Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

there are four types of agent loops. most people only know one. loop engineering is a choice between four structures, each handing off one more job than the last. every one answers two questions: what starts a run, and what ends it. hand-run, you answer both yourself, every time....

hanakoxbt's profile picture

Hanako

16,967 subscribers

477,394 görüntüleme • 2 ay önce •via X (Twitter)

Bilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

You're still typing every turn The guy who built the tool wrote the loop that types them for him "I don't prompt Claude anymore I write loops that prompt Claude" A loop takes four shapes turn-based, you close it each round goal-based - all tests pass, stop after 5 tries time-based - every 10 min, fix what's red, overnight proactive - CI breaks, agents fix it and open a PR, no human at all A judge closes the loop, not you The prompt was never the unit of work the loop is Full breakdown below
0:13

You're still typing every turn The guy who built the tool wrote the loop that types them for him "I don't prompt Claude anymore I write loops that prompt Claude" A loop takes four shapes turn-based, you close it each round goal-based - all tests pass, stop after 5 tries time-based - every 10 min, fix what's red, overnight proactive - CI breaks, agents fix it and open a PR, no human at all A judge closes the loop, not you The prompt was never the unit of work the loop is Full breakdown below

Skaly_Bull

12,558 görüntüleme • 1 ay önce

an agent is four parts in a loop. you own one. the other three break it. that's why the demo works and prod doesn't. you can't debug what you can't see. 1) the prompt → what you tell the model each turn. you own this one. good. 2) the context window → what it sees right now. the framework fills it with junk, and you never notice until it rots. 3) the tools → what it can do. you own the list, not when or why it fires them. 4) the control flow → what happens next, when to stop. the framework owns this. it's what breaks at 80%. own all four and your agent stops being a magic trick that works on stage and dies on call. this isn't my idea. it's the 12-factor agents guide (24k stars) github: the whole thing every serious builder ends up rewriting their stack around. full breakdown in the article below.
0:19

an agent is four parts in a loop. you own one. the other three break it. that's why the demo works and prod doesn't. you can't debug what you can't see. 1) the prompt → what you tell the model each turn. you own this one. good. 2) the context window → what it sees right now. the framework fills it with junk, and you never notice until it rots. 3) the tools → what it can do. you own the list, not when or why it fires them. 4) the control flow → what happens next, when to stop. the framework owns this. it's what breaks at 80%. own all four and your agent stops being a magic trick that works on stage and dies on call. this isn't my idea. it's the 12-factor agents guide (24k stars) github: the whole thing every serious builder ends up rewriting their stack around. full breakdown in the article below.

Hanako

38,184 görüntüleme • 1 ay önce

ONE PROMPT WON'T MAKE YOU RICH👀 It won’t change your life overnight. And it won’t solve all your problems. But the right prompt can do something much more important. It can reveal things you hadn’t noticed before. Most people use AI to find answers. But the most useful prompts work differently. They make you ask yourself questions. > What’s really holding you back? > What decisions have you been putting off for months? > What are you wasting your time on, convincing yourself it’s important? Sometimes, one honest answer is more valuable than a hundred motivational videos and dozens of books. That’s exactly why I liked this prompt. It doesn’t try to impress with complexity. It helps you see your situation from the outside. Spend a few minutes on it. Perhaps a single conversation with AI will give you more clarity than you expect.
0:13

ONE PROMPT WON'T MAKE YOU RICH👀 It won’t change your life overnight. And it won’t solve all your problems. But the right prompt can do something much more important. It can reveal things you hadn’t noticed before. Most people use AI to find answers. But the most useful prompts work differently. They make you ask yourself questions. > What’s really holding you back? > What decisions have you been putting off for months? > What are you wasting your time on, convincing yourself it’s important? Sometimes, one honest answer is more valuable than a hundred motivational videos and dozens of books. That’s exactly why I liked this prompt. It doesn’t try to impress with complexity. It helps you see your situation from the outside. Spend a few minutes on it. Perhaps a single conversation with AI will give you more clarity than you expect.

kozh ./

24,139 görüntüleme • 2 ay önce

THE LOOP ENGINEERING SETUP THAT LETS CLAUDE RUN YOUR WORK FOR HOURS WITHOUT YOU you sit there babysitting it prompt by prompt other people set the loop up once and let Claude plan, act, verify and fix its own work with nobody at the keyboard that gap is the whole skill of loop engineering the 3 resources that actually teach it, in the order i'd read them: > Claude's "Getting started with loops" - the cleanest entry point, straight from the Claude team ↳ > Claude loop engineering: how to build an agent that works while you sleep - the full roadmap from a single prompt to a loop that runs overnight ↳ > the Loop Engineering orange book - the deep conceptual breakdown, for when you want the whole mental model ↳ entry point, then practice, then the concept. that order saves you a week learn this and the work that eats your whole day starts running without you
0:12

THE LOOP ENGINEERING SETUP THAT LETS CLAUDE RUN YOUR WORK FOR HOURS WITHOUT YOU you sit there babysitting it prompt by prompt other people set the loop up once and let Claude plan, act, verify and fix its own work with nobody at the keyboard that gap is the whole skill of loop engineering the 3 resources that actually teach it, in the order i'd read them: > Claude's "Getting started with loops" - the cleanest entry point, straight from the Claude team ↳ > Claude loop engineering: how to build an agent that works while you sleep - the full roadmap from a single prompt to a loop that runs overnight ↳ > the Loop Engineering orange book - the deep conceptual breakdown, for when you want the whole mental model ↳ entry point, then practice, then the concept. that order saves you a week learn this and the work that eats your whole day starts running without you

Mr. Buzzoni

18,186 görüntüleme • 5 gün önce

FIVE LAYERS OF AGENT ENGINEERING, EACH ONE WRAPS THE ONE BELOW IT. IF YOU SKIP LAYER 2, YOUR LAYER 5 WILL LOOK BROKEN WHEN IT IS ACTUALLY JUST STANDING ON NOTHING. for weeks i debated harness vs loop vs graph like they were competing choices. then a stack diagram made the shape obvious. they are not choices. they are floors. 01 | prompt engineering. the message. unit of work: one input. inputs are role, instructions, examples, format. output is a single raw response. 02 | context engineering. the memory. unit of work: what stays in the window. a curator selects, compresses, and drops from query, docs, memory, prior turns, and tool outputs before the prompt runs. 03 | harness engineering. the machine. unit of work: the machine itself. gather (context + prompt) → LLM → tools or sub-agents → verifier → final response. the article calls this the operating environment. 04 | loop engineering. the system. unit of work: the run. goal + success criteria + max iterations + budget + completion check wrap around one harness pass. failed pass appends results to context and retries. 05 | graph engineering. the topology. unit of work: the graph run. goal + nodes + edges + state schema. graph routes to agent nodes, tool nodes, or human approval. a reviewer node with a different model and fresh context checks the final answer. the wrapping is the whole point. layer 5 assumes layer 4 works. layer 4 assumes layer 3 works. skip layer 2 and layer 3's verifier keeps failing without a clear reason. this is why swapping the model is a one-day project and swapping the stack is a quarter. the model is the commodity. the five layers around it are the engineering. full three-layer breakdown of the top of the stack (harness, loop, graph) in the post below.
0:20

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

kocer

30,675 görüntüleme • 14 gün önce

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.
0:16

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

shmidt

19,505 görüntüleme • 1 ay önce

Your body fat is a tank with a tap on it, and the tap narrows as the tank empties. - Plenty of fat: your body covers almost any deficit you ask it to - Getting leaner: it covers less each day - Properly lean: it covers very little, and the rest comes off the plate Which is why the first stone comes off while you barely notice, and the last one takes everything you have. So when you are lean, the shortfall has to arrive as food. And the industry hands you the wrong bag. Push the protein. Two hundred grams. Two fifty. Chicken breast on a kitchen scale. Past what you build with, protein is a fuel your liver has to strip the nitrogen off before you can use a calorie of it, and that machinery has a speed limit. So the extra hundred grams builds nothing and lifts nothing. Protein is what you build with. Fat and carbohydrate are what you lift with. Cut them both to make room for another shake and you have removed the thing that was moving the weight. Fat wins that choice. Twice the energy per gram. Leaves insulin alone, so the fat you are burning is not told to stay put every three hours. Keeps you full. And it is the same fuel your own stores are already releasing. Eat the fat. It is the one thing on the plate that matters more the leaner you get, and the first thing they told you to cut.
0:17

Your body fat is a tank with a tap on it, and the tap narrows as the tank empties. - Plenty of fat: your body covers almost any deficit you ask it to - Getting leaner: it covers less each day - Properly lean: it covers very little, and the rest comes off the plate Which is why the first stone comes off while you barely notice, and the last one takes everything you have. So when you are lean, the shortfall has to arrive as food. And the industry hands you the wrong bag. Push the protein. Two hundred grams. Two fifty. Chicken breast on a kitchen scale. Past what you build with, protein is a fuel your liver has to strip the nitrogen off before you can use a calorie of it, and that machinery has a speed limit. So the extra hundred grams builds nothing and lifts nothing. Protein is what you build with. Fat and carbohydrate are what you lift with. Cut them both to make room for another shake and you have removed the thing that was moving the weight. Fat wins that choice. Twice the energy per gram. Leaves insulin alone, so the fat you are burning is not told to stay put every three hours. Keeps you full. And it is the same fuel your own stores are already releasing. Eat the fat. It is the one thing on the plate that matters more the leaner you get, and the first thing they told you to cut.

Sama Hoole

23,527 görüntüleme • 27 gün önce

There is nothing more valuable than your time. And yet it is time that most goes to waste. Money can’t give you more time. But money can get you the time of others. And that time is worth much much more than most folks are being compensated in exchange for it. You can’t get that time back. The majority believing there is little value for their time is part of how those who do assign high value to their own time keep their control. Time is a real resource. Money is a social construct. One of the two is much more valuable. But what do I know, I’m just a silly girl with hand puppets.
0:18

There is nothing more valuable than your time. And yet it is time that most goes to waste. Money can’t give you more time. But money can get you the time of others. And that time is worth much much more than most folks are being compensated in exchange for it. You can’t get that time back. The majority believing there is little value for their time is part of how those who do assign high value to their own time keep their control. Time is a real resource. Money is a social construct. One of the two is much more valuable. But what do I know, I’m just a silly girl with hand puppets.

Liz Katz

76,299 görüntüleme • 1 ay önce

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓
0:15

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓

Argona

891,251 görüntüleme • 1 ay önce

The most boring bot on Polymarket is the most reliable one. It's a sweeper. It doesn't predict anything. But it prints me ~$11k /month PASSSIVELY. My public wallet: < It waits until the outcome is ALREADY decided, then buys a sure thing for less than a dollar. Here's the whole idea: When BTC has clearly closed above the line with seconds left, that share is worth $1. But someone's still selling it at 99c. You buy it. You redeem it at a dollar. The gap is yours. No forecast. No coin flip. Just collecting a cent someone left on the table, hundreds of times a day. That's why it runs on crypto markets, the outcomes resolve fast and clean. Full build + code in the article below. Thank me later.
0:16

The most boring bot on Polymarket is the most reliable one. It's a sweeper. It doesn't predict anything. But it prints me ~$11k /month PASSSIVELY. My public wallet: < It waits until the outcome is ALREADY decided, then buys a sure thing for less than a dollar. Here's the whole idea: When BTC has clearly closed above the line with seconds left, that share is worth $1. But someone's still selling it at 99c. You buy it. You redeem it at a dollar. The gap is yours. No forecast. No coin flip. Just collecting a cent someone left on the table, hundreds of times a day. That's why it runs on crypto markets, the outcomes resolve fast and clean. Full build + code in the article below. Thank me later.

Punisher

16,000 görüntüleme • 1 ay önce

COPY is live on Robinhood Chain $COPY CA: 0xac79255f6f404eba14f316e8669d76573a2d7b1e Five walls read a setup before you copy it: how strong the source is, how deep the pool is, whether the market actually turns over, whether the move is still inside the band, and whether there is a fresh mark to trade against. EDGE, DEPTH, TURN, MOMO, PRICE. A wallet you follow buying is not a reason. Most setups die on the first wall, and you get the exact wall that refused it, every time. Every decision is printed. The terminal runs from one process, keeps local state, and half of it needs no key at all. It never predicts a price. It tells you what you would actually be copying. Open source, MIT, runs on your machine. No browser wallet, nothing signs.
0:20

COPY is live on Robinhood Chain $COPY CA: 0xac79255f6f404eba14f316e8669d76573a2d7b1e Five walls read a setup before you copy it: how strong the source is, how deep the pool is, whether the market actually turns over, whether the move is still inside the band, and whether there is a fresh mark to trade against. EDGE, DEPTH, TURN, MOMO, PRICE. A wallet you follow buying is not a reason. Most setups die on the first wall, and you get the exact wall that refused it, every time. Every decision is printed. The terminal runs from one process, keeps local state, and half of it needs no key at all. It never predicts a price. It tells you what you would actually be copying. Open source, MIT, runs on your machine. No browser wallet, nothing signs.

Lunar

107,788 görüntüleme • 3 gün önce

the people running shopify stores are being robbed. they tell you that you need apps for everything. they tell you that you need a monthly bill for every little thing. it is a scam. my stores do not have apps. my stores use sections. it is very fast. it is very clean. you buy it one time and you own it forever. you can use it on all your stores. the app guys hate me for this. they want your money every month. i want you to win. i am giving away one of my top sections today. comment "win" below. i will send it to you. (you must follow me so i can send the link)
0:15

the people running shopify stores are being robbed. they tell you that you need apps for everything. they tell you that you need a monthly bill for every little thing. it is a scam. my stores do not have apps. my stores use sections. it is very fast. it is very clean. you buy it one time and you own it forever. you can use it on all your stores. the app guys hate me for this. they want your money every month. i want you to win. i am giving away one of my top sections today. comment "win" below. i will send it to you. (you must follow me so i can send the link)

George

19,423 görüntüleme • 7 ay önce

this is more useful than my entire degree Elon Musk's rocket company signed a $60,000,000,000 deal for Cursor in June, and eight days ago the two of them put a worker on sale for $200 a month: it gets its own computer in the cloud, signs into your accounts, clicks through your real apps, and hands back finished work instead of a draft for you to paste i ran one against my receipts folder on sunday and got back 14 filed, 2 it held because they needed a card number, and a saved method i never wrote myself Grok Bot is the one you train by doing your own job in front of it, and the whole handover fits in four messages tonight: 1. write out one job you did today the way you would brief a new hire: what has to be finished, which sites and files to work from, what to hand back, and where it stops and asks you 2. let it run once on something safe to get wrong, then correct the result until it is worth your name 3. say "save what we just did as a skill", and add the one rule about what always needs your approval 4. say "run that skill every weekday at 8 and post the result here. if the source is missing, tell me instead of using yesterday's numbers" xAI wrote that order into its own manual: one real job, then the saved method, then the clock. a schedule sitting on top of a method nobody checked replaces two hours of your clicking with two hours of your mistake turns out you never get to pick the brain, and that is the part i would argue about: the manual says there is no model picker for members or admins, no plan to add one, and the bill follows whichever model answered bookmark this, then open the piece below: which jobs deserve a worker of their own, and which ones quietly burn the seat ↓
0:15

this is more useful than my entire degree Elon Musk's rocket company signed a $60,000,000,000 deal for Cursor in June, and eight days ago the two of them put a worker on sale for $200 a month: it gets its own computer in the cloud, signs into your accounts, clicks through your real apps, and hands back finished work instead of a draft for you to paste i ran one against my receipts folder on sunday and got back 14 filed, 2 it held because they needed a card number, and a saved method i never wrote myself Grok Bot is the one you train by doing your own job in front of it, and the whole handover fits in four messages tonight: 1. write out one job you did today the way you would brief a new hire: what has to be finished, which sites and files to work from, what to hand back, and where it stops and asks you 2. let it run once on something safe to get wrong, then correct the result until it is worth your name 3. say "save what we just did as a skill", and add the one rule about what always needs your approval 4. say "run that skill every weekday at 8 and post the result here. if the source is missing, tell me instead of using yesterday's numbers" xAI wrote that order into its own manual: one real job, then the saved method, then the clock. a schedule sitting on top of a method nobody checked replaces two hours of your clicking with two hours of your mistake turns out you never get to pick the brain, and that is the part i would argue about: the manual says there is no model picker for members or admins, no plan to add one, and the bill follows whichever model answered bookmark this, then open the piece below: which jobs deserve a worker of their own, and which ones quietly burn the seat ↓

Argona

21,946 görüntüleme • 25 gün önce

I know you want a design team, and actually the best one - without the hassle of hiring or long-term commitments? That’s exactly what Kree8 is. Just book a Call, and let’s Kree8 it. 👇 We work like your in-house design team. You send in a task - one at a time or two simultaneously (your call), and we get it done. No chasing. No delays. Just clean, high-quality design delivered when you need it.
0:12

I know you want a design team, and actually the best one - without the hassle of hiring or long-term commitments? That’s exactly what Kree8 is. Just book a Call, and let’s Kree8 it. 👇 We work like your in-house design team. You send in a task - one at a time or two simultaneously (your call), and we get it done. No chasing. No delays. Just clean, high-quality design delivered when you need it.

Jay Dwivedi

254,322 görüntüleme • 1 yıl önce

Alright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.
0:15

Alright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.

Google AI

22,487 görüntüleme • 9 ay önce

sorry, they just did WHAT someone gave a machine one disease name, the leading cause of blindness in the developed world with 1.5 million americans already in its path, and it came back pointing at a drug that has sat in pharmacies for years under a different label: 551 papers read in 30 minutes against the 294 hours a human would have needed, and the loop that did it is public on GitHub most agent setups answer one question at a time, so the ceiling on the work is the quality of the question you happened to think of this one was handed a single question and wrote the second one itself. turns out that follow-up is where the real find was: a target called ABCA1, upregulated threefold, in an experiment no human ordered i read the whole paper looking for the trick, and the trick is structural. that is the second question, and it is the gap between an assistant and a factory: - hand the loop a field rather than a task: it was given a disease, and choosing the mechanism was part of its job - make it rank before it spends: 151 papers in, ten candidate mechanisms out, scored against each other before anything touched a bench - split reading from judging, so the agent that forms the theory is a different agent from the one grading it - close every cycle on physical reality: the verdict was an experiment, and another model's opinion was never allowed to stand in for one - feed each result back as the next question rather than a log line, which is the step almost nobody builds - search what already passed inspection first: the winner was an approved compound with a safety file already on record - write down what the round learned before opening the next one, so round two starts where round one stopped my read, and i think it is the uncomfortable one: reading was the entire bottleneck in that field, and everybody spent the decade optimising the writing. people ran every physical experiment here, the analysis agent needs a domain expert writing its prompts, and the authors decline to call this the leap it resembles. the thinking got replaced, and the hands did not so the question i cannot answer for my own setup: which step of your loop still stops dead until you sit down and type something bookmark this one. the four parts that turn one model into a line that runs like this, the queue, the rooms, the write permissions and the gate, are built file by file in the piece below ↓
0:15

sorry, they just did WHAT someone gave a machine one disease name, the leading cause of blindness in the developed world with 1.5 million americans already in its path, and it came back pointing at a drug that has sat in pharmacies for years under a different label: 551 papers read in 30 minutes against the 294 hours a human would have needed, and the loop that did it is public on GitHub most agent setups answer one question at a time, so the ceiling on the work is the quality of the question you happened to think of this one was handed a single question and wrote the second one itself. turns out that follow-up is where the real find was: a target called ABCA1, upregulated threefold, in an experiment no human ordered i read the whole paper looking for the trick, and the trick is structural. that is the second question, and it is the gap between an assistant and a factory: - hand the loop a field rather than a task: it was given a disease, and choosing the mechanism was part of its job - make it rank before it spends: 151 papers in, ten candidate mechanisms out, scored against each other before anything touched a bench - split reading from judging, so the agent that forms the theory is a different agent from the one grading it - close every cycle on physical reality: the verdict was an experiment, and another model's opinion was never allowed to stand in for one - feed each result back as the next question rather than a log line, which is the step almost nobody builds - search what already passed inspection first: the winner was an approved compound with a safety file already on record - write down what the round learned before opening the next one, so round two starts where round one stopped my read, and i think it is the uncomfortable one: reading was the entire bottleneck in that field, and everybody spent the decade optimising the writing. people ran every physical experiment here, the analysis agent needs a domain expert writing its prompts, and the authors decline to call this the leap it resembles. the thinking got replaced, and the hands did not so the question i cannot answer for my own setup: which step of your loop still stops dead until you sit down and type something bookmark this one. the four parts that turn one model into a line that runs like this, the queue, the rooms, the write permissions and the gate, are built file by file in the piece below ↓

Argona

32,475 görüntüleme • 1 ay önce

"Heavy lifting is dangerous at your age" is the most harmful sentence in the field, and a doctor, a physio or a well-meaning relative hands it out every day. Follow it and watch what it does. From your forties you lose muscle every year unless you fight for it. That decline is the whole game: the difference between carrying your own shopping at 80 and waiting for someone to carry it for you. Muscle you don't load shrinks. Bone no longer pulled on turns brittle. Balance you never challenge drains away. Two years of "taking it easy" and you have built the exact frail body everyone feared. The advice didn't prevent the fall. It built the person who couldn't survive one. And here is the lie inside it. Supervised resistance training has one of the lowest injury rates of anything an older adult does. Lower than gardening. Lower than a wet pavement. Lower than the stairs you climb without thinking. So instead they steer you to pilates, aqua aerobics, a gentle tai chi class. Pleasant, sociable, and none of it loads a muscle hard enough to stop it wasting. You feel active while the decline rolls on regardless. Strength is not vanity at this age. It is the garden you kneel in, the stairs you keep, the grandchild you lift. Independence with the years added on. Frightened of a barbell? Fine. You don't need one. Machines are built for exactly this. Fixed path, nothing to wobble sideways. You sit, you're supported, you push. When a set gets hard you stop, and the machine holds the weight, not your spine. A leg press loads your legs as heavy as you'll ever need with almost no way to hurt yourself. Same with a chest press, a row, a pulldown. The decline is coming for everyone. You train against it or you hand years of your life away. The safest tool for the job sits unused in every gym, while the people who need it most get a rubber band and a spot in the church hall. Careful is what's killing them.
0:19

"Heavy lifting is dangerous at your age" is the most harmful sentence in the field, and a doctor, a physio or a well-meaning relative hands it out every day. Follow it and watch what it does. From your forties you lose muscle every year unless you fight for it. That decline is the whole game: the difference between carrying your own shopping at 80 and waiting for someone to carry it for you. Muscle you don't load shrinks. Bone no longer pulled on turns brittle. Balance you never challenge drains away. Two years of "taking it easy" and you have built the exact frail body everyone feared. The advice didn't prevent the fall. It built the person who couldn't survive one. And here is the lie inside it. Supervised resistance training has one of the lowest injury rates of anything an older adult does. Lower than gardening. Lower than a wet pavement. Lower than the stairs you climb without thinking. So instead they steer you to pilates, aqua aerobics, a gentle tai chi class. Pleasant, sociable, and none of it loads a muscle hard enough to stop it wasting. You feel active while the decline rolls on regardless. Strength is not vanity at this age. It is the garden you kneel in, the stairs you keep, the grandchild you lift. Independence with the years added on. Frightened of a barbell? Fine. You don't need one. Machines are built for exactly this. Fixed path, nothing to wobble sideways. You sit, you're supported, you push. When a set gets hard you stop, and the machine holds the weight, not your spine. A leg press loads your legs as heavy as you'll ever need with almost no way to hurt yourself. Same with a chest press, a row, a pulldown. The decline is coming for everyone. You train against it or you hand years of your life away. The safest tool for the job sits unused in every gym, while the people who need it most get a rubber band and a spot in the church hall. Careful is what's killing them.

Sama Hoole

14,532 görüntüleme • 2 ay önce

The advice on lifting weights runs backwards. It gets gentler at exactly the rate the danger gets worse. Young, with muscle to spare, you are told to lift heavy. Middle-aged, losing about 1 per cent of it a year, you are told to keep active. Older, with the bone thinning, you are told to try swimming. Older still, when a fall is the thing most likely to end your independence, you are handed a resistance band the colour of a boiled sweet. Old, when a broken hip kills 1 in 4 within the year, you are told to sit down. Then you are told you did well to get here. Grip strength predicts how long you will live better than your blood pressure does. Nobody has ever been prescribed a heavier bar for it. The muscle you have in old age is the muscle you built and kept. It is the only pension that pays out in getting off the floor. The body asks for load harder every decade. The guidance answers with a chair. The people who need the heavy weights most are the only people told not to touch one.
0:16

The advice on lifting weights runs backwards. It gets gentler at exactly the rate the danger gets worse. Young, with muscle to spare, you are told to lift heavy. Middle-aged, losing about 1 per cent of it a year, you are told to keep active. Older, with the bone thinning, you are told to try swimming. Older still, when a fall is the thing most likely to end your independence, you are handed a resistance band the colour of a boiled sweet. Old, when a broken hip kills 1 in 4 within the year, you are told to sit down. Then you are told you did well to get here. Grip strength predicts how long you will live better than your blood pressure does. Nobody has ever been prescribed a heavier bar for it. The muscle you have in old age is the muscle you built and kept. It is the only pension that pays out in getting off the floor. The body asks for load harder every decade. The guidance answers with a chair. The people who need the heavy weights most are the only people told not to touch one.

Sama Hoole

65,392 görüntüleme • 5 gün önce

1 Neural Network + Obsidian + Karpathy’s 1-file method = the most unhinged second brain build of 2026. It remembers everything you’ve ever done, and it costs $0 on top of what you already pay. The base is Karpathy’s append and review: 1 giant note, new thoughts stack on top, old ones sink, every few days you reread and pull the survivors back up. No folders, no tags, no plugins the rereading IS the system, because review is what turns storage into thinking. The flaw: past 10,000 lines, no human rereads anything. That’s where the neural network takes over. You keep the note in Obsidian 1 vault, everything dumps to the top: ideas, links, meeting fragments, half-thoughts. You never organize, you only dump. It all lives as plain markdown on your own disk, and that detail is the whole trick. Because now you point Claude Code at the vault folder, and it reads every line you’ve ever written. “What did I think about pricing in March.” “Find the 3 ideas I keep circling.” “What did I drop that deserves a second look.” It answers from YOUR notes, with quotes, in 15 seconds. Then once a week, 1 prompt closes the loop: read the last 7 days, surface the 5 entries worth pulling back up, flag anything that contradicts what I wrote a month ago. The model does the sinking and surfacing Karpathy did by hand, and the note stays alive instead of turning into a graveyard. Week 1 feels like nothing. Week 4 you hit the first “I already solved this in January.” Month 3 you consult your past self more than Google. Most second brains die in 11 days under 40 plugins and 200 folders. This one is 1 file and a loop, and it compounds because dumping takes 0 discipline. Notion stores what you thought. This thing argues back.
0:16

1 Neural Network + Obsidian + Karpathy’s 1-file method = the most unhinged second brain build of 2026. It remembers everything you’ve ever done, and it costs $0 on top of what you already pay. The base is Karpathy’s append and review: 1 giant note, new thoughts stack on top, old ones sink, every few days you reread and pull the survivors back up. No folders, no tags, no plugins the rereading IS the system, because review is what turns storage into thinking. The flaw: past 10,000 lines, no human rereads anything. That’s where the neural network takes over. You keep the note in Obsidian 1 vault, everything dumps to the top: ideas, links, meeting fragments, half-thoughts. You never organize, you only dump. It all lives as plain markdown on your own disk, and that detail is the whole trick. Because now you point Claude Code at the vault folder, and it reads every line you’ve ever written. “What did I think about pricing in March.” “Find the 3 ideas I keep circling.” “What did I drop that deserves a second look.” It answers from YOUR notes, with quotes, in 15 seconds. Then once a week, 1 prompt closes the loop: read the last 7 days, surface the 5 entries worth pulling back up, flag anything that contradicts what I wrote a month ago. The model does the sinking and surfacing Karpathy did by hand, and the note stays alive instead of turning into a graveyard. Week 1 feels like nothing. Week 4 you hit the first “I already solved this in January.” Month 3 you consult your past self more than Google. Most second brains die in 11 days under 40 plugins and 200 folders. This one is 1 file and a loop, and it compounds because dumping takes 0 discipline. Notion stores what you thought. This thing argues back.

West Lord

24,679 görüntüleme • 1 ay önce