正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

context engineering vs graph engineering. every few months the list gets a new word and everyone treats it as a replacement for the last one. these two are not on the same list. one decides what the model sees this turn, the other decides what exists at all. the... cleanest way to tell them apart is to ask what a single unit of work looks like. > context engineering is the window the window opens empty, every single time. you assemble what goes in it. the prompt, the docs, the history, the tool results. the assembling is the work. the window only grows. it never shrinks on its own, so eventually something gets dropped. usually from the middle. usually without telling you. then the turn ends and the window is thrown away. not archived, thrown away. the next turn opens empty again and you re-explain what you already explained. good context engineering is knowing what to leave out, not what to pack in. the unit of work is one window. > graph engineering is the structure the same material arrives from the same sources. instead of packing it into a window, you pull entities out of it, resolve the duplicates into one node, and write typed edges between them. nothing here is stored as text you hope to find again. it is stored as a thing with a name and its connections to other things. when the turn ends, the graph is still there. the next turn does not start from zero. it starts by querying what already exists, and the query walks edges instead of guessing at similarity. good graph engineering is deciding what counts as the same thing twice. the unit of work is one relationship. > they are not alternatives the graph is what refills the window. context engineering decides what fits. graph engineering decides what there is to choose from. remove the graph and every session starts blind. remove the context work and the best structure in the world arrives as an unreadable dump. that also tells you which one broke. the answer drifted from what you actually said, or forgot something from this same session. that is the window. the answer is coherent but invents a connection that does not exist, or cannot join two facts it has clearly seen. that is the structure. people debug the prompt because the prompt is the easiest thing to edit. it keeps taking the blame for failures that live a layer down. save this - then read the full breakdown belowshow more

Hanako

13,480 subscribers

19,160 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Context vs. Graphs, clearly explained! context engineering is great, but it has a ceiling: you can make one window perfect. there is still only one of it. every technique on that layer is rationing the same scarce thing. compact, retrieve less, delete, defer. all of it is deciding what to drop. Graph engineering fixes this by moving the decision up a layer: not what goes in the window, but how many windows there are and what each one is for. you need both. here's how it works: ↳ inside a window: context engineering. what loads, in what order, what gets compacted ↳ between windows: the graph. how many lanes, what each one is allowed to see, what comes back Prompts → Context → Harness → Loops → Graphs each lane gets a clean window, nothing in one competes with anything in another, and your main thread stops filling up. the trick is being selective about what comes back. a subagent reads six thousand tokens of files and hands you a four hundred token summary. that ratio is the whole point. send back the raw material instead and you have moved the problem, not solved it. one thing to know before you scale it. not everything survives compaction equally, and almost nobody knows the table. ↳ the project-root rules file and auto memory are re-injected from disk. they come back intact ↳ path-scoped rules and nested rules files live in message history. they get summarized away and do not return until a matching file is read again so a rule that genuinely must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: shared context makes parallel agents converge. four auditors on one window produce one opinion with three echoes. you paid four times for it. 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 ↓

Context vs. Graphs, clearly explained! context engineering is great, but it has a ceiling: you can make one window perfect. there is still only one of it. every technique on that layer is rationing the same scarce thing. compact, retrieve less, delete, defer. all of it is deciding what to drop. Graph engineering fixes this by moving the decision up a layer: not what goes in the window, but how many windows there are and what each one is for. you need both. here's how it works: ↳ inside a window: context engineering. what loads, in what order, what gets compacted ↳ between windows: the graph. how many lanes, what each one is allowed to see, what comes back Prompts → Context → Harness → Loops → Graphs each lane gets a clean window, nothing in one competes with anything in another, and your main thread stops filling up. the trick is being selective about what comes back. a subagent reads six thousand tokens of files and hands you a four hundred token summary. that ratio is the whole point. send back the raw material instead and you have moved the problem, not solved it. one thing to know before you scale it. not everything survives compaction equally, and almost nobody knows the table. ↳ the project-root rules file and auto memory are re-injected from disk. they come back intact ↳ path-scoped rules and nested rules files live in message history. they get summarized away and do not return until a matching file is read again so a rule that genuinely must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: shared context makes parallel agents converge. four auditors on one window produce one opinion with three echoes. you paid four times for it. 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

36,970 次观看 • 2 个月前

FIVE LAYERS OF AGENT ENGINEERING, EACH ONE WRAPS THE ONE BELOW IT. IF YOU SKIP LAYER 2, YOUR LAYER 5 WILL LOOK BROKEN WHEN IT IS ACTUALLY JUST STANDING ON NOTHING. for weeks i debated harness vs loop vs graph like they were competing choices. then a stack diagram made the shape obvious. they are not choices. they are floors. 01 | prompt engineering. the message. unit of work: one input. inputs are role, instructions, examples, format. output is a single raw response. 02 | context engineering. the memory. unit of work: what stays in the window. a curator selects, compresses, and drops from query, docs, memory, prior turns, and tool outputs before the prompt runs. 03 | harness engineering. the machine. unit of work: the machine itself. gather (context + prompt) → LLM → tools or sub-agents → verifier → final response. the article calls this the operating environment. 04 | loop engineering. the system. unit of work: the run. goal + success criteria + max iterations + budget + completion check wrap around one harness pass. failed pass appends results to context and retries. 05 | graph engineering. the topology. unit of work: the graph run. goal + nodes + edges + state schema. graph routes to agent nodes, tool nodes, or human approval. a reviewer node with a different model and fresh context checks the final answer. the wrapping is the whole point. layer 5 assumes layer 4 works. layer 4 assumes layer 3 works. skip layer 2 and layer 3's verifier keeps failing without a clear reason. this is why swapping the model is a one-day project and swapping the stack is a quarter. the model is the commodity. the five layers around it are the engineering. full three-layer breakdown of the top of the stack (harness, loop, graph) in the post below.

FIVE LAYERS OF AGENT ENGINEERING, EACH ONE WRAPS THE ONE BELOW IT. IF YOU SKIP LAYER 2, YOUR LAYER 5 WILL LOOK BROKEN WHEN IT IS ACTUALLY JUST STANDING ON NOTHING. for weeks i debated harness vs loop vs graph like they were competing choices. then a stack diagram made the shape obvious. they are not choices. they are floors. 01 | prompt engineering. the message. unit of work: one input. inputs are role, instructions, examples, format. output is a single raw response. 02 | context engineering. the memory. unit of work: what stays in the window. a curator selects, compresses, and drops from query, docs, memory, prior turns, and tool outputs before the prompt runs. 03 | harness engineering. the machine. unit of work: the machine itself. gather (context + prompt) → LLM → tools or sub-agents → verifier → final response. the article calls this the operating environment. 04 | loop engineering. the system. unit of work: the run. goal + success criteria + max iterations + budget + completion check wrap around one harness pass. failed pass appends results to context and retries. 05 | graph engineering. the topology. unit of work: the graph run. goal + nodes + edges + state schema. graph routes to agent nodes, tool nodes, or human approval. a reviewer node with a different model and fresh context checks the final answer. the wrapping is the whole point. layer 5 assumes layer 4 works. layer 4 assumes layer 3 works. skip layer 2 and layer 3's verifier keeps failing without a clear reason. this is why swapping the model is a one-day project and swapping the stack is a quarter. the model is the commodity. the five layers around it are the engineering. full three-layer breakdown of the top of the stack (harness, loop, graph) in the post below.

kocer

31,198 次观看 • 2 个月前

Most people lump prompt engineering, context engineering, and graph engineering together. Here's the simple breakdown: - Prompt engineering: how you ask the AI a better question. - Context engineering: how you give the AI better information. - Graph engineering: how you design the work around the AI so it stops living inside one giant chat. Example: researching a startup idea. The chat way: - One model, one pass. - It decides what matters - Researches the market - Interprets the evidence - Writes the recommendation - Grades its own confidence. The graph way: - A planner breaks the question into angles - 5 researchers split up: customer, competitors, distribution, pricing, risks - A skeptic tries to kill the weak findings - A merger turns what survives into a one-page recommendation - You approve before you act Same written report. Completely different work behind it. Think: - Prompt = the question - Context = the information - Graph = the workflow Design the workflow. That's where it clicks.

