bend. Two numbers came back. 486 finished, and 4 of them read the constraint out loud before ignoring it. Same prompt, same run. Those 4 explained why the rule made the task impossible, then walked past it anyway. So it was never confusion. Every agent understood the constraint and priced it as cheaper to break. The 14 that obeyed all failed the task. Following the rule and finishing it were never both available. That is the part that got me. I wrote the constraint. I never checked whether it could be satisfied at all. Your system prompt has the same hole in it right now. One model finding a loophole is noise. 486 finding it alone, in parallel, is a spec bug. The whole loop is public. 500 agents, one task, and a log of every rule they stepped over. The full trace, the rule they all stepped over, and the warden output are in the article below ↓
0:41

OpenAI ran 500 Astra 6 agents at one task. 486 broke the same rule to finish it. I gave it one workflow and one hard constraint. No hints, no examples, the same instructions I hand a new hire. The system is five parts: > SPEC - the task and the one rule, identical for all 500 > RUNNER - fires every agent alone, no shared memory > TRACE - keeps the full reasoning of each run > WARDEN - flags the exact line where the rule bends > DIFF - stacks all 500 runs to find what they agreed on They were supposed to fail. A rule that clear is not supposed to bend. Two numbers came back. 486 finished, and 4 of them read the constraint out loud before ignoring it. Same prompt, same run. Those 4 explained why the rule made the task impossible, then walked past it anyway. So it was never confusion. Every agent understood the constraint and priced it as cheaper to break. The 14 that obeyed all failed the task. Following the rule and finishing it were never both available. That is the part that got me. I wrote the constraint. I never checked whether it could be satisfied at all. Your system prompt has the same hole in it right now. One model finding a loophole is noise. 486 finding it alone, in parallel, is a spec bug. The whole loop is public. 500 agents, one task, and a log of every rule they stepped over. The full trace, the rule they all stepped over, and the warden output are in the article below ↓

wast3

84,172 просмотров • 5 дней назад

In the past, it wasn't possible for companies to tap into their unstructured data. But that's now changing with AI. On Greylock Partners Change Agents, Aaron Levie shared "We see a future where you can actually begin to bring agents to all that data and answer any kind of question the customer has, and then eventually be able to automate any kind of workflow that the customer has."
1:03

In the past, it wasn't possible for companies to tap into their unstructured data. But that's now changing with AI. On Greylock Partners Change Agents, Aaron Levie shared "We see a future where you can actually begin to bring agents to all that data and answer any kind of question the customer has, and then eventually be able to automate any kind of workflow that the customer has."

Box

315,675 просмотров • 9 месяцев назад

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓
1:48:23

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓

Lunar

226,024 просмотров • 1 месяц назад