Загрузка видео...

Не удалось загрузить видео

На главную

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...

hanakoxbt's profile picture

Hanako

21,712 subscribers

48,225 просмотров • 1 месяц назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 13

Фото профиля Shon Pazarker
Shon Pazarker1 месяц назад

A memory file stores the transcript. A graph stores the rule that survived it. That is how context avoids becoming slop.

Фото профиля morph
morph1 месяц назад

thanks for the info. if was useful

Фото профиля kocer
kocer1 месяц назад

the video makes the token bloat vs 3 rules thing obvious

Фото профиля AI Mastery Guide
AI Mastery Guide1 месяц назад

55x fewer tokens is a big deal actually

Фото профиля Agent Rails
Agent Rails1 месяц назад

The payments version of this is brutal. Memory tells you the agent paid that vendor twice last week. A graph edge tells you it can't. One is a log, the other is a rule you can enforce

Фото профиля David Starmac Ai
David Starmac Ai1 месяц назад

Memory and graphs solve different problems, sure, but fifty lines is a retrieval problem, not a storage one. A decent index fixes that before you need a graph.

Фото профиля Max Bevza
Max Bevza1 месяц назад

finally a clean way to scale context without the bloat

Фото профиля tidequant
tidequant1 месяц назад

drop the bludclart ticker

Фото профиля Rachit Gupta
Rachit Gupta1 месяц назад

Can you share how you made this animated infographic?

Фото профиля slash1s
slash1s1 месяц назад

yeah everyone need to learn it

Фото профиля Web3WithAi
Web3WithAi1 месяц назад

So basically memory scales linearly while graphs let you actually route to what matters. Makes sense why folks are moving there.

Фото профиля The Time for Patriots is Now
The Time for Patriots is Now1 месяц назад

I have no idea what you posted here but it seems legit and at some point i need ai to teach me how to make it do things.

Фото профиля Atenov int.
Atenov int.1 месяц назад

I get what you mean about the edge being the output instead of the input

Похожие видео

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 ↓
0:53

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 просмотров • 2 месяцев назад

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. 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 ↓
0:41

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. 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

73,867 просмотров • 2 месяцев назад

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 ↓
0:51

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 просмотров • 1 месяц назад

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 ↓
0:47

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 просмотров • 1 месяц назад

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 ↓
0:53

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 просмотров • 1 месяц назад

Loops vs. Graphs, clearly explained! loops are great, and the ceiling is one you can watch turn: a loop is a gear. it produces, checks, corrects, and comes back around. after six turns you have one job, done very well. after six hundred turns you still have one job, done very well. the teeth are perfect. they are touching nothing. Graph engineering fixes this by moving the decision up a layer: not how well one gear turns, but what it is meshed into. you need both, and here is the sentence that resolves the whole confusion: the loop lives inside a node. the graph lives between them. ↳ inside one unit: produce, check, correct, repeat until green ↳ between units: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the loop does not go away when you build a graph. it moves inside, and now there are three of them turning at once on three things you would never have thought to run. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. one thing to know before you scale it. a loop that cannot fail is not a loop, it is a repeat with a bill attached. ↳ the test suite exits 0 is a check. the diff touches only the files in the plan is a check ↳ the output looks good, the model says it is confident, no errors were raised, none of those are checks that last one catches careful people. absence of an error is not evidence of correctness, and a loop built on it will confidently repeat a mistake until the budget runs out, with a clean log the whole way. and the one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. 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 ↓
0:50

Loops vs. Graphs, clearly explained! loops are great, and the ceiling is one you can watch turn: a loop is a gear. it produces, checks, corrects, and comes back around. after six turns you have one job, done very well. after six hundred turns you still have one job, done very well. the teeth are perfect. they are touching nothing. Graph engineering fixes this by moving the decision up a layer: not how well one gear turns, but what it is meshed into. you need both, and here is the sentence that resolves the whole confusion: the loop lives inside a node. the graph lives between them. ↳ inside one unit: produce, check, correct, repeat until green ↳ between units: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the loop does not go away when you build a graph. it moves inside, and now there are three of them turning at once on three things you would never have thought to run. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. one thing to know before you scale it. a loop that cannot fail is not a loop, it is a repeat with a bill attached. ↳ the test suite exits 0 is a check. the diff touches only the files in the plan is a check ↳ the output looks good, the model says it is confident, no errors were raised, none of those are checks that last one catches careful people. absence of an error is not evidence of correctness, and a loop built on it will confidently repeat a mistake until the budget runs out, with a clean log the whole way. and the one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. 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

32,807 просмотров • 1 месяц назад

Loops vs. Graphs, clearly explained! loops are great, and they have a ceiling you can watch happen: a loop goes around. it produces, checks, corrects, and goes around again. after six passes you have one job, done very well. after six hundred passes you still have one job, done very well. Graph engineering fixes this by moving the decision up a layer: not how well one job gets done, but which jobs exist to be done at all. you need both, and here is the sentence that resolves the whole confusion: the loop lives inside a node. the graph lives between them. ↳ inside one unit: produce, check, correct, repeat until green ↳ between units: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the loop does not go away when you build a graph. it moves inside, and now there are three of them running at once on three things you would never have thought to run. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. one thing to know before you scale it. a loop that cannot fail is not a loop, it is a repeat with a bill attached. and the check people write is almost always the wrong kind. ↳ the test suite exits 0 is a check. the diff touches only the files in the plan is a check ↳ the output looks good, the model says it is confident, no errors were raised, none of those are checks that last one catches careful people. absence of an error is not evidence of correctness, and a loop built on it will confidently repeat a mistake until the budget runs out, with a clean log the whole way. and the one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. 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 ↓
0:50

Loops vs. Graphs, clearly explained! loops are great, and they have a ceiling you can watch happen: a loop goes around. it produces, checks, corrects, and goes around again. after six passes you have one job, done very well. after six hundred passes you still have one job, done very well. Graph engineering fixes this by moving the decision up a layer: not how well one job gets done, but which jobs exist to be done at all. you need both, and here is the sentence that resolves the whole confusion: the loop lives inside a node. the graph lives between them. ↳ inside one unit: produce, check, correct, repeat until green ↳ between units: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the loop does not go away when you build a graph. it moves inside, and now there are three of them running at once on three things you would never have thought to run. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. one thing to know before you scale it. a loop that cannot fail is not a loop, it is a repeat with a bill attached. and the check people write is almost always the wrong kind. ↳ the test suite exits 0 is a check. the diff touches only the files in the plan is a check ↳ the output looks good, the model says it is confident, no errors were raised, none of those are checks that last one catches careful people. absence of an error is not evidence of correctness, and a loop built on it will confidently repeat a mistake until the budget runs out, with a clean log the whole way. and the one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. 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

129,105 просмотров • 1 месяц 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

97,154 просмотров • 2 месяцев назад

The creator of High Bandwidth Memory (HBM) put a number on the AI build that should stop every infra investor cold. A cluster of a million GPUs runs at roughly 10-20% utilization (Save this). Kim Jung-ho spent thirty years building what feeds the GPU, and his claim is that the GPU is barely working. Here is what is actually happening. Every time a model generates output, the data has to be read out of memory, computed, and written back. The read and the write swallow almost the entire cycle. While that data moves, the GPU does nothing. It sits there, fully powered, fully paid for, waiting. By Kim's estimate the memory is doing only about 30 percent of the work it needs to do. The processor idles the rest. So a million installed GPUs run at 10 to 20 percent. You are not compute constrained. You are memory constrained, and the expensive part is standing around. Adding more GPUs does not fix this. It gives you more processors starving for the same data. Here is the part that decides the next decade. Memory can grow. When a cell cannot shrink any further, you stack it into a high-rise, layer on layer. A GPU cannot be stacked. It runs too hot and needs a cooler bolted to its back, so the one move that rescues memory is closed to the processor. The thing that can keep stacking compounds. The thing that cannot plateaus. The marginal dollar in an AI build now buys more by fixing the memory path than by bolting on another idle GPU. Which is why the companies that control memory bandwidth and supply are not suppliers to the AI trade. They are the AI trade.
0:50

The creator of High Bandwidth Memory (HBM) put a number on the AI build that should stop every infra investor cold. A cluster of a million GPUs runs at roughly 10-20% utilization (Save this). Kim Jung-ho spent thirty years building what feeds the GPU, and his claim is that the GPU is barely working. Here is what is actually happening. Every time a model generates output, the data has to be read out of memory, computed, and written back. The read and the write swallow almost the entire cycle. While that data moves, the GPU does nothing. It sits there, fully powered, fully paid for, waiting. By Kim's estimate the memory is doing only about 30 percent of the work it needs to do. The processor idles the rest. So a million installed GPUs run at 10 to 20 percent. You are not compute constrained. You are memory constrained, and the expensive part is standing around. Adding more GPUs does not fix this. It gives you more processors starving for the same data. Here is the part that decides the next decade. Memory can grow. When a cell cannot shrink any further, you stack it into a high-rise, layer on layer. A GPU cannot be stacked. It runs too hot and needs a cooler bolted to its back, so the one move that rescues memory is closed to the processor. The thing that can keep stacking compounds. The thing that cannot plateaus. The marginal dollar in an AI build now buys more by fixing the memory path than by bolting on another idle GPU. Which is why the companies that control memory bandwidth and supply are not suppliers to the AI trade. They are the AI trade.

Fireside Alpha

38,370 просмотров • 4 месяцев назад

Anthropic engineer: "At Anthropic we don't write prompts anymore. We build loops and graphs." In 32 minutes she shows how Anthropic builds agents that remember, fix their own mistakes and get sharper every run Prompts → Agents → Loops → Graphs a loop catches the mistake and sends it back to the step that made it a graph keeps what worked and hands it to the next run as a rule the first half is the part people build, the second is the part almost nobody does watch it today then save the full graph engineering guide below before everyone catches up ↓
32:03

Anthropic engineer: "At Anthropic we don't write prompts anymore. We build loops and graphs." In 32 minutes she shows how Anthropic builds agents that remember, fix their own mistakes and get sharper every run Prompts → Agents → Loops → Graphs a loop catches the mistake and sends it back to the step that made it a graph keeps what worked and hands it to the next run as a rule the first half is the part people build, the second is the part almost nobody does watch it today then save the full graph engineering guide below before everyone catches up ↓

Callan

31,640 просмотров • 1 месяц назад

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 below
0:40

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 below

Hanako

19,160 просмотров • 3 месяцев 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

85,117 просмотров • 1 месяц назад

you told it something in the middle of a session, and an hour later it behaved like you never had you were not forgotten, you were never written down an instruction can live in three places and compaction treats them differently: the project root file is re-read from disk and put back, a nested one or a path scoped rule comes back only when the model next opens a file it applies to, and anything you only said out loud comes back never so the rule you typed most recently, in the moment it mattered most, is the one with the shortest life in the room you thought you were configuring it you were talking to it one of those survives the summary
1:13

you told it something in the middle of a session, and an hour later it behaved like you never had you were not forgotten, you were never written down an instruction can live in three places and compaction treats them differently: the project root file is re-read from disk and put back, a nested one or a path scoped rule comes back only when the model next opens a file it applies to, and anything you only said out loud comes back never so the rule you typed most recently, in the moment it mattered most, is the one with the shortest life in the room you thought you were configuring it you were talking to it one of those survives the summary

Lagosaur

10,263 просмотров • 1 месяц назад

Anthropic engineer: "At Anthropic we don't write prompts anymore. We build loops and graphs." In 29 minutes she shows how Anthropic builds agents that remember, fix their own mistakes and get sharper every run Prompts → Agents → Loops → Graphs a loop catches the mistake and sends it back to the step that made it a graph keeps what worked and hands it to the next run as a rule the first half is the part people build, the second is the part almost nobody does watch it today, then save the full graph engineering guide below ↓
29:36

Anthropic engineer: "At Anthropic we don't write prompts anymore. We build loops and graphs." In 29 minutes she shows how Anthropic builds agents that remember, fix their own mistakes and get sharper every run Prompts → Agents → Loops → Graphs a loop catches the mistake and sends it back to the step that made it a graph keeps what worked and hands it to the next run as a rule the first half is the part people build, the second is the part almost nobody does watch it today, then save the full graph engineering guide below ↓

Callan

59,756 просмотров • 1 месяц назад

A developer in Hangzhou runs an AI that remembers everything about him for $0.40 a year. No vector database. One file that never grows past 4,000 tokens. He published the whole schema. His version starts from the opposite idea. Memory is not storage. It's a write policy. Six fields. Rewritten every time, never appended: > IDENTITY - who you are, what you build. 300 tokens. Changes monthly at most > STATE - what you're on right now. 400 tokens. Rewritten daily > DECISIONS - what's already settled, so nothing gets re-argued. 800 tokens > CORRECTIONS - every time you said "no, not like that." 600 tokens > PEOPLE - names, roles, who's waiting on what. 500 tokens > DEAD - tried and abandoned, so it never comes back as a suggestion. 400 tokens Three thousand tokens. Ceiling of four. When a section fills, the model rewrites it shorter. Nothing is ever added. Only replaced. Kimi K2.5 bills $0.10 per million cached input tokens. Four thousand tokens a turn is $0.0004. That's 2,500 turns for a dollar. The free tier hands you 1.5 million tokens a day. 375 turns before you pay anything at all. CORRECTIONS is the field nobody builds, and it's the one that does the work. A model that remembers being wrong stops repeating it. Everyone else is paying to search their own history. He pays to keep it short. The bill stopped growing when the file did. Your memory system isn't defined by what it stores. It's defined by what it agrees to delete. The article below is the full build - schema, rewrite prompts, the compaction rule that keeps it under the cap. Save it. You'll want it open in the other tab.
0:41

A developer in Hangzhou runs an AI that remembers everything about him for $0.40 a year. No vector database. One file that never grows past 4,000 tokens. He published the whole schema. His version starts from the opposite idea. Memory is not storage. It's a write policy. Six fields. Rewritten every time, never appended: > IDENTITY - who you are, what you build. 300 tokens. Changes monthly at most > STATE - what you're on right now. 400 tokens. Rewritten daily > DECISIONS - what's already settled, so nothing gets re-argued. 800 tokens > CORRECTIONS - every time you said "no, not like that." 600 tokens > PEOPLE - names, roles, who's waiting on what. 500 tokens > DEAD - tried and abandoned, so it never comes back as a suggestion. 400 tokens Three thousand tokens. Ceiling of four. When a section fills, the model rewrites it shorter. Nothing is ever added. Only replaced. Kimi K2.5 bills $0.10 per million cached input tokens. Four thousand tokens a turn is $0.0004. That's 2,500 turns for a dollar. The free tier hands you 1.5 million tokens a day. 375 turns before you pay anything at all. CORRECTIONS is the field nobody builds, and it's the one that does the work. A model that remembers being wrong stops repeating it. Everyone else is paying to search their own history. He pays to keep it short. The bill stopped growing when the file did. Your memory system isn't defined by what it stores. It's defined by what it agrees to delete. The article below is the full build - schema, rewrite prompts, the compaction rule that keeps it under the cap. Save it. You'll want it open in the other tab.

wast3

15,862 просмотров • 2 месяцев назад

If you think Grok Bot has no business anywhere near your money, look at what it wrote before it was allowed to touch a single dollar. One prompt. It came back with this: > a story on its own is never a trade, it needs the money flow behind it in the same hour > it will not open a position until the exit is already written down > every claim it makes comes with the filing or the transaction it came from, no source and the claim does not exist > one agent exists only to say no, and its veto beats every score on the desk It does not care what you trade. Gold, oil, a stock you inherited or a coin that launched an hour ago, the rules are the same. Now be honest. Do you know why you are holding what you are holding? Do you write your exit before your entry? It does both every time, and it does not get bored at 2am. This is not a chat window that dies when you close the tab. Every agent has its own computer in the cloud that never logs off. $1,000 to $3,900 on day one came out of that, not out of luck. Full proofs below.
0:50

If you think Grok Bot has no business anywhere near your money, look at what it wrote before it was allowed to touch a single dollar. One prompt. It came back with this: > a story on its own is never a trade, it needs the money flow behind it in the same hour > it will not open a position until the exit is already written down > every claim it makes comes with the filing or the transaction it came from, no source and the claim does not exist > one agent exists only to say no, and its veto beats every score on the desk It does not care what you trade. Gold, oil, a stock you inherited or a coin that launched an hour ago, the rules are the same. Now be honest. Do you know why you are holding what you are holding? Do you write your exit before your entry? It does both every time, and it does not get bored at 2am. This is not a chat window that dies when you close the tab. Every agent has its own computer in the cloud that never logs off. $1,000 to $3,900 on day one came out of that, not out of luck. Full proofs below.

cvxv666

13,754 просмотров • 2 месяцев назад

your ai agent tested 1,262 trading strategies overnight. by morning it had forgotten every one of them. so tonight it tests some of them again. next week, again. everything it learned is sitting in a log file that nothing reads. every run starts on the same blank page. that's why it keeps handing you the idea that already died in a crash, with a new name on it, and you pay to find out twice. ai agent already does everything a fund does. finds the idea, writes the code, tests it against years of history, puts it live, reads what went wrong afterwards. all of it runs tonight for nothing. the one thing it can't do is remember. what got tried, what failed, in which market. nobody has built that part yet. that's the whole gap. not better models. a notebook. whoever builds it first gets a system that improves every week without them touching it. read the article below and save it. it's the full guide to how an ai trading agent is built, and how to make it remember every strategy it has already tested.
0:44

your ai agent tested 1,262 trading strategies overnight. by morning it had forgotten every one of them. so tonight it tests some of them again. next week, again. everything it learned is sitting in a log file that nothing reads. every run starts on the same blank page. that's why it keeps handing you the idea that already died in a crash, with a new name on it, and you pay to find out twice. ai agent already does everything a fund does. finds the idea, writes the code, tests it against years of history, puts it live, reads what went wrong afterwards. all of it runs tonight for nothing. the one thing it can't do is remember. what got tried, what failed, in which market. nobody has built that part yet. that's the whole gap. not better models. a notebook. whoever builds it first gets a system that improves every week without them touching it. read the article below and save it. it's the full guide to how an ai trading agent is built, and how to make it remember every strategy it has already tested.

cvxv666

49,181 просмотров • 2 месяцев назад

you opened a memory file and could not tell when it was written there is a field for that, and some of those files will never have it the timestamp goes into frontmatter, and it is only added to files that already begin with frontmatter, it is never added to a file that has none so a note created without those three dashes at the top is undateable for the rest of its life, and on screen it looks exactly like the ones that are current sixteen of my thirty nine are sitting there with no date on them right now you are not reading a memory you are reading an undated claim that loads before you speak
1:57

you opened a memory file and could not tell when it was written there is a field for that, and some of those files will never have it the timestamp goes into frontmatter, and it is only added to files that already begin with frontmatter, it is never added to a file that has none so a note created without those three dashes at the top is undateable for the rest of its life, and on screen it looks exactly like the ones that are current sixteen of my thirty nine are sitting there with no date on them right now you are not reading a memory you are reading an undated claim that loads before you speak

Lagosaur

31,471 просмотров • 1 месяц назад

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
35:25

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

194,990 просмотров • 6 месяцев назад

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
0:50

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 просмотров • 2 месяцев назад