Most people lump prompt engineering, context engineering, and graph engineering together. Here's the simple breakdown: - Prompt engineering: how you ask the AI a better question. - Context engineering: how you give the AI better information. - Graph engineering: how you design the work around the AI so it stops living inside one giant chat. Example: researching a startup idea. The chat way: - One model, one pass. - It decides what matters - Researches the market - Interprets the evidence - Writes the recommendation - Grades its own confidence. The graph way: - A planner breaks the question into angles - 5 researchers split up: customer, competitors, distribution, pricing, risks - A skeptic tries to kill the weak findings - A merger turns what survives into a one-page recommendation - You approve before you act Same written report. Completely different work behind it. Think: - Prompt = the question - Context = the information - Graph = the workflow Design the workflow. That's where it clicks.

The Startup Ideas Podcast (SIP) 🧃

19,232 次观看 • 3 个月前

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 ↓

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

97,154 次观看 • 2 个月前

Workflows vs. Graphs, clearly explained! workflows are great, and almost everyone has one. here is the ceiling: a workflow decides every step before it runs. you drew eight boxes in March. six months later the same three fire, every single time, and the other five have never once been reached. then a case arrives that nobody drew, and it goes to the closest wrong box. quietly, with a green status, because from the inside that looks exactly like success. Graph engineering fixes this by moving the decision: not what the steps do, but when the steps get chosen. you need both, and here is the sentence that resolves the whole confusion: a workflow decides the steps before it runs. a graph decides them while it runs. ↳ drawn in advance: the boxes, the branches, the order, the error path ↳ decided at runtime: how many units exist, what each one is allowed to see, which ones get created at all Prompts → Context → Harness → Loops → Graphs branches do not make it a graph. the branches were drawn in advance too, which means every one of them is a case you already thought of. the trick is knowing which part is allowed to be fixed. the node kinds are fixed. a splitter is a splitter, a gate is a gate, a merge is code. what is not fixed is how many of them exist this run, and that is decided after something has been read. one thing to know before you scale it. a workflow fails in a way that never pages anyone. ↳ the wrong branch ran, every check inside it passed, and the output is well formed ↳ nothing errored, because routing to the wrong box is not an error, it is a route that last one catches careful people. you cannot test your way out of it either, because the test suite was written from the same diagram that has the gap in it. and the one that eats whole nights: a workflow that has never surprised you is not stable, it is narrow. if it has run four hundred times and produced the same three shapes, it is not handling your work. it is handling the part of your work that fits it, and you have quietly stopped sending it the rest. 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 ↓

Workflows vs. Graphs, clearly explained! workflows are great, and almost everyone has one. here is the ceiling: a workflow decides every step before it runs. you drew eight boxes in March. six months later the same three fire, every single time, and the other five have never once been reached. then a case arrives that nobody drew, and it goes to the closest wrong box. quietly, with a green status, because from the inside that looks exactly like success. Graph engineering fixes this by moving the decision: not what the steps do, but when the steps get chosen. you need both, and here is the sentence that resolves the whole confusion: a workflow decides the steps before it runs. a graph decides them while it runs. ↳ drawn in advance: the boxes, the branches, the order, the error path ↳ decided at runtime: how many units exist, what each one is allowed to see, which ones get created at all Prompts → Context → Harness → Loops → Graphs branches do not make it a graph. the branches were drawn in advance too, which means every one of them is a case you already thought of. the trick is knowing which part is allowed to be fixed. the node kinds are fixed. a splitter is a splitter, a gate is a gate, a merge is code. what is not fixed is how many of them exist this run, and that is decided after something has been read. one thing to know before you scale it. a workflow fails in a way that never pages anyone. ↳ the wrong branch ran, every check inside it passed, and the output is well formed ↳ nothing errored, because routing to the wrong box is not an error, it is a route that last one catches careful people. you cannot test your way out of it either, because the test suite was written from the same diagram that has the gap in it. and the one that eats whole nights: a workflow that has never surprised you is not stable, it is narrow. if it has run four hundred times and produced the same three shapes, it is not handling your work. it is handling the part of your work that fits it, and you have quietly stopped sending it the rest. 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

16,810 次观看 • 1 个月前

Orchestrators vs. Graphs, clearly explained! orchestrators are great, and everyone builds one first. here is the ceiling: an orchestrator sits above the work and routes every message. five agents report to it. it reads all five. it decides what each one does next, and reads all five replies. that is ten trips through one context, and by the fifth agent that context has read four reports, five instructions and its own reasoning about all of them. Graph engineering fixes this by removing the seat: not a better router, but no router at all. you need both, and here is the sentence that resolves the whole confusion: an orchestrator sits above the work and holds all of it. a graph is the shape of the work, and holds none of it. ↳ above the work: one context that has to see everything before anything ships ↳ inside the work: a splitter that hands out and lets go, and a merge that reads nothing Prompts → Context → Harness → Loops → Graphs the coordination did not disappear. it moved into the edges, where it costs nothing and cannot get tired. the trick is noticing what you actually built. if one node has to see every result before the run can finish, you did not remove the bottleneck. you hired it, gave it the longest context in the system, and made it the thing you were counting on to stay sharp. one thing to know before you scale it. an orchestrator degrades in the one way nothing catches. ↳ it does not crash, time out or return an error. it stays up and keeps routing ↳ it just starts routing worse, somewhere around the fifth report, and every downstream agent does exactly what it was told that last one catches careful people. you can have perfect isolation on every worker and still have one window quietly drifting at the top, and the traces will all look clean because each worker did its job. and the one that eats whole nights: the merge is where this shows up first. ranking five findings is not judgment, it is a sort. if a model is doing it, you are paying a model to read five reports so it can put them in an order that three lines of code would have got right, and now that model has read everything too. 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 ↓

Orchestrators vs. Graphs, clearly explained! orchestrators are great, and everyone builds one first. here is the ceiling: an orchestrator sits above the work and routes every message. five agents report to it. it reads all five. it decides what each one does next, and reads all five replies. that is ten trips through one context, and by the fifth agent that context has read four reports, five instructions and its own reasoning about all of them. Graph engineering fixes this by removing the seat: not a better router, but no router at all. you need both, and here is the sentence that resolves the whole confusion: an orchestrator sits above the work and holds all of it. a graph is the shape of the work, and holds none of it. ↳ above the work: one context that has to see everything before anything ships ↳ inside the work: a splitter that hands out and lets go, and a merge that reads nothing Prompts → Context → Harness → Loops → Graphs the coordination did not disappear. it moved into the edges, where it costs nothing and cannot get tired. the trick is noticing what you actually built. if one node has to see every result before the run can finish, you did not remove the bottleneck. you hired it, gave it the longest context in the system, and made it the thing you were counting on to stay sharp. one thing to know before you scale it. an orchestrator degrades in the one way nothing catches. ↳ it does not crash, time out or return an error. it stays up and keeps routing ↳ it just starts routing worse, somewhere around the fifth report, and every downstream agent does exactly what it was told that last one catches careful people. you can have perfect isolation on every worker and still have one window quietly drifting at the top, and the traces will all look clean because each worker did its job. and the one that eats whole nights: the merge is where this shows up first. ranking five findings is not judgment, it is a sort. if a model is doing it, you are paying a model to read five reports so it can put them in an order that three lines of code would have got right, and now that model has read everything too. 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

44,226 次观看 • 1 个月前

your agent reviewing its own work is not a check. it is a second opinion from the same source. this is the most common gap in agent systems and it hides in plain sight, because the step exists. there is a review. it just cannot do the thing you think it does. here is the mechanism. the model produced an output from a context. you then ask the same model, holding the same context, whether that output is correct. it answers fluently, because that is what it does. and the answer is drawn from the same distribution that produced the thing being judged. same weights, same window, same blind spots. if the reason the output is wrong is something the model does not know, the review does not know it either. if the reason is something the context does not contain, the review has the same context. the failure mode and the detector share a cause. > why it feels like it works because most of the time the output is fine, and the review says fine. agreement is not evidence of detection. a reviewer that says pass on everything agrees with reality most of the time too. what you actually want to measure is what happens on the cases that are wrong. that is the only place a check earns its name, and it is exactly the place where a self-review is weakest. there is research on this. Huang and colleagues at DeepMind showed at ICLR 2024 that intrinsic self-correction, revising without external grounding, does not reliably help and often makes things worse. > what to actually do move the check outside the model. a test that runs, a schema that validates, a file that exists or does not, an exit code from something you did not write. these are not smarter than the model. they are just not correlated with it, and that is the entire value. when the judgement genuinely needs a model, at minimum use a different family. same family means shared blind spots, and frontier judges measurably inflate scores for outputs that look like their own. and split the work by kind. anything objectively checkable goes to code. only the genuinely semantic calls go to a judge, and those get a rubric written as one line. a review inside the loop tells you the model is confident. a check outside it tells you whether the work is done. save this - then read the eval setup below

your agent reviewing its own work is not a check. it is a second opinion from the same source. this is the most common gap in agent systems and it hides in plain sight, because the step exists. there is a review. it just cannot do the thing you think it does. here is the mechanism. the model produced an output from a context. you then ask the same model, holding the same context, whether that output is correct. it answers fluently, because that is what it does. and the answer is drawn from the same distribution that produced the thing being judged. same weights, same window, same blind spots. if the reason the output is wrong is something the model does not know, the review does not know it either. if the reason is something the context does not contain, the review has the same context. the failure mode and the detector share a cause. > why it feels like it works because most of the time the output is fine, and the review says fine. agreement is not evidence of detection. a reviewer that says pass on everything agrees with reality most of the time too. what you actually want to measure is what happens on the cases that are wrong. that is the only place a check earns its name, and it is exactly the place where a self-review is weakest. there is research on this. Huang and colleagues at DeepMind showed at ICLR 2024 that intrinsic self-correction, revising without external grounding, does not reliably help and often makes things worse. > what to actually do move the check outside the model. a test that runs, a schema that validates, a file that exists or does not, an exit code from something you did not write. these are not smarter than the model. they are just not correlated with it, and that is the entire value. when the judgement genuinely needs a model, at minimum use a different family. same family means shared blind spots, and frontier judges measurably inflate scores for outputs that look like their own. and split the work by kind. anything objectively checkable goes to code. only the genuinely semantic calls go to a judge, and those get a rubric written as one line. a review inside the loop tells you the model is confident. a check outside it tells you whether the work is done. save this - then read the eval setup below

Hanako

14,325 次观看 • 3 个月前

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 ↓

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

32,987 次观看 • 2 个月前

A Korean developer just explained the jump from Prompt Engineering to Graph Engineering better than anyone. Bookmark this guide, most people are still building agents the way that's about to be obsolete. > Prompt, Context, Loop, Graph: each stage fixes what the last couldn't > a loop plans, acts, observes, and revises until the work is done > a graph stops running one loop and orchestrates many with structure > most people camp at Prompt and Context, then wonder why their agents break the punchline: it was never about a better prompt. it's whether you moved up to loops and graphs or got stuck typing. I broke the same architecture down with Kimi K3. full guide, From Loops to Graphs, below

A Korean developer just explained the jump from Prompt Engineering to Graph Engineering better than anyone. Bookmark this guide, most people are still building agents the way that's about to be obsolete. > Prompt, Context, Loop, Graph: each stage fixes what the last couldn't > a loop plans, acts, observes, and revises until the work is done > a graph stops running one loop and orchestrates many with structure > most people camp at Prompt and Context, then wonder why their agents break the punchline: it was never about a better prompt. it's whether you moved up to loops and graphs or got stuck typing. I broke the same architecture down with Kimi K3. full guide, From Loops to Graphs, below

