Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Hair Dynamics Broken When Moving Your Model Try This Fix! #BlenderHairFix #HairDynamics #BlenderTipsAndTricks #BlenderSimulation #HairCacheProblem #BlenderShorts #BlenderWorkflowTips #3DAssetReuse #BlenderHairSimulation #BlenderAnimationHack

VFX Grace

2,796 subscribers

11,553 просмотров • 1 год назад •via X (Twitter)

#BlenderHairFix #HairDynamics #BlenderTipsAndTricks #BlenderSimulation #HairCacheProblem #BlenderShorts #BlenderWorkflowTips #3DAssetReuse #BlenderHairSimulation #BlenderAnimationHack

Anya Rossi• Live Now

Private livecam show

Комментарии: 3

Фото профиля Rombout versluijs

Rombout versluijs1 год назад

Clever tip

Фото профиля Phil@TheMFTs

Phil@TheMFTs1 год назад

Dope! Kinda makes me wanna grow digital feathers now 😂

Фото профиля 黑洞

黑洞1 год назад

牛逼啊

Похожие видео

👤 junkyu mon, show us your face! 🐨 if you see my face right now, you’ll go, “who are you?!” 🐨 (laughs) it’s just like that~ 🐨 I planned something to some extent. since my hair is long right now~ I will try to fix my hair this week & come to do live again 🐨 but first of all, I’m going to just fix my hair, then the next time when we have comeback or something like that right? from there, what I’m thinking is that, I will try to match (the timing) in a flexible way & change something (his hair) then. that kind of feeling~

👤 junkyu mon, show us your face! 🐨 if you see my face right now, you’ll go, “who are you?!” 🐨 (laughs) it’s just like that~ 🐨 I planned something to some extent. since my hair is long right now~ I will try to fix my hair this week & come to do live again 🐨 but first of all, I’m going to just fix my hair, then the next time when we have comeback or something like that right? from there, what I’m thinking is that, I will try to match (the timing) in a flexible way & change something (his hair) then. that kind of feeling~

ain

11,378 просмотров • 6 месяцев назад

Crypto hiring is broken. Ghost candidates after four rounds. Hide salaries until the offer letter. Hire through group chats and nepotism. Ignore global talent because "time zones are hard." Pay in mystery tokens with a 4-year cliff. Verify nothing. We built deciml to fix this. The job finds you. Not the other way around. You create your profile once. That's it. No endless applications. No rewriting your CV for every role. AI matches you to jobs that actually fit your skills, experience, and what you're looking for. When something matches, you click apply. One click. Want to know what you should be asking for? We built a salary benchmarking tool based on real Web3 placements. No more guessing if you're being lowballed. You get notified when something relevant drops. In the app, Telegram, however you want it. You also get notified when your application moves stages so you're never sitting there wondering. Full salary transparency on every listing. Skills verification that actually means something. A shareable profile link you can drop anywhere. Try it now.

0xBawar

36,866 просмотров • 4 месяцев назад

This leftist bro is literally golfing on a pristine American course — polo on, glove ready — filming this emotional rant: “America isn’t home anymore… me and my wife are moving to Thailand, Malaysia, Vietnam or the Philippines next year so we can actually live.” My guy… you’re out here living better than 99% of humans who’ve ever existed, in the one country on Earth where millions risk everything just to get IN — and you’re tapping out because rent’s high, drivers honk, and your neighbors don’t wave? That’s not America failing you. That’s quitter energy. The American Dream isn’t dead. Quitters like this are just too soft to grind for it anymore. Real patriots don’t run when it gets hard. They stay, build, fix what’s broken, and make this country HOME again. If you can’t hack it here with your online income plan and golf course afternoons, good luck with the visas, culture shock, and starting over. We’re staying. We’re fighting. We’re winning! 🇺🇸🔥

This leftist bro is literally golfing on a pristine American course — polo on, glove ready — filming this emotional rant: “America isn’t home anymore… me and my wife are moving to Thailand, Malaysia, Vietnam or the Philippines next year so we can actually live.” My guy… you’re out here living better than 99% of humans who’ve ever existed, in the one country on Earth where millions risk everything just to get IN — and you’re tapping out because rent’s high, drivers honk, and your neighbors don’t wave? That’s not America failing you. That’s quitter energy. The American Dream isn’t dead. Quitters like this are just too soft to grind for it anymore. Real patriots don’t run when it gets hard. They stay, build, fix what’s broken, and make this country HOME again. If you can’t hack it here with your online income plan and golf course afternoons, good luck with the visas, culture shock, and starting over. We’re staying. We’re fighting. We’re winning! 🇺🇸🔥

DocumentingLibs

46,168 просмотров • 3 месяцев назад

Hey ICICI Bank team!! Make sure this message reaches Radhika Saxena, all regional heads, and your top management. Before harassing, abusing, and mentally pressurising your employees in the name of targets, you seriously need to fix yourselves first. All you people do is scream CASA..CASA all day long and dump impossible targets on ground-level staff. But have you ever bothered to look at your pathetic service standards? Customers struggle with unnecessary minimum balance issues just to open accounts. While public sector banks remain open for customers till 4 PM, ICICI Bank shuts its shutters by 3:30 PM. Cash deposits are refused after 2 PM and customers are pushed towards ATMs, and when those ATMs don’t work, the standard response is “come tomorrow.” Tell me one thing..if you don’t provide basic banking services, how exactly do you expect CASA to grow? By abusing employees? By threatening staff? My own experience with ICICI Bank has been consistently bad, and I know I’m not alone. Instead of unloading your frustration and incompetence on employees who are already overworked, fix your broken service model. Improve customer experience first..CASA and business will follow automatically. Until then, stop pretending that pressure and abuse are substitutes for leadership.

Hey ICICI Bank team!! Make sure this message reaches Radhika Saxena, all regional heads, and your top management. Before harassing, abusing, and mentally pressurising your employees in the name of targets, you seriously need to fix yourselves first. All you people do is scream CASA..CASA all day long and dump impossible targets on ground-level staff. But have you ever bothered to look at your pathetic service standards? Customers struggle with unnecessary minimum balance issues just to open accounts. While public sector banks remain open for customers till 4 PM, ICICI Bank shuts its shutters by 3:30 PM. Cash deposits are refused after 2 PM and customers are pushed towards ATMs, and when those ATMs don’t work, the standard response is “come tomorrow.” Tell me one thing..if you don’t provide basic banking services, how exactly do you expect CASA to grow? By abusing employees? By threatening staff? My own experience with ICICI Bank has been consistently bad, and I know I’m not alone. Instead of unloading your frustration and incompetence on employees who are already overworked, fix your broken service model. Improve customer experience first..CASA and business will follow automatically. Until then, stop pretending that pressure and abuse are substitutes for leadership.

Vijaya Sharma

96,937 просмотров • 7 месяцев назад

TARS debuted their DexHand at the world's most prestigious robotics conference this week. The hand has 21 degrees of freedom built at 1:1 human anatomical scale. Inside each fingertip: sensors that detect texture at 0.05mm resolution at over 240Hz. A human hair is 0.07mm wide. The hand is more sensitive than your skin, continuously, during active manipulation. It doesn't just sense. Their TacForeSight model then predicts the dynamics of contact before it happens and adjusts grip before any camera registers the movement. In March 2026, their A1 robot set a Guinness World Record: over 100 sub-millimeter wire harness assemblies in 60 minutes. Engineers call this task the Goldbach Conjecture of industrial automation. It has resisted automation for decades. At ICRA, A1 packed a backpack live. Picked up stationery, sorted it, zipped it shut. When it dropped something it replanned and kept going. No reset. No human intervention. Nearly $700 million raised. 2 years old. One Guinness record. Vienna was a statement.

TARS debuted their DexHand at the world's most prestigious robotics conference this week. The hand has 21 degrees of freedom built at 1:1 human anatomical scale. Inside each fingertip: sensors that detect texture at 0.05mm resolution at over 240Hz. A human hair is 0.07mm wide. The hand is more sensitive than your skin, continuously, during active manipulation. It doesn't just sense. Their TacForeSight model then predicts the dynamics of contact before it happens and adjusts grip before any camera registers the movement. In March 2026, their A1 robot set a Guinness World Record: over 100 sub-millimeter wire harness assemblies in 60 minutes. Engineers call this task the Goldbach Conjecture of industrial automation. It has resisted automation for decades. At ICRA, A1 packed a backpack live. Picked up stationery, sorted it, zipped it shut. When it dropped something it replanned and kept going. No reset. No human intervention. Nearly $700 million raised. 2 years old. One Guinness record. Vienna was a statement.

Shruti

12,979 просмотров • 2 месяцев назад

Try out Gemini Code: a coding assistant in your terminal powered by Gemini 2.5 Pro. 💜 💜 Release Notes: → It's easy to get started, just run `pip install gemini-code` in a virtual environment, and then run `gemini` to initialize it. It requires your own API key, so don't forget to get one from → I built this because I love Claude Code and wanted a similar experience -- I like that I can just use my own API key and Gemini is generally way cheaper as well. → Found a bug? Feel free to fork the code and fix it (lol)! If you want to try to improve it, please do so - repo is public! → Reminder and a disclaimer that I don't work at Google and this is not an official Google project - just a weekend side hack → It is highly likely you'll get throttled by rate limits - I put as much info as I can in the guide so you know what behavior to expect when that happens. You can also set which default model to use if you want to switch to 1.5 Pro.

Try out Gemini Code: a coding assistant in your terminal powered by Gemini 2.5 Pro. 💜 💜 Release Notes: → It's easy to get started, just run `pip install gemini-code` in a virtual environment, and then run `gemini` to initialize it. It requires your own API key, so don't forget to get one from → I built this because I love Claude Code and wanted a similar experience -- I like that I can just use my own API key and Gemini is generally way cheaper as well. → Found a bug? Feel free to fork the code and fix it (lol)! If you want to try to improve it, please do so - repo is public! → Reminder and a disclaimer that I don't work at Google and this is not an official Google project - just a weekend side hack → It is highly likely you'll get throttled by rate limits - I put as much info as I can in the guide so you know what behavior to expect when that happens. You can also set which default model to use if you want to switch to 1.5 Pro.

Raiza Martin

159,723 просмотров • 1 год назад

34 Auditing Tips to crush it in 2026 - Think in bets - Constraint behaviour - If it's hard for you it's hard for everyone - Seek truth - Understand it first, then break it - Building is harder than breaking - Tools are substitutes for thinking - A fully understood Low is better than an untested fix - If it's not tested, it's broken - AI is a brainstorming tool - Work with Progressive Escalation - Understand the meaning of being average - Formally verify stateless libraries to extract constraints - There are no easy paths, you have to get better - Understand when to clamp and when not to - Rewrite it your way and compare notes - Peak experiences are like a wave. - Most Contest winners have a brutal track record - There's no rush in writing a report and POC - it's always a very serious deal or just don't bother - Start with the end in mind - Read the code until you can't anymore, then try something else - You don't understand the intensity of reviewing code, until you've seen it - If you're done before the end of the engagement, you're probably wrong - Understand your edge and use it to your advantage - There is no overnight success, only the world catching up to you - The path to mastery is simple, do the thing with 100% of intention, review the results, learn - Model people that inspire you - Forge your own path - Read about common bugs - Create your own category defining bugs - Resting is work - Be careful about your own biases - The only constant is you

34 Auditing Tips to crush it in 2026 - Think in bets - Constraint behaