Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

A drop set does not get you extra growth. A superset does not get you extra growth. Both fail for the same reason. Fatigue does not stay where you made it. You finish a hard set and the fatigue is systemic, central and metabolic, and it takes minutes to...

SamaHoole's profile picture

Sama Hoole

182,236 subscribers

10,857 Aufrufe • vor 3 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

People think low reps are more fatiguing than high reps because the weight is heavier. They have it backwards. Here is a set of 8 Romanian deadlifts to failure. It wiped me out. Over five minutes before I could face the next set. A few minutes earlier I did 4 reps with 30kg more on the bar. Walked away fine. The heavier set was the easier one. Fatigue does not track the weight. It tracks the reps. The more you do, the deeper the hole, and that hole comes with a recovery debt and blunts the growth you were chasing. Heavy and brief leaves you fresh. Light and endless leaves you wrecked. I didn't write the rules. Your body did.
0:30

People think low reps are more fatiguing than high reps because the weight is heavier. They have it backwards. Here is a set of 8 Romanian deadlifts to failure. It wiped me out. Over five minutes before I could face the next set. A few minutes earlier I did 4 reps with 30kg more on the bar. Walked away fine. The heavier set was the easier one. Fatigue does not track the weight. It tracks the reps. The more you do, the deeper the hole, and that hole comes with a recovery debt and blunts the growth you were chasing. Heavy and brief leaves you fresh. Light and endless leaves you wrecked. I didn't write the rules. Your body did.

Sama Hoole

50,149 Aufrufe • vor 1 Monat

Reality check, and it is not a pleasant one. The only evidence that you are building muscle is that the weight on the bar is going up. A bigger muscle produces more force. That is what the tissue is for. If the load has not moved, it has not grown. Everything else, with what it actually tells you: - The pump (blood and water, gone by lunchtime) - Soreness (damage, and damage competes with growth) - Sweat (thermoregulation) - The mirror (lies twice daily, in both directions) - The scale (water, food, and whatever you drank) - Feeling it in the right place (a sensation, not a signal) - Session length (an hour of nothing is still nothing) - Set count (a tally, and the tissue cannot count) - The programme's name (marketing) - Steps, wearables, readiness scores (a subscription) Open the log. Same lift, same reps, same effort, twelve weeks ago. Now the part nobody wants. When the bar stops moving it is almost never because you did too little. It is fatigue, banked over weeks, quietly capping every set you take. The instinct is to add sets. The answer is to cut them, rest properly, and come back in a fortnight to find the weight up while you did less. Muscle cannot get bigger and stay just as weak. If it has not got stronger, it has not got bigger.
0:22

Reality check, and it is not a pleasant one. The only evidence that you are building muscle is that the weight on the bar is going up. A bigger muscle produces more force. That is what the tissue is for. If the load has not moved, it has not grown. Everything else, with what it actually tells you: - The pump (blood and water, gone by lunchtime) - Soreness (damage, and damage competes with growth) - Sweat (thermoregulation) - The mirror (lies twice daily, in both directions) - The scale (water, food, and whatever you drank) - Feeling it in the right place (a sensation, not a signal) - Session length (an hour of nothing is still nothing) - Set count (a tally, and the tissue cannot count) - The programme's name (marketing) - Steps, wearables, readiness scores (a subscription) Open the log. Same lift, same reps, same effort, twelve weeks ago. Now the part nobody wants. When the bar stops moving it is almost never because you did too little. It is fatigue, banked over weeks, quietly capping every set you take. The instinct is to add sets. The answer is to cut them, rest properly, and come back in a fortnight to find the weight up while you did less. Muscle cannot get bigger and stay just as weak. If it has not got stronger, it has not got bigger.

Sama Hoole

208,765 Aufrufe • vor 1 Monat

you numbered the steps so it could not get lost it does not get lost that list was written for a model that wandered, and this one plans better than the list does, so every number you added is a place where it is no longer allowed, to be smarter than you state the goal, the constraints, and how you will know it worked keep the numbers only where exactly one sequence is safe, which is deletes, auth and compliance the procedure felt like rigour it is a cage built to the dimensions of a model that is not in the room
1:21

you numbered the steps so it could not get lost it does not get lost that list was written for a model that wandered, and this one plans better than the list does, so every number you added is a place where it is no longer allowed, to be smarter than you state the goal, the constraints, and how you will know it worked keep the numbers only where exactly one sequence is safe, which is deletes, auth and compliance the procedure felt like rigour it is a cage built to the dimensions of a model that is not in the room

Lagosaur

14,857 Aufrufe • vor 12 Tagen

Why low-rep training feels wrong to almost everyone: You finish a hard set of five. No pump. No burn. Heart rate barely moved. You could carry on a conversation about the weather before the bar stops swinging. Brain says: that wasn't enough. You finish a set of fifteen. Pump like a balloon animal. Quads on fire. Sweating. Sitting on the bench wondering if you should find some gummie bears before your next set. Brain says: now that was a workout. The brain is reading systemic fatigue as muscular stimulus. They are not the same currency. They feel similar from the inside. They produce different results on the outside. The muscle got the signal at rep five. Everything from rep six onwards was generating tiredness, which the brain rewards because tiredness feels like effort and effort feels like progress. Hypertrophy does not score your session by feel. It scores it by mechanical tension on individual fibres at high recruitment. The heavy five did that. The fifteen mostly produced lactate and an interesting selfie. The disconnect is the whole game. Trust the stimulus. Ignore the receipt.
0:21

Why low-rep training feels wrong to almost everyone: You finish a hard set of five. No pump. No burn. Heart rate barely moved. You could carry on a conversation about the weather before the bar stops swinging. Brain says: that wasn't enough. You finish a set of fifteen. Pump like a balloon animal. Quads on fire. Sweating. Sitting on the bench wondering if you should find some gummie bears before your next set. Brain says: now that was a workout. The brain is reading systemic fatigue as muscular stimulus. They are not the same currency. They feel similar from the inside. They produce different results on the outside. The muscle got the signal at rep five. Everything from rep six onwards was generating tiredness, which the brain rewards because tiredness feels like effort and effort feels like progress. Hypertrophy does not score your session by feel. It scores it by mechanical tension on individual fibres at high recruitment. The heavy five did that. The fifteen mostly produced lactate and an interesting selfie. The disconnect is the whole game. Trust the stimulus. Ignore the receipt.

Sama Hoole

55,308 Aufrufe • vor 4 Monaten

you wrapped the tool call in a try block and logged the error the model never found out the exception went to your log, the conversation got nothing, and nothing is indistinguishable from success so it kept planning around a file it believes exists, and wrote the summary of the run where the call worked one line of defensive code cost you twice it could not adapt to a failure it was never shown and the only thing that went wrong is the one thing your trace does not contain
0:57

you wrapped the tool call in a try block and logged the error the model never found out the exception went to your log, the conversation got nothing, and nothing is indistinguishable from success so it kept planning around a file it believes exists, and wrote the summary of the run where the call worked one line of defensive code cost you twice it could not adapt to a failure it was never shown and the only thing that went wrong is the one thing your trace does not contain

Lagosaur

18,563 Aufrufe • vor 8 Tagen

The elites don’t want you know that a set of 5 reps with great technique taken close to failure is basically the most efficient/effective set you can do for muscle growth/strength Unfortunately for the elites but fortunately for you… I AM HERE TO SPREAD THE WORD!
0:23

The elites don’t want you know that a set of 5 reps with great technique taken close to failure is basically the most efficient/effective set you can do for muscle growth/strength Unfortunately for the elites but fortunately for you… I AM HERE TO SPREAD THE WORD!

Dean Turner

181,359 Aufrufe • vor 3 Monaten

Robert Pattinson says the “Dune” set was more challenging that “The Odyssey” set Zendaya: “Which is a more challenging set, Dune or The Odyssey?” Robert Pattinson: “Probably Dune, yeah” “and they’re like “can you stop sweating?” and i’m like “we’re in the desert, i sweat in England” “you cannot have one drop of sweat or it ruins the take” Zendaya: “And the heavy, heavy makeup” Robert Pattinson: “you have to redo it, it takes three hours to reset” Zendaya: “I did feel bad for you because you were a trooper… i’ve never seen you so still in my life”
0:36

Robert Pattinson says the “Dune” set was more challenging that “The Odyssey” set Zendaya: “Which is a more challenging set, Dune or The Odyssey?” Robert Pattinson: “Probably Dune, yeah” “and they’re like “can you stop sweating?” and i’m like “we’re in the desert, i sweat in England” “you cannot have one drop of sweat or it ruins the take” Zendaya: “And the heavy, heavy makeup” Robert Pattinson: “you have to redo it, it takes three hours to reset” Zendaya: “I did feel bad for you because you were a trooper… i’ve never seen you so still in my life”

5sta reze

2,254,115 Aufrufe • vor 1 Monat

"I think the one that stands out probably the most is that you have to train to all-out failure to optimize muscle development. So I came from the old school, either you go all out, or you go home, or the vein in the side of my head wasn't bulging at the end of every set. I wasn't training hard enough. And the research that we have on the topic now really shows you can be a couple reps or three short of failure and still get roughly the same amount of muscle growth." Brad Schoenfeld, PhD
0:52

"I think the one that stands out probably the most is that you have to train to all-out failure to optimize muscle development. So I came from the old school, either you go all out, or you go home, or the vein in the side of my head wasn't bulging at the end of every set. I wasn't training hard enough. And the research that we have on the topic now really shows you can be a couple reps or three short of failure and still get roughly the same amount of muscle growth." Brad Schoenfeld, PhD

Louisa Nicola

11,927 Aufrufe • vor 3 Monaten

There was a parent who lost a child to the needle. Not lost to death, which at least lets you grieve and one day stop. Lost to the street. To the years of disappearing, the phone that stops being answered, the front door left unlocked every single night for a decade on the chance the child might finally come through it. And the parent never stopped. Did not move on. Did not decide the child was too far gone. Drove to the worst parts of town to scan the faces under the overpass. Searched for years, going gray with it, burying the hope a hundred times and digging it back up every morning, because a parent does not get to stop loving a child just because the child is lost. And then came the day it finally happened. The child, hollowed out, certain they were beyond all loving, looked up, and there was the parent's face. And neither of them could speak. They just held on, and they wept, the kind of weeping that has years of grief and years of longing pouring out of it at once, the child sobbing the only word they could find, sorry, sorry, and the parent saying the only word that mattered, which was not "where have you been" and not "do you know what you did to me," but only, over and over into their hair, you're home, you're home, you're home. Now understand. That is not just a real story about a parent and a child. That is God, and that is humanity. No one is forgotten by the Father. He did not fold His arms and wait at home for you to crawl back and prove you were worth it. The moment you were lost, He came after you. And the cost He paid to reach the very bottom of your pit was not patience, and it was not effort. It was His Son, sent down below all of it, so there would be no depth where His face was not already waiting for you to find it. So hear this, wherever it finds you. You were never forgotten, not for one second, not in the worst of it. The door has been unlocked every night since the day you left. He is still driving the worst parts of town. He is still scanning the faces under the overpass. He is still weeping over the ones who are certain they have fallen too far to ever come back. And the moment you turn around, you will not hear "where have you been." You will only hear, said over and over into your hair, the one thing that has been true since before the foundation of the world: you're home, you're home, you're home. Stop running. Come home.
0:39

There was a parent who lost a child to the needle. Not lost to death, which at least lets you grieve and one day stop. Lost to the street. To the years of disappearing, the phone that stops being answered, the front door left unlocked every single night for a decade on the chance the child might finally come through it. And the parent never stopped. Did not move on. Did not decide the child was too far gone. Drove to the worst parts of town to scan the faces under the overpass. Searched for years, going gray with it, burying the hope a hundred times and digging it back up every morning, because a parent does not get to stop loving a child just because the child is lost. And then came the day it finally happened. The child, hollowed out, certain they were beyond all loving, looked up, and there was the parent's face. And neither of them could speak. They just held on, and they wept, the kind of weeping that has years of grief and years of longing pouring out of it at once, the child sobbing the only word they could find, sorry, sorry, and the parent saying the only word that mattered, which was not "where have you been" and not "do you know what you did to me," but only, over and over into their hair, you're home, you're home, you're home. Now understand. That is not just a real story about a parent and a child. That is God, and that is humanity. No one is forgotten by the Father. He did not fold His arms and wait at home for you to crawl back and prove you were worth it. The moment you were lost, He came after you. And the cost He paid to reach the very bottom of your pit was not patience, and it was not effort. It was His Son, sent down below all of it, so there would be no depth where His face was not already waiting for you to find it. So hear this, wherever it finds you. You were never forgotten, not for one second, not in the worst of it. The door has been unlocked every night since the day you left. He is still driving the worst parts of town. He is still scanning the faces under the overpass. He is still weeping over the ones who are certain they have fallen too far to ever come back. And the moment you turn around, you will not hear "where have you been." You will only hear, said over and over into your hair, the one thing that has been true since before the foundation of the world: you're home, you're home, you're home. Stop running. Come home.

Kirk Rollins

21,168 Aufrufe • vor 2 Monaten

A man who went to prison for talking people out of their money filmed himself doing it live, then sold the method as a course. 7 million people have watched him work. The man is Jordan Belfort. The film about him made him famous. What almost nobody has done is watch the real one, on camera, running the actual technique on a real prospect for 22 minutes with no script and no edit. And the way he does it is the reason to watch. He barely talks about the product. The first minutes are almost entirely questions, and every answer gets used against the person later in his own words. He is not persuading. He is collecting. Then the phrase the comments turned into a meme. He ends his key sentences with four words that make agreement feel like the neutral option and refusal feel like rudeness. Once you notice it, you cannot unhear it, and you will catch it in the next call you take. One viewer broke the whole method into 9 steps in a comment. It got 12 thousand likes, which tells you people are studying this video like a manual. Here is the uncomfortable part. Every technique in it is ordinary sales advice: listen, mirror, remove friction, set expectations. That is exactly what makes it worth studying. The tools were never the crime. The intent was. Learn what is being done to you and it stops working on you. That is the only defense there is. 22 minutes. No script. It is in the video.
21:56

A man who went to prison for talking people out of their money filmed himself doing it live, then sold the method as a course. 7 million people have watched him work. The man is Jordan Belfort. The film about him made him famous. What almost nobody has done is watch the real one, on camera, running the actual technique on a real prospect for 22 minutes with no script and no edit. And the way he does it is the reason to watch. He barely talks about the product. The first minutes are almost entirely questions, and every answer gets used against the person later in his own words. He is not persuading. He is collecting. Then the phrase the comments turned into a meme. He ends his key sentences with four words that make agreement feel like the neutral option and refusal feel like rudeness. Once you notice it, you cannot unhear it, and you will catch it in the next call you take. One viewer broke the whole method into 9 steps in a comment. It got 12 thousand likes, which tells you people are studying this video like a manual. Here is the uncomfortable part. Every technique in it is ordinary sales advice: listen, mirror, remove friction, set expectations. That is exactly what makes it worth studying. The tools were never the crime. The intent was. Learn what is being done to you and it stops working on you. That is the only defense there is. 22 minutes. No script. It is in the video.

Silverhand

1,510,415 Aufrufe • vor 1 Monat

Ran Takahashi's signature move 'FAKE SET' ✨️🙂‍↕️❤️‍🔥 And then he explained about it : "This is a technique where you fake a spike but set the ball instead, if you realize two blockers are coming up, you set the ball to the side, effectively drawing the blockers away. The fake set was popularized by the French player Ngapeth, and from there, players from other countries started to imitate this fake set, and that's how it all began."~
1:34

Ran Takahashi's signature move 'FAKE SET' ✨️🙂‍↕️❤️‍🔥 And then he explained about it : "This is a technique where you fake a spike but set the ball instead, if you realize two blockers are coming up, you set the ball to the side, effectively drawing the blockers away. The fake set was popularized by the French player Ngapeth, and from there, players from other countries started to imitate this fake set, and that's how it all began."~

Yuranamore

21,959 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 28 Tagen

your agent has thirty tools. it calls two of them. the other twenty eight are not sitting idle somewhere. they are in the request, every request, and they are doing damage in two places at once. first the obvious one. tool schemas go into the prompt, and a schema is not a name. it is a description, a parameter list, types, required fields, an example. thirty of those is a few thousand tokens that ship with every single call, including the ones where the agent just says thanks and stops. you are paying rent on twenty eight tools that have never fired. second, and this is the one that costs more. when the request says cancel the order, the model picks by matching against everything available. four of your tools are plausible: cancel_order, refund_order, update_order, void_order. it is choosing among them based on the descriptions you wrote, one afternoon, months ago. every tool you add is another candidate in that shortlist. the twenty eight you never call are not neutral. they are noise in the one decision that determines whether the run works. > why it grows without anyone deciding to nobody adds thirty tools on purpose. you add one for a task, it works, it stays. six months later the registry is a catalogue and no one has ever removed anything, because removing a tool feels risky and adding one feels free. and there is no feedback telling you otherwise. the unused ones never error. they never appear in a failing trace. they are invisible in exactly the way that lets them accumulate. > what to actually do count calls per tool over the last thousand runs. this is one group-by and it usually shocks people. the ones at zero are pure cost. ship the tools the task needs, not the whole registry. a research phase does not need deploy. a writing phase does not need the database. swap the set between phases instead of loading everything up front. same agent, different tools, depending on where the run is. and when two tools could both plausibly answer the same request, that is not redundancy you can ignore. it is a coin flip you built into the system. the twenty eight tools are not unused. they are used every time, by the part of the run you cannot see.
0:52

your agent has thirty tools. it calls two of them. the other twenty eight are not sitting idle somewhere. they are in the request, every request, and they are doing damage in two places at once. first the obvious one. tool schemas go into the prompt, and a schema is not a name. it is a description, a parameter list, types, required fields, an example. thirty of those is a few thousand tokens that ship with every single call, including the ones where the agent just says thanks and stops. you are paying rent on twenty eight tools that have never fired. second, and this is the one that costs more. when the request says cancel the order, the model picks by matching against everything available. four of your tools are plausible: cancel_order, refund_order, update_order, void_order. it is choosing among them based on the descriptions you wrote, one afternoon, months ago. every tool you add is another candidate in that shortlist. the twenty eight you never call are not neutral. they are noise in the one decision that determines whether the run works. > why it grows without anyone deciding to nobody adds thirty tools on purpose. you add one for a task, it works, it stays. six months later the registry is a catalogue and no one has ever removed anything, because removing a tool feels risky and adding one feels free. and there is no feedback telling you otherwise. the unused ones never error. they never appear in a failing trace. they are invisible in exactly the way that lets them accumulate. > what to actually do count calls per tool over the last thousand runs. this is one group-by and it usually shocks people. the ones at zero are pure cost. ship the tools the task needs, not the whole registry. a research phase does not need deploy. a writing phase does not need the database. swap the set between phases instead of loading everything up front. same agent, different tools, depending on where the run is. and when two tools could both plausibly answer the same request, that is not redundancy you can ignore. it is a coin flip you built into the system. the twenty eight tools are not unused. they are used every time, by the part of the run you cannot see.

Hanako

24,656 Aufrufe • vor 25 Tagen

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

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

Hanako

96,243 Aufrufe • vor 11 Tagen

The FIRST working set you do of an exercise should be the BEST working set you do of that exercise (assuming relative intensity is equated across sets) In the event that it’s not, you almost assuredly are NOT warming up properly Fatigue accumulates over the course of a workout as sets transpire This makes it physiologically impossible to improve performance as a session progresses unless you (A) weren’t ready from the outset or (B) were sandbagging earlier sets (could be intentional or unintentional)
1:13

The FIRST working set you do of an exercise should be the BEST working set you do of that exercise (assuming relative intensity is equated across sets) In the event that it’s not, you almost assuredly are NOT warming up properly Fatigue accumulates over the course of a workout as sets transpire This makes it physiologically impossible to improve performance as a session progresses unless you (A) weren’t ready from the outset or (B) were sandbagging earlier sets (could be intentional or unintentional)

Dean Turner

46,755 Aufrufe • vor 3 Monaten

Sam Altman just handed every startup founder a one-question autopsy. Altman: “If you’re building something on GPT-4 that a reasonable observer would say we’re going to steamroll you.” Not might. Not could. Going to. He said it with the calm of someone describing weather. Because to him it is weather. The model improves. Whatever was built on the old version’s weaknesses gets washed away. That is not strategy. That is erosion. And most founders are building on the erosion line. They find a gap in the current model. They wrap a product around it. They raise money. They hire. They scale. Then OpenAI releases the next version and the gap closes and the product has no reason to exist anymore. Altman: “When we just do our fundamental job, which is make the model better with every crank, then you get the ‘OpenAI killed my startup’ meme.” He is telling you directly. They are not hunting you. They are not even thinking about you. They are just improving the model. You happen to be standing where the improvement lands. That is the part founders refuse to hear. OpenAI does not need to compete with you. It just needs to keep doing exactly what it was already doing and your entire company disappears as a side effect. You are not a competitor. You are a temporary symptom of incomplete intelligence. The moment the intelligence completes you become nothing. Then Brad Lightcap delivered the cleanest diagnostic ever spoken in venture capital. Lightcap: “Ask if a 100x improvement in the model is something they’re excited about.” One question. The entire investment thesis reduced to a single binary. Does the next model make your company more powerful or does it make your company pointless. There is no middle ground. Lightcap: “We know the companies that come to us saying, ‘We want the next model. When is it coming out? I want to be the first to try it.’” These companies built something that feeds on intelligence. The smarter the model gets the more their product can do. They are not threatened by progress. They are starving for it. Then there are the companies Lightcap never hears from. The ones who go quiet when a new model drops. The ones who read the release notes like a death sentence. The ones privately praying the next generation takes longer because every improvement shrinks the ground beneath them. If you are hoping the model stays roughly where it is you have already told the market everything it needs to know about your company. You are not building on intelligence. You are building on the absence of it. Altman: “95% of the world should be betting on the latter category.” The latter category is simple. Assume the model keeps getting better at the pace it has been getting better. Build for that world. Not the world where GPT-4 is the ceiling. The world where GPT-4 is the floor and the ceiling has not been built yet. Then Altman told a story that should be framed on the wall of every startup in the country. A medical AI company came to him that morning. They were not complaining about the model. They were not worried about being replaced. They were demanding it improve faster. Altman: “Here’s how many people are dying every day you delay.” That is what alignment with the trajectory looks like. A company so deeply built on intelligence improving that every day the model stays the same is a day someone dies who did not have to. They are not building on a flaw. They are building on a future that has not arrived fast enough. That is the difference. The wrapper startup patches what the model cannot do today. The real company builds what the model will unlock tomorrow. One is running from the train. The other is laying the track. Altman told you the train is not slowing down. Lightcap told you exactly how to know which side you are on. One question. Does a 100x smarter model make you more valuable or erase you. If you had to pause before answering you already did.
2:28

Sam Altman just handed every startup founder a one-question autopsy. Altman: “If you’re building something on GPT-4 that a reasonable observer would say we’re going to steamroll you.” Not might. Not could. Going to. He said it with the calm of someone describing weather. Because to him it is weather. The model improves. Whatever was built on the old version’s weaknesses gets washed away. That is not strategy. That is erosion. And most founders are building on the erosion line. They find a gap in the current model. They wrap a product around it. They raise money. They hire. They scale. Then OpenAI releases the next version and the gap closes and the product has no reason to exist anymore. Altman: “When we just do our fundamental job, which is make the model better with every crank, then you get the ‘OpenAI killed my startup’ meme.” He is telling you directly. They are not hunting you. They are not even thinking about you. They are just improving the model. You happen to be standing where the improvement lands. That is the part founders refuse to hear. OpenAI does not need to compete with you. It just needs to keep doing exactly what it was already doing and your entire company disappears as a side effect. You are not a competitor. You are a temporary symptom of incomplete intelligence. The moment the intelligence completes you become nothing. Then Brad Lightcap delivered the cleanest diagnostic ever spoken in venture capital. Lightcap: “Ask if a 100x improvement in the model is something they’re excited about.” One question. The entire investment thesis reduced to a single binary. Does the next model make your company more powerful or does it make your company pointless. There is no middle ground. Lightcap: “We know the companies that come to us saying, ‘We want the next model. When is it coming out? I want to be the first to try it.’” These companies built something that feeds on intelligence. The smarter the model gets the more their product can do. They are not threatened by progress. They are starving for it. Then there are the companies Lightcap never hears from. The ones who go quiet when a new model drops. The ones who read the release notes like a death sentence. The ones privately praying the next generation takes longer because every improvement shrinks the ground beneath them. If you are hoping the model stays roughly where it is you have already told the market everything it needs to know about your company. You are not building on intelligence. You are building on the absence of it. Altman: “95% of the world should be betting on the latter category.” The latter category is simple. Assume the model keeps getting better at the pace it has been getting better. Build for that world. Not the world where GPT-4 is the ceiling. The world where GPT-4 is the floor and the ceiling has not been built yet. Then Altman told a story that should be framed on the wall of every startup in the country. A medical AI company came to him that morning. They were not complaining about the model. They were not worried about being replaced. They were demanding it improve faster. Altman: “Here’s how many people are dying every day you delay.” That is what alignment with the trajectory looks like. A company so deeply built on intelligence improving that every day the model stays the same is a day someone dies who did not have to. They are not building on a flaw. They are building on a future that has not arrived fast enough. That is the difference. The wrapper startup patches what the model cannot do today. The real company builds what the model will unlock tomorrow. One is running from the train. The other is laying the track. Altman told you the train is not slowing down. Lightcap told you exactly how to know which side you are on. One question. Does a 100x smarter model make you more valuable or erase you. If you had to pause before answering you already did.

Dustin

39,109 Aufrufe • vor 5 Monaten

One of the most powerful verses in the Bible: ““Before I formed you in the womb I knew you, before you were born I set you apart; I appointed you as a prophet to the nations.”” Jeremiah 1:5 NIV What does it mean?
3:11

One of the most powerful verses in the Bible: ““Before I formed you in the womb I knew you, before you were born I set you apart; I appointed you as a prophet to the nations.”” Jeremiah 1:5 NIV What does it mean?

NancyH

16,130 Aufrufe • vor 6 Monaten

I’m shocked, totally shocked….who could ever have seen this coming. The Crown Prosecution service has decided NOT to push ahead with a further trial for the Manchester airport brothers….massive surprise…not. It was never gonna happen. The authorities are desperate to make it go away and desperate not to upset the “community”. What precedent does it set for the police force, what precedent does it set for violent scumbags like these two and what does it say about the future of Jury trials?
5:03

I’m shocked, totally shocked….who could ever have seen this coming. The Crown Prosecution service has decided NOT to push ahead with a further trial for the Manchester airport brothers….massive surprise…not. It was never gonna happen. The authorities are desperate to make it go away and desperate not to upset the “community”. What precedent does it set for the police force, what precedent does it set for violent scumbags like these two and what does it say about the future of Jury trials?

John Hannam

15,707 Aufrufe • vor 3 Monaten

Matt Damon reveals how unprofessional the cast was on set and the secret, hilarious way they punished whoever arrived last to the scene. ​Matt Damon: “Hey, I don't even understand what happened in there. What did I say? You called his niece a whore. A very cheap one. What? She's 7, currently confined to bed with a wicked case... no, don't tell him, don't tell him that. I'm sorry. Okay, so what does this mean? It means you stay here." "​Well, we rarely kept a straight face. I mean, what's in the movie are the takes where we didn't kind of fall out laughing cause we were pretty unprofessional. Steven used to complain; he was like the teacher trying to keep everybody in line." "​But we just had so much fun together, and it was such a good group. There was no ego on those sets. If you were the last person to get to set you know, cause you all get called at the same time and the last person invariably got a round of applause, like a standing ovation from everyone else, even if you're like two minutes early to set. Like, if you're the last one." "​So, kind of the opposite of what you might expect in a situation where ego could get involved. It just never happened.”
0:49

Matt Damon reveals how unprofessional the cast was on set and the secret, hilarious way they punished whoever arrived last to the scene. ​Matt Damon: “Hey, I don't even understand what happened in there. What did I say? You called his niece a whore. A very cheap one. What? She's 7, currently confined to bed with a wicked case... no, don't tell him, don't tell him that. I'm sorry. Okay, so what does this mean? It means you stay here." "​Well, we rarely kept a straight face. I mean, what's in the movie are the takes where we didn't kind of fall out laughing cause we were pretty unprofessional. Steven used to complain; he was like the teacher trying to keep everybody in line." "​But we just had so much fun together, and it was such a good group. There was no ego on those sets. If you were the last person to get to set you know, cause you all get called at the same time and the last person invariably got a round of applause, like a standing ovation from everyone else, even if you're like two minutes early to set. Like, if you're the last one." "​So, kind of the opposite of what you might expect in a situation where ego could get involved. It just never happened.”

Mide

817,590 Aufrufe • vor 2 Monaten

Richard Feynman, Nobel Prize-winning physicist: "The universe itself doesn't know what happens next. it only knows the odds. I won a Nobel proving reality runs on probability, not certainty, which means the casino isn't cheating you. it's just closer to how nature works than you are." this free lecture from 1964 is a Nobel laureate explaining that certainty is not something the universe offers, and it has been public for sixty years. at the board it's simple. Feynman showed that at the deepest level nature does not decide what will happen, only the probability of what might. Fire a single electron at two slits and no one alive can tell you where it lands, only the odds of each spot. This drove Einstein to say God does not play dice. Feynman and the experiments proved him wrong. Reality is a probability machine, all the way down. That's the whole thing, minus the mysticism. Which means the casino is not an exception to how the world works. It is a scale model of it. Nobody gets certainty, not the gambler, not the trader, not the universe. Same point as my article above: the house wins not because it knows the outcome, but because it prices the odds while you chase a sure thing that does not exist anywhere in nature. the physics is free and it has been settled for a century. what nobody can sell you is the discipline to give up the craving for certainty and act on probabilities instead. That surrender is the whole edge, and it is the hardest thing a human mind ever does.
53:34

Richard Feynman, Nobel Prize-winning physicist: "The universe itself doesn't know what happens next. it only knows the odds. I won a Nobel proving reality runs on probability, not certainty, which means the casino isn't cheating you. it's just closer to how nature works than you are." this free lecture from 1964 is a Nobel laureate explaining that certainty is not something the universe offers, and it has been public for sixty years. at the board it's simple. Feynman showed that at the deepest level nature does not decide what will happen, only the probability of what might. Fire a single electron at two slits and no one alive can tell you where it lands, only the odds of each spot. This drove Einstein to say God does not play dice. Feynman and the experiments proved him wrong. Reality is a probability machine, all the way down. That's the whole thing, minus the mysticism. Which means the casino is not an exception to how the world works. It is a scale model of it. Nobody gets certainty, not the gambler, not the trader, not the universe. Same point as my article above: the house wins not because it knows the outcome, but because it prices the odds while you chase a sure thing that does not exist anywhere in nature. the physics is free and it has been settled for a century. what nobody can sell you is the discipline to give up the craving for certainty and act on probabilities instead. That surrender is the whole edge, and it is the hardest thing a human mind ever does.

Voltex

10,875 Aufrufe • vor 1 Monat