Kirill

39,068 次观看 • 2 个月前

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite

elune

16,875 次观看 • 3 个月前

Harness vs. Graphs, clearly explained! a harness is great, and most people think it is the whole thing: retries, timeouts, a sandbox, a log, the context it assembles before every call. all of that is real work, and all of it wraps exactly one call. run it a hundred times and you have one call, made very safely, a hundred times. Graph engineering fixes this by moving the decision up a layer: not how safely one call is made, but which calls exist to be made at all. you need both, and here is the sentence that resolves the whole confusion: the harness is everything around one call. the graph is everything between them. ↳ around one call: retry, timeout, sandbox, log, assemble the context, hand back a result ↳ between calls: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the harness does not go away when you build a graph. it moves under each node, and now there are five of them, each wrapping a call you would never have made by hand. the trick is knowing which layer a failure belongs to. turn a piece off and run it again. if the call still works, it was the harness. if the wrong step runs at all, it was the graph. people spend weeks hardening a harness around a node that should not have existed. one thing to know before you scale it. most of what people call their agent is a harness with a chat box on it. ↳ it retries, it times out, it logs, it assembles context, it holds one call up beautifully ↳ it has never once decided that a second call should exist, and that is the entire difference that last one catches careful people. a harness that never fails is not evidence the system is right. it is evidence one call went well, which is the smallest possible claim. and the one that eats whole nights: a harness cannot save you from the wrong step running. you can retry a bad decision three times with a clean log and perfect isolation, and all you bought was three copies of it. 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 ↓

Harness vs. Graphs, clearly explained! a harness is great, and most people think it is the whole thing: retries, timeouts, a sandbox, a log, the context it assembles before every call. all of that is real work, and all of it wraps exactly one call. run it a hundred times and you have one call, made very safely, a hundred times. Graph engineering fixes this by moving the decision up a layer: not how safely one call is made, but which calls exist to be made at all. you need both, and here is the sentence that resolves the whole confusion: the harness is everything around one call. the graph is everything between them. ↳ around one call: retry, timeout, sandbox, log, assemble the context, hand back a result ↳ between calls: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the harness does not go away when you build a graph. it moves under each node, and now there are five of them, each wrapping a call you would never have made by hand. the trick is knowing which layer a failure belongs to. turn a piece off and run it again. if the call still works, it was the harness. if the wrong step runs at all, it was the graph. people spend weeks hardening a harness around a node that should not have existed. one thing to know before you scale it. most of what people call their agent is a harness with a chat box on it. ↳ it retries, it times out, it logs, it assembles context, it holds one call up beautifully ↳ it has never once decided that a second call should exist, and that is the entire difference that last one catches careful people. a harness that never fails is not evidence the system is right. it is evidence one call went well, which is the smallest possible claim. and the one that eats whole nights: a harness cannot save you from the wrong step running. you can retry a bad decision three times with a clean log and perfect isolation, and all you bought was three copies of it. 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

51,717 次观看 • 1 个月前

Memory vs. Graphs, clearly explained! memory is great, and the ceiling arrives quietly: it stores what happened. it does not store what to do about it. six runs later your file has fifty lines, and the model reloads all of them before it does anything. Graph engineering fixes this by changing what memory is: not a place things are kept, but an edge that runs backwards. you need both, and here is the sentence that resolves the whole confusion: a store keeps what happened. an edge keeps what to do about it. ↳ a store grows with every run, and every line is reloaded before the next one ↳ an edge carries one derived rule, and the rule replaces the run that produced it Prompts → Context → Harness → Loops → Graphs the transcript goes away, the constraint stays. and the constraint is smaller, because "adapters preserve keyword args exactly" is four hundred tokens shorter than the run that proved it. the same four blocks work on anything you can cut into lanes. i pointed them at token launches on Robinhood Chain, open source, nothing leaves your terminal the trick is knowing what deserves to survive. an output is not memory. "ported the utils slice, green on first pass" tells the next run nothing it can act on. the rule you derived from it does. one thing to know before you scale it. what you write down is not what comes back. ↳ the root rules file and auto memory are re-injected from disk. they come back intact, every time ↳ path-scoped rules live in message history. they get summarized away and do not return until a matching file is read again so a rule that must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: a memory file that has never had a line deleted is not memory. it is a tax on every run you will ever make, and nobody reads it back. 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 the repo that runs it is below ↓

Memory vs. Graphs, clearly explained! memory is great, and the ceiling arrives quietly: it stores what happened. it does not store what to do about it. six runs later your file has fifty lines, and the model reloads all of them before it does anything. Graph engineering fixes this by changing what memory is: not a place things are kept, but an edge that runs backwards. you need both, and here is the sentence that resolves the whole confusion: a store keeps what happened. an edge keeps what to do about it. ↳ a store grows with every run, and every line is reloaded before the next one ↳ an edge carries one derived rule, and the rule replaces the run that produced it Prompts → Context → Harness → Loops → Graphs the transcript goes away, the constraint stays. and the constraint is smaller, because "adapters preserve keyword args exactly" is four hundred tokens shorter than the run that proved it. the same four blocks work on anything you can cut into lanes. i pointed them at token launches on Robinhood Chain, open source, nothing leaves your terminal the trick is knowing what deserves to survive. an output is not memory. "ported the utils slice, green on first pass" tells the next run nothing it can act on. the rule you derived from it does. one thing to know before you scale it. what you write down is not what comes back. ↳ the root rules file and auto memory are re-injected from disk. they come back intact, every time ↳ path-scoped rules live in message history. they get summarized away and do not return until a matching file is read again so a rule that must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: a memory file that has never had a line deleted is not memory. it is a tax on every run you will ever make, and nobody reads it back. 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 the repo that runs it is below ↓

Hanako

48,225 次观看 • 2 个月前

I'm sharing with you one of the best papers I've read on Harness Engineering it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line: agent = model + harness what you walk away with: > what a harness actually is > how today's coding agents are built under the hood > the patterns every one of them repeats > where the whole category is heading > their checklist for building your own the model gets the headlines. the harness decides whether the agent works loop and graph engineering on top of it - in my article below

I'm sharing with you one of the best papers I've read on Harness Engineering it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line: agent = model + harness what you walk away with: > what a harness actually is > how today's coding agents are built under the hood > the patterns every one of them repeats > where the whole category is heading > their checklist for building your own the model gets the headlines. the harness decides whether the agent works loop and graph engineering on top of it - in my article below

Mr. Buzzoni

84,277 次观看 • 1 个月前

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

195,059 次观看 • 7 个月前

the loop is not the agent it is one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls repetition turns retries budgets exits success checks no progress use durable execution when the run must survive failure → GRAPH ENGINEERING controls topology nodes edges state branches checkpoints handoffs build stateful agents as explicit graphs → analyze the topology without putting a model in the loop → HARNESS ENGINEERING controls the blast radius tools permissions memory sandboxes evals traces humans isolate generated code from the host → test behavior before it reaches users → keep one trace across every model node and tool call → without loop control it never stops without graph structure you cannot see the path without harness control it can touch anything the loop lives inside the graph the graph lives inside the harness the model is not the system debug the layer that owns the failure save this

the loop is not the agent it is one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls repetition turns retries budgets exits success checks no progress use durable execution when the run must survive failure → GRAPH ENGINEERING controls topology nodes edges state branches checkpoints handoffs build stateful agents as explicit graphs → analyze the topology without putting a model in the loop → HARNESS ENGINEERING controls the blast radius tools permissions memory sandboxes evals traces humans isolate generated code from the host → test behavior before it reaches users → keep one trace across every model node and tool call → without loop control it never stops without graph structure you cannot see the path without harness control it can touch anything the loop lives inside the graph the graph lives inside the harness the model is not the system debug the layer that owns the failure save this

elune

50,193 次观看 • 3 个月前

A million-token window solved the wrong problem, and Kimi K3 shipping one made that harder to see. 2.8T parameters, weights on your disk, an entire codebase in one prompt. Feels like memory. Isn't. Memory is what survives the session ending. A window is what survives the next token. Self-hosting sharpens it. Now you pay in GPU seconds, not API credits. Every re-read of the same history burns the same compute. Owning the weights didn't make the past free. Kimi Delta Attention cuts what long context costs. Cheaper repetition is still repetition. And a bigger window buys the one thing you don't want: room to keep everything. Nothing in a transcript is dated, ranked, or retired. Old and current load at identical weight. The fix runs beside the model, not inside it. Capture rejects, consolidation merges, decay forgets on schedule. Then a million tokens becomes headroom instead of a bill. You fill 5,000 and leave the rest empty. Look at what your longest thread reloads every run. Then ask how much of it earned the slot.

A million-token window solved the wrong problem, and Kimi K3 shipping one made that harder to see. 2.8T parameters, weights on your disk, an entire codebase in one prompt. Feels like memory. Isn't. Memory is what survives the session ending. A window is what survives the next token. Self-hosting sharpens it. Now you pay in GPU seconds, not API credits. Every re-read of the same history burns the same compute. Owning the weights didn't make the past free. Kimi Delta Attention cuts what long context costs. Cheaper repetition is still repetition. And a bigger window buys the one thing you don't want: room to keep everything. Nothing in a transcript is dated, ranked, or retired. Old and current load at identical weight. The fix runs beside the model, not inside it. Capture rejects, consolidation merges, decay forgets on schedule. Then a million tokens becomes headroom instead of a bill. You fill 5,000 and leave the rest empty. Look at what your longest thread reloads every run. Then ask how much of it earned the slot.

wast3

17,620 次观看 • 2 个月前

GRAPH ENGINEERING: STOP ADDING AGENTS AND START DESIGNING SYSTEMS More agents won’t save you if every step depends on the previous one Graph Engineering forces the better question “Where does the work naturally split? When it does, parallel researchers + independent verifiers + a final merge consistently outperform one overloaded model Verification is more valuable than generation Self-review is usually weaker than dedicated challengers Prompt engineering → Loop engineering → Graph Engineering Are you still designing prompts, or are you designing systems? Bookmark this, then read the article below

GRAPH ENGINEERING: STOP ADDING AGENTS AND START DESIGNING SYSTEMS More agents won’t save you if every step depends on the previous one Graph Engineering forces the better question “Where does the work naturally split? When it does, parallel researchers + independent verifiers + a final merge consistently outperform one overloaded model Verification is more valuable than generation Self-review is usually weaker than dedicated challengers Prompt engineering → Loop engineering → Graph Engineering Are you still designing prompts, or are you designing systems? Bookmark this, then read the article below

beamnxw ./

13,768 次观看 • 3 个月前

LOOP + GRAPH + CONTEXT ENGINEERING = THE KIMI K3 STACK THAT KEEPS RUNNING 300 Kimi K3 agents built one graph out of 100 companies. no 300 documents to read yourself kimi-swarm/ ├── swarm_launch.md task, sources, stop condition ├── CONSTRAINTS.md corrections from every past run ├── graph/ 384 entities, 1,064 typed edges, 8 closed verbs └── cron/ re-fires the swarm on schedule > one node sits at the center with 12 inbound edges - the vendor everyone depends on and nobody flagged in the prompt > 2 hops already answers most of what you'd actually ask it loop decides when it fires -> graph decides what's kept -> context decides what survives after the session closes how people are getting paid on this: > one build sold as a competitive teardown - replaces a four-figure analyst contract, done in an hour, unattended > the same graph on retainer - charge weekly for every new edge that shows up > wire the stack for someone else's market once it's proven on your own full version of this tree is in the article below

LOOP + GRAPH + CONTEXT ENGINEERING = THE KIMI K3 STACK THAT KEEPS RUNNING 300 Kimi K3 agents built one graph out of 100 companies. no 300 documents to read yourself kimi-swarm/ ├── swarm_launch.md task, sources, stop condition ├── CONSTRAINTS.md corrections from every past run ├── graph/ 384 entities, 1,064 typed edges, 8 closed verbs └── cron/ re-fires the swarm on schedule > one node sits at the center with 12 inbound edges - the vendor everyone depends on and nobody flagged in the prompt > 2 hops already answers most of what you'd actually ask it loop decides when it fires -> graph decides what's kept -> context decides what survives after the session closes how people are getting paid on this: > one build sold as a competitive teardown - replaces a four-figure analyst contract, done in an hour, unattended > the same graph on retainer - charge weekly for every new edge that shows up > wire the stack for someone else's market once it's proven on your own full version of this tree is in the article below

Mr. Buzzoni

15,462 次观看 • 2 个月前

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 ↓

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

19,999 次观看 • 2 个月前

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 次观看 • 5 个月前