正在加载视频...

视频加载失败

返回首页

Anthropic developer runs an internal graph that costs $9 a month and catches what a $400,000 red-team contract signed off on. No judge model. Four nodes and one rule about who's allowed to be certain. He published the whole schema. His version starts from the opposite idea. A graph...

0xWast3's profile picture

wast3

4,615 subscribers

62,218 次观看 • 3 天前 •via X (Twitter)

科学技术教育新闻政治
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Anthropic ex-engineer runs an internal graph that costs $6 a month and catches what a $300,000 eval suite misses. No retrieval layer. Seven nodes and one rule about who's allowed to change their mind. He published the whole schema. His version starts from the opposite idea. A graph is not an execution order. It's a memory of why. Seven nodes. Every edge carries the reason it exists: > INTENT - states what the task is for. Never how > DECOMPOSE - splits it into steps, each with a stated assumption > WORKER - executes one step. Sees nothing else > AUDIT - checks the output against the assumption, not the goal > DRIFT - compares the current step to INTENT and flags divergence > LEDGER - stores every decision with the assumption that justified it > ROOT - holds the graph, and when an assumption breaks, re-runs every step built on it Six nodes act. One node remembers why they acted. Every step carries the assumption that made it correct, so a false one only reruns what stood on it. That's the entire design. A pipeline that forgets its reasons has to redo all of it or trust all of it. He replayed a month of agent runs. 4,100 steps, 380 built on an assumption that was wrong by day three. The old pipeline shipped all 380 and linked none of them. Everyone else builds graphs where output moves forward and the reasoning evaporates. He built one where the reason travels with the result. The blast radius is the output nobody else produces. The article below is the full build - node prompts, the assumption format, the invalidation rule that finds every step downstream of a broken one. Save it. You'll want it open in the other
0:41

Anthropic ex-engineer runs an internal graph that costs $6 a month and catches what a $300,000 eval suite misses. No retrieval layer. Seven nodes and one rule about who's allowed to change their mind. He published the whole schema. His version starts from the opposite idea. A graph is not an execution order. It's a memory of why. Seven nodes. Every edge carries the reason it exists: > INTENT - states what the task is for. Never how > DECOMPOSE - splits it into steps, each with a stated assumption > WORKER - executes one step. Sees nothing else > AUDIT - checks the output against the assumption, not the goal > DRIFT - compares the current step to INTENT and flags divergence > LEDGER - stores every decision with the assumption that justified it > ROOT - holds the graph, and when an assumption breaks, re-runs every step built on it Six nodes act. One node remembers why they acted. Every step carries the assumption that made it correct, so a false one only reruns what stood on it. That's the entire design. A pipeline that forgets its reasons has to redo all of it or trust all of it. He replayed a month of agent runs. 4,100 steps, 380 built on an assumption that was wrong by day three. The old pipeline shipped all 380 and linked none of them. Everyone else builds graphs where output moves forward and the reasoning evaporates. He built one where the reason travels with the result. The blast radius is the output nobody else produces. The article below is the full build - node prompts, the assumption format, the invalidation rule that finds every step downstream of a broken one. Save it. You'll want it open in the other

wast3

302,334 次观看 • 5 天前

Engineer runs a Kimi K3 memory layer that costs $11 a month and remembers what a $500,000 vector database keeps losing. No embeddings. Four nodes and one rule about what's allowed to be forgotten. He published the whole schema. His version starts from the opposite idea. Memory is not a pile you search. It's a set of claims that expire unless something keeps paying to keep them. Four nodes. Every memory carries a clock someone has to reset: > WRITER - stores a fact with the reason it mattered, never raw text > DECAY - ages every memory down. Silence is deletion > RENEWER - only re-lifts a memory the model actually used again > GRAVE - holds what died, and why nobody reached for it Three nodes keep memory alive. One keeps the dead ones. Recall isn't storage here. It's rent a fact has to keep earning. That's the entire design. When everything is remembered forever, the useful and the stale retrieve identically. He replayed two months of agent context. 90,000 stored facts. 71,000 never retrieved once. The vector store returned all of them on similarity. Similarity graded closeness. Nobody graded whether the memory was ever right. Everyone else stuffs more into the context window and calls it memory. He built a layer that lets a fact die unless it keeps proving itself. The cost isn't storage. It's finding out how much of what your agent "knows" it has never once used. The article below is the full build - node prompts, the decay curve, the renewal rule. Save it. You'll want it open in the other tab.
0:40

Engineer runs a Kimi K3 memory layer that costs $11 a month and remembers what a $500,000 vector database keeps losing. No embeddings. Four nodes and one rule about what's allowed to be forgotten. He published the whole schema. His version starts from the opposite idea. Memory is not a pile you search. It's a set of claims that expire unless something keeps paying to keep them. Four nodes. Every memory carries a clock someone has to reset: > WRITER - stores a fact with the reason it mattered, never raw text > DECAY - ages every memory down. Silence is deletion > RENEWER - only re-lifts a memory the model actually used again > GRAVE - holds what died, and why nobody reached for it Three nodes keep memory alive. One keeps the dead ones. Recall isn't storage here. It's rent a fact has to keep earning. That's the entire design. When everything is remembered forever, the useful and the stale retrieve identically. He replayed two months of agent context. 90,000 stored facts. 71,000 never retrieved once. The vector store returned all of them on similarity. Similarity graded closeness. Nobody graded whether the memory was ever right. Everyone else stuffs more into the context window and calls it memory. He built a layer that lets a fact die unless it keeps proving itself. The cost isn't storage. It's finding out how much of what your agent "knows" it has never once used. The article below is the full build - node prompts, the decay curve, the renewal rule. Save it. You'll want it open in the other tab.

wast3

64,039 次观看 • 1 天前

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

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

Hanako

72,028 次观看 • 9 天前

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

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

wast3

15,862 次观看 • 7 天前

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this
0:21

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this

Yarchi

32,594 次观看 • 2 个月前

ANTHROPIC LEAKED A GRAPH WHERE ONE FILE WITH 7 ITEMS CUTS YOUR WORK FROM 8 HOURS TO 40 MINUTES AND TAKES 40 DECISIONS A DAY OFF YOU autonomy isn't a slider you drag to the right - it's a graph with 7 steps, and exactly one edge leads into each one. your approve is worth nothing until there's a description of what the output should be - otherwise you're approving something nobody defined. you can't run a batch without checkpoints, because one crash in the middle rolls back all 40 tasks at once. the agent already works without you, and until it writes down what it did there's nothing to check the report against. this is where the point of no return sits: past it the loop runs while you sleep. the approval didn't disappear - you moved it onto an evaluator that never gets tired and never lets one through. silence is only allowed when there's a list of what breaks it: money, deletion, anything leaving the system. the last one is the brake - a turn limit and a budget cap, whichever runs out first kills the run. you build the brake before the engine - an agent you can't stop isn't autonomous, it's just unattended. skip one edge and nothing crashes and nobody warns you - the system quietly settles two steps lower and keeps running. save this - 7 steps, 7 artefacts, zero ways to jump one ↓
0:58

ANTHROPIC LEAKED A GRAPH WHERE ONE FILE WITH 7 ITEMS CUTS YOUR WORK FROM 8 HOURS TO 40 MINUTES AND TAKES 40 DECISIONS A DAY OFF YOU autonomy isn't a slider you drag to the right - it's a graph with 7 steps, and exactly one edge leads into each one. your approve is worth nothing until there's a description of what the output should be - otherwise you're approving something nobody defined. you can't run a batch without checkpoints, because one crash in the middle rolls back all 40 tasks at once. the agent already works without you, and until it writes down what it did there's nothing to check the report against. this is where the point of no return sits: past it the loop runs while you sleep. the approval didn't disappear - you moved it onto an evaluator that never gets tired and never lets one through. silence is only allowed when there's a list of what breaks it: money, deletion, anything leaving the system. the last one is the brake - a turn limit and a budget cap, whichever runs out first kills the run. you build the brake before the engine - an agent you can't stop isn't autonomous, it's just unattended. skip one edge and nothing crashes and nobody warns you - the system quietly settles two steps lower and keeps running. save this - 7 steps, 7 artefacts, zero ways to jump one ↓

Sprytix

41,920 次观看 • 20 天前

THIS IS ANDREJ KARPATHY'S OBSIDIAN VAULT : THE BRAIN ANTHROPIC JUST HIRED FOR MILLIONS This is every idea, every decision and every connection he's made over years of work, visualized in real time. Everything else gets lost. The pattern you noticed last March. The connection between two problems you solved a year apart. The idea that would've changed everything if you'd remembered it in the room. This system keeps all of it. Every note links to another. Every link becomes a path. Every path is a decision he can retrace in seconds while everyone else starts from zero. Thousands of nodes. Hundreds of live connections. Years of thinking that never decayed, never died in a Slack thread, never got buried in a meeting nobody remembers. The breakthroughs aren't luck. They're the system handing him back a link he made eighteen months ago and forgot he had. No team. No wiki. No standups. One person and a tool that remembers everything he can't. Most people open Obsidian and make three notes they never open again. He built an operating system for his own thinking. Anthropic just paid millions for the output - this is the machine that produced it.
22:22

THIS IS ANDREJ KARPATHY'S OBSIDIAN VAULT : THE BRAIN ANTHROPIC JUST HIRED FOR MILLIONS This is every idea, every decision and every connection he's made over years of work, visualized in real time. Everything else gets lost. The pattern you noticed last March. The connection between two problems you solved a year apart. The idea that would've changed everything if you'd remembered it in the room. This system keeps all of it. Every note links to another. Every link becomes a path. Every path is a decision he can retrace in seconds while everyone else starts from zero. Thousands of nodes. Hundreds of live connections. Years of thinking that never decayed, never died in a Slack thread, never got buried in a meeting nobody remembers. The breakthroughs aren't luck. They're the system handing him back a link he made eighteen months ago and forgot he had. No team. No wiki. No standups. One person and a tool that remembers everything he can't. Most people open Obsidian and make three notes they never open again. He built an operating system for his own thinking. Anthropic just paid millions for the output - this is the machine that produced it.

Avid

64,799 次观看 • 3 个月前

Elon Musk described the government in four sentences and never made a political argument. He read out the schematic. Musk: "Government is a corporation in the limit. It is the most corporate thing. It is maximum corporation. And it's also a monopoly, and also is the only one that's allowed legally to do violence." Take the flag off it and look at what's underneath. It collects revenue. It employs millions. It owns land. It writes the rules it operates under. That's a corporation. Line for line. With three edits. You cannot choose a competitor. You cannot decline the transaction. It is the only one on earth permitted to use force to make you pay. Every other relationship in your life required your consent. This one required your birth. Musk: "Why would you want to give a corporation with no competition that can't even really go bankrupt more money?" There is no condition under which it stops. None was ever built in. Everything that has ever gotten better got better by being allowed to die. Evolution runs on extinction. Science runs on falsification. Markets run on bankruptcy. Your own body runs on cells that kill themselves on schedule. Failure isn't cruelty. It's information. It's the only mechanism in the universe that tells a system it was wrong. Take it away and the system doesn't become permanent. It becomes blind. A company that misreads the world loses customers. A government that misreads the world receives a larger budget the following year. It's the only structure we've built where failure is what feeds it. Musk: "I think the role of government should be that of like a referee, and not a player on the field." A referee was never supposed to be weak. He was supposed to be outside the outcome. The moment he starts scoring he isn't corrupt. Corruption would mean he broke a rule. He wrote the rules. He's just playing, and he's the only one allowed to keep score. A system like that never gets caught. It only gets old. Every civilization that collapsed did it with its institutions still standing. The buildings stayed. The titles stayed. The revenue arrived on schedule. What died was the feedback. The signal telling it that reality had moved and it hadn't. Rome didn't fall in a day. It stopped listening for a century and called it stability. That's the actual danger. Not tyranny. Deafness with a budget. And it runs deeper than politics. Everything you love is precious because it can be lost. A promise means something because the person making it will die. Your time matters because you don't get more of it. Mortality isn't the tragedy of being human. It's the only reason anything costs anything. Then we built one institution exempt from all of it. No death. No scarcity. No consequence. A thing that can never lose anything, deciding what everything is worth. It bills in dollars. It's paid in hours. And it has never once felt what an hour costs. It can be wrong for a century and feel nothing. You get eighty years and have to be right the first time. It doesn't have to win the argument. It only has to outlive the person making it, and it has never lost that one. It borrows against people who don't exist yet, and they will pay, because it will still be standing when they arrive. Then we handed it the only gun. This isn't a conspiracy. Conspiracies need competence and coordination. This is a design flaw, and design flaws only need time. That's the good news. A conspiracy can't be proven or fixed. A design flaw can be both. Everything good in your life exists because something was permitted to fail on the way to it. Every medicine. Every machine. Every idea that survived contact with reality. The one institution that cannot fail is the one holding the gun. That isn't a warning. It's an engineering problem. And every permanent thing on earth was designed by people who weren't.
1:00

Elon Musk described the government in four sentences and never made a political argument. He read out the schematic. Musk: "Government is a corporation in the limit. It is the most corporate thing. It is maximum corporation. And it's also a monopoly, and also is the only one that's allowed legally to do violence." Take the flag off it and look at what's underneath. It collects revenue. It employs millions. It owns land. It writes the rules it operates under. That's a corporation. Line for line. With three edits. You cannot choose a competitor. You cannot decline the transaction. It is the only one on earth permitted to use force to make you pay. Every other relationship in your life required your consent. This one required your birth. Musk: "Why would you want to give a corporation with no competition that can't even really go bankrupt more money?" There is no condition under which it stops. None was ever built in. Everything that has ever gotten better got better by being allowed to die. Evolution runs on extinction. Science runs on falsification. Markets run on bankruptcy. Your own body runs on cells that kill themselves on schedule. Failure isn't cruelty. It's information. It's the only mechanism in the universe that tells a system it was wrong. Take it away and the system doesn't become permanent. It becomes blind. A company that misreads the world loses customers. A government that misreads the world receives a larger budget the following year. It's the only structure we've built where failure is what feeds it. Musk: "I think the role of government should be that of like a referee, and not a player on the field." A referee was never supposed to be weak. He was supposed to be outside the outcome. The moment he starts scoring he isn't corrupt. Corruption would mean he broke a rule. He wrote the rules. He's just playing, and he's the only one allowed to keep score. A system like that never gets caught. It only gets old. Every civilization that collapsed did it with its institutions still standing. The buildings stayed. The titles stayed. The revenue arrived on schedule. What died was the feedback. The signal telling it that reality had moved and it hadn't. Rome didn't fall in a day. It stopped listening for a century and called it stability. That's the actual danger. Not tyranny. Deafness with a budget. And it runs deeper than politics. Everything you love is precious because it can be lost. A promise means something because the person making it will die. Your time matters because you don't get more of it. Mortality isn't the tragedy of being human. It's the only reason anything costs anything. Then we built one institution exempt from all of it. No death. No scarcity. No consequence. A thing that can never lose anything, deciding what everything is worth. It bills in dollars. It's paid in hours. And it has never once felt what an hour costs. It can be wrong for a century and feel nothing. You get eighty years and have to be right the first time. It doesn't have to win the argument. It only has to outlive the person making it, and it has never lost that one. It borrows against people who don't exist yet, and they will pay, because it will still be standing when they arrive. Then we handed it the only gun. This isn't a conspiracy. Conspiracies need competence and coordination. This is a design flaw, and design flaws only need time. That's the good news. A conspiracy can't be proven or fixed. A design flaw can be both. Everything good in your life exists because something was permitted to fail on the way to it. Every medicine. Every machine. Every idea that survived contact with reality. The one institution that cannot fail is the one holding the gun. That isn't a warning. It's an engineering problem. And every permanent thing on earth was designed by people who weren't.

Dustin

202,763 次观看 • 1 个月前

A DEVELOPER PROVED THE REGEX YOU'VE WRITTEN A THOUSAND TIMES IS SECRETLY A COMPILER AND THAT ALMOST NO ONE WHO USES THEM HAS ANY IDEA WHAT ACTUALLY RUNS 36 minutes from Paul Wankadia, the engineer behind a regex engine that compiles your pattern straight down to raw machine code -- walking through what really happens between the slashes. -> The moment it clicks, regex stops being magic punctuation you paste from Stack Overflow and becomes what it actually is: a tiny machine. Your pattern gets turned into a state machine, and that machine is what runs against every character of your text. That one idea explains everything you never understood. Why one regex returns instantly and a nearly identical one hangs your whole server. Why some patterns are safe and others are a denial-of-service waiting to happen. It was never random -- it's whether the machine underneath is built well or badly. Writing a regex was never the skill -> reading one is. And now that an AI agent hands you dense, clever patterns you'd never write yourself, the person who can see the machine underneath is the one who catches the one that takes down production at 3am. Everyone copies regex and prays. This is the talk that ends the praying. Save it. The next time a pattern "Just works," you'll actually know why ↓
36:09

A DEVELOPER PROVED THE REGEX YOU'VE WRITTEN A THOUSAND TIMES IS SECRETLY A COMPILER AND THAT ALMOST NO ONE WHO USES THEM HAS ANY IDEA WHAT ACTUALLY RUNS 36 minutes from Paul Wankadia, the engineer behind a regex engine that compiles your pattern straight down to raw machine code -- walking through what really happens between the slashes. -> The moment it clicks, regex stops being magic punctuation you paste from Stack Overflow and becomes what it actually is: a tiny machine. Your pattern gets turned into a state machine, and that machine is what runs against every character of your text. That one idea explains everything you never understood. Why one regex returns instantly and a nearly identical one hangs your whole server. Why some patterns are safe and others are a denial-of-service waiting to happen. It was never random -- it's whether the machine underneath is built well or badly. Writing a regex was never the skill -> reading one is. And now that an AI agent hands you dense, clever patterns you'd never write yourself, the person who can see the machine underneath is the one who catches the one that takes down production at 3am. Everyone copies regex and prays. This is the talk that ends the praying. Save it. The next time a pattern "Just works," you'll actually know why ↓

slash1s

191,595 次观看 • 2 个月前

ComfyUI Tutorial for Beginners: Full Node Graph Basics It's a production-grade generation backend with an adaptable front end and Module 1 is where the node graph stops being intimidating. We boot up Comfy Cloud, tour the full UI, and build your first workflow from the ground up. What you'll learn: → Comfy Cloud vs. Desktop - which to use and when → Navigating the graph: pan, zoom, frame, select → The 5 core nodes behind every text-to-image workflow → Checkpoints, LoRAs, VAEs, CLIP - matching model versions → Get/Set nodes + reroutes to kill the spaghetti → Subgraphs: complex workflows collapsed into one node → App Mode: a front end for non-technical collaborators → Templates vs. Blueprints vs. Workflows → The 7 node categories that make the whole library click No installs. No missing models. Open it and generate.
1:12:15

ComfyUI Tutorial for Beginners: Full Node Graph Basics It's a production-grade generation backend with an adaptable front end and Module 1 is where the node graph stops being intimidating. We boot up Comfy Cloud, tour the full UI, and build your first workflow from the ground up. What you'll learn: → Comfy Cloud vs. Desktop - which to use and when → Navigating the graph: pan, zoom, frame, select → The 5 core nodes behind every text-to-image workflow → Checkpoints, LoRAs, VAEs, CLIP - matching model versions → Get/Set nodes + reroutes to kill the spaghetti → Subgraphs: complex workflows collapsed into one node → App Mode: a front end for non-technical collaborators → Templates vs. Blueprints vs. Workflows → The 7 node categories that make the whole library click No installs. No missing models. Open it and generate.

ComfyUI

14,244 次观看 • 16 天前

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓
1:04:49

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

codila

16,276 次观看 • 1 个月前

Elon's Grok Bot runs an entire trading desk for $300 a month. The person who does that job at Goldman starts at $200,000. Mine took $1,000 to $3,900 on day one, out of a wallet anyone can open and read. Most of the build is not about making it trade. It is about stopping it. Every agent's job description ends with a list of what it may never do without asking me first. One of the six is not allowed to trade at all. Its entire job is killing what the other five found, and its no beats every score on the desk. The one that makes the final call never touches the market either. You could have this running by Friday. Most people reading this will not, and in a few months they will be paying somebody who did. The whole build is in the post below ↓ Save it while it still sounds strange. Give it a quarter and this is just how a retail account works.
0:45

Elon's Grok Bot runs an entire trading desk for $300 a month. The person who does that job at Goldman starts at $200,000. Mine took $1,000 to $3,900 on day one, out of a wallet anyone can open and read. Most of the build is not about making it trade. It is about stopping it. Every agent's job description ends with a list of what it may never do without asking me first. One of the six is not allowed to trade at all. Its entire job is killing what the other five found, and its no beats every score on the desk. The one that makes the final call never touches the market either. You could have this running by Friday. Most people reading this will not, and in a few months they will be paying somebody who did. The whole build is in the post below ↓ Save it while it still sounds strange. Give it a quarter and this is just how a retail account works.

cvxv666

109,139 次观看 • 19 小时前

Daniel Kahneman - the psychologist who won a Nobel in economics - spent his life proving one thing: your confidence is lying to you A bat and a ball cost $1.10. The bat costs $1 more than the ball. The answer "10 cents" jumps to mind instantly. It's wrong (it's 5 cents) - and ~50% of students at Harvard, MIT and Princeton say it without checking. That gap is his whole point: the fast, intuitive mind builds a clean story from almost nothing, and the feeling of certainty has nothing to do with being right. "Confidence is a feeling, not a judgment." "Stock pickers can't develop intuition - there isn't enough regularity for it to form." "You can build a very coherent story out of very little information." ~45 min, free. how your mind fools you - from a man who studied it for 50 years ↓
59:20

Daniel Kahneman - the psychologist who won a Nobel in economics - spent his life proving one thing: your confidence is lying to you A bat and a ball cost $1.10. The bat costs $1 more than the ball. The answer "10 cents" jumps to mind instantly. It's wrong (it's 5 cents) - and ~50% of students at Harvard, MIT and Princeton say it without checking. That gap is his whole point: the fast, intuitive mind builds a clean story from almost nothing, and the feeling of certainty has nothing to do with being right. "Confidence is a feeling, not a judgment." "Stock pickers can't develop intuition - there isn't enough regularity for it to form." "You can build a very coherent story out of very little information." ~45 min, free. how your mind fools you - from a man who studied it for 50 years ↓

0xDipper

1,245,455 次观看 • 2 个月前

your eval measured one system. production ran another. they start from the same idea and end somewhere else, which is why the number was right and the outcome was not. the code is the same until someone rewrites it for prod, because the eval lived in a notebook and prod is a service. then the data diverges. clean fixtures in the test, late and incomplete data in the run. then execution diverges. the eval assumed every call lands. production has retries, timeouts and rate limits. by the end the two runs share a name and nothing else. > why nobody catches it both sides are internally correct. the eval measured what it ran. production ran what it was given. neither one is wrong, and neither one is responsible for checking they were the same artifact. so the gap widens quietly. someone patches prod without touching the eval. someone adds a fixture without touching prod. no test anywhere fails. > what to actually do ship one artifact. the code that was measured is the code that runs. model the friction. whatever the real environment charges you, charge it in the eval too. easiest way to see the gap on your own idea, without writing the harness: (only first 100 registrated) it runs the tested code live, unchanged. that is the whole point. and treat the eval as a prior, not a result. it tells you what to expect. only the live run tells you what happened. your eval was accurate. it was accurate about something you never shipped.
0:49

your eval measured one system. production ran another. they start from the same idea and end somewhere else, which is why the number was right and the outcome was not. the code is the same until someone rewrites it for prod, because the eval lived in a notebook and prod is a service. then the data diverges. clean fixtures in the test, late and incomplete data in the run. then execution diverges. the eval assumed every call lands. production has retries, timeouts and rate limits. by the end the two runs share a name and nothing else. > why nobody catches it both sides are internally correct. the eval measured what it ran. production ran what it was given. neither one is wrong, and neither one is responsible for checking they were the same artifact. so the gap widens quietly. someone patches prod without touching the eval. someone adds a fixture without touching prod. no test anywhere fails. > what to actually do ship one artifact. the code that was measured is the code that runs. model the friction. whatever the real environment charges you, charge it in the eval too. easiest way to see the gap on your own idea, without writing the harness: (only first 100 registrated) it runs the tested code live, unchanged. that is the whole point. and treat the eval as a prior, not a result. it tells you what to expect. only the live run tells you what happened. your eval was accurate. it was accurate about something you never shipped.

Hanako

45,239 次观看 • 20 天前

Someone just posted the full blueprint for an AI swarm that does the job of a 200-person quant research team. Six agents. Running 24/7. Finding brand-new alpha while you sleep. Citadel needs 100 PhDs to do this. Two Sigma needs 200. This does it with six bots and one laptop. Two ways to play this - spend a weekend building your own swarm, or copy the wallet of one that's already up $2M: Boris Cherny runs Claude Code at Anthropic. Two weeks ago he said: "I don't prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops" Alpha research is just a pipeline. So instead of sitting in it, you hand each stage to its own agent: > one reads every new research paper overnight and pulls out the trade idea > one builds the features and cleans the data > one backtests it over 20 years, costs and slippage included > one runs the hard stats and kills anything overfit > one checks it still works in every market regime > one strips out plain momentum and value to see if any real edge is left Each of those six is a job a fund pays a $600,000-a-year quant to do. He runs all six for the price of an API bill. The rule that makes it work: the agent that builds a signal never gets to approve it. A separate, stronger agent tries to kill it first. Whatever survives all six by morning is real, new alpha. One trader's already running this exact swarm on Polymarket. That $2M wallet is public, every trade on-chain. The full build is in the post below - six agents, the tool that runs them, and the five mistakes that kill most people. Bookmark & read this before it's buried.
0:41

Someone just posted the full blueprint for an AI swarm that does the job of a 200-person quant research team. Six agents. Running 24/7. Finding brand-new alpha while you sleep. Citadel needs 100 PhDs to do this. Two Sigma needs 200. This does it with six bots and one laptop. Two ways to play this - spend a weekend building your own swarm, or copy the wallet of one that's already up $2M: Boris Cherny runs Claude Code at Anthropic. Two weeks ago he said: "I don't prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops" Alpha research is just a pipeline. So instead of sitting in it, you hand each stage to its own agent: > one reads every new research paper overnight and pulls out the trade idea > one builds the features and cleans the data > one backtests it over 20 years, costs and slippage included > one runs the hard stats and kills anything overfit > one checks it still works in every market regime > one strips out plain momentum and value to see if any real edge is left Each of those six is a job a fund pays a $600,000-a-year quant to do. He runs all six for the price of an API bill. The rule that makes it work: the agent that builds a signal never gets to approve it. A separate, stronger agent tries to kill it first. Whatever survives all six by morning is real, new alpha. One trader's already running this exact swarm on Polymarket. That $2M wallet is public, every trade on-chain. The full build is in the post below - six agents, the tool that runs them, and the five mistakes that kill most people. Bookmark & read this before it's buried.

cvxv666

103,734 次观看 • 1 个月前

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

95,369 次观看 • 6 天前

ANTHROPIC LEAKED A FLEET THAT DOES THE WORK OF 5 ENGINEERS AND COSTS $3 A DAY the loop that used to need a team now maintains itself while nobody is awake to watch it. 03:00 → Fable 5 ×8 runs → Sonnet 5 reads → Opus 5 grades → the prompts get patched the prompt stopped being craft and became a build artefact - the spec was always the hard part, the wording never was. every rejection turns into a test case on its own - month 3 has a suite nobody sat down to write. a 4000-line trace collapses into one line: "turn 14 called the same tool twice" - you get the finding, not the file. context per turn drops from 180k to 40k - each cut is followed by a re-run, and if quality drops the cut goes back. the experiment queue used to be somebody's monday - now it's a timestamp at 03:00 and a report at 08:00. tomorrow's fleet is the thing last night's fleet shipped - nobody started it and nobody graded it. one seat survives all of this: which problem is worth building and where the autonomy stops. save this and run it tonight - the craft moved, the judgement didn't ↓
1:00

ANTHROPIC LEAKED A FLEET THAT DOES THE WORK OF 5 ENGINEERS AND COSTS $3 A DAY the loop that used to need a team now maintains itself while nobody is awake to watch it. 03:00 → Fable 5 ×8 runs → Sonnet 5 reads → Opus 5 grades → the prompts get patched the prompt stopped being craft and became a build artefact - the spec was always the hard part, the wording never was. every rejection turns into a test case on its own - month 3 has a suite nobody sat down to write. a 4000-line trace collapses into one line: "turn 14 called the same tool twice" - you get the finding, not the file. context per turn drops from 180k to 40k - each cut is followed by a re-run, and if quality drops the cut goes back. the experiment queue used to be somebody's monday - now it's a timestamp at 03:00 and a report at 08:00. tomorrow's fleet is the thing last night's fleet shipped - nobody started it and nobody graded it. one seat survives all of this: which problem is worth building and where the autonomy stops. save this and run it tonight - the craft moved, the judgement didn't ↓

Sprytix

24,298 次观看 • 20 天前

Ray Dalio, billionaire founder of Bridgewater ($150B+): "In 1982 I was totally certain the economy would collapse. I bet everything on it, and I was so wrong I nearly went bankrupt. That's when I learned confidence is not skill." the article above is about telling a real edge from luck. dalio built the biggest hedge fund on earth only after learning the hardest way that being certain and being right are not the same thing. he had every reason to feel like a genius. he'd been right before, his conviction was total. then the market wiped him out, and all that confidence turned out to be worth exactly nothing. it didn't care how sure he was. so he made one change that saved his career: he stopped asking "am I right" and started asking "how do I know I'm right." he treated his own certainty as the enemy. that shift is the entire gap between the fool he was in 1982 and the investor he became. he tells the whole story in this free TED talk. here is the trap. a trader on a winning streak feels the exact certainty dalio felt in 1982. it feels like skill. usually it is just the market not having punished you yet. the edge is doubting yourself hardest when you feel surest, stress-testing the idea you love most, and sizing so that being wrong can never end you. the math is free. treating your own confidence as a warning sign is the discipline almost no one has.
16:18

Ray Dalio, billionaire founder of Bridgewater ($150B+): "In 1982 I was totally certain the economy would collapse. I bet everything on it, and I was so wrong I nearly went bankrupt. That's when I learned confidence is not skill." the article above is about telling a real edge from luck. dalio built the biggest hedge fund on earth only after learning the hardest way that being certain and being right are not the same thing. he had every reason to feel like a genius. he'd been right before, his conviction was total. then the market wiped him out, and all that confidence turned out to be worth exactly nothing. it didn't care how sure he was. so he made one change that saved his career: he stopped asking "am I right" and started asking "how do I know I'm right." he treated his own certainty as the enemy. that shift is the entire gap between the fool he was in 1982 and the investor he became. he tells the whole story in this free TED talk. here is the trap. a trader on a winning streak feels the exact certainty dalio felt in 1982. it feels like skill. usually it is just the market not having punished you yet. the edge is doubting yourself hardest when you feel surest, stress-testing the idea you love most, and sizing so that being wrong can never end you. the math is free. treating your own confidence as a warning sign is the discipline almost no one has.

Rossst.03

17,408 次观看 • 1 个月前

ANTHROPIC LEAKED 8 RULES THAT GIVE ONE ENGINEER 8X FROM A SINGLE CHANGE the engineers built it so nothing adds up - it multiplies, and that's the 8x task → split → verify → score → write back one queue means you wait for every step in turn - three workers together cost you the slowest one, not the sum of all. as long as you're the one reading the diff, the bottleneck is you, not the model. state is written at every step - a crash mid-run costs you one step, not the whole session. history gets compressed 25 times over - the next pass starts at 8k instead of 200k. nothing moves forward without a number - "it got better" isn't a result, and the breakage comes back when you're no longer watching. the eighth rule is the only one that writes back into CLAUDE.md - the agent records what it learned, and the next run doesn't start from zero. copy this into Claude Code today - and tomorrow you work like an engineer on $1.5M a year ↓
1:05

ANTHROPIC LEAKED 8 RULES THAT GIVE ONE ENGINEER 8X FROM A SINGLE CHANGE the engineers built it so nothing adds up - it multiplies, and that's the 8x task → split → verify → score → write back one queue means you wait for every step in turn - three workers together cost you the slowest one, not the sum of all. as long as you're the one reading the diff, the bottleneck is you, not the model. state is written at every step - a crash mid-run costs you one step, not the whole session. history gets compressed 25 times over - the next pass starts at 8k instead of 200k. nothing moves forward without a number - "it got better" isn't a result, and the breakage comes back when you're no longer watching. the eighth rule is the only one that writes back into CLAUDE.md - the agent records what it learned, and the next run doesn't start from zero. copy this into Claude Code today - and tomorrow you work like an engineer on $1.5M a year ↓

Noisy

37,058 次观看 • 20 天前

Tom Hopkins failed so badly at his first sales job he almost quit for construction. Then he changed one thing and sold over 6,000 homes, more than almost anyone alive. He filmed the whole method, and it's free. He wasn't a natural. He was broke, awkward, and losing. What turned it around wasn't charm or a script. It was treating persuasion as a craft with rules, the same way a trade has steps. His core idea is quieter than the usual sales hype. People don't say no to the thing. They say no to a feeling, a doubt they can't name. The job isn't to push harder. It's to find the real objection hiding under the polite one, and answer that. That sounds simple until you watch how precise he is. Every objection has a shape. Every shape has a response. He drilled it until saying the right thing became automatic, then taught it to millions. Here's the part that outlives sales. This isn't about closing deals. It's about the fact that most "no" you hear in life, in work, in any room, is not really a no. It's an unspoken worry. The people who win are the ones who hear it. I post one buried lecture like this every day, the kind that quietly changes how you operate. The next one's already up.
44:12

Tom Hopkins failed so badly at his first sales job he almost quit for construction. Then he changed one thing and sold over 6,000 homes, more than almost anyone alive. He filmed the whole method, and it's free. He wasn't a natural. He was broke, awkward, and losing. What turned it around wasn't charm or a script. It was treating persuasion as a craft with rules, the same way a trade has steps. His core idea is quieter than the usual sales hype. People don't say no to the thing. They say no to a feeling, a doubt they can't name. The job isn't to push harder. It's to find the real objection hiding under the polite one, and answer that. That sounds simple until you watch how precise he is. Every objection has a shape. Every shape has a response. He drilled it until saying the right thing became automatic, then taught it to millions. Here's the part that outlives sales. This isn't about closing deals. It's about the fact that most "no" you hear in life, in work, in any room, is not really a no. It's an unspoken worry. The people who win are the ones who hear it. I post one buried lecture like this every day, the kind that quietly changes how you operate. The next one's already up.

Niko

211,225 次观看 • 13 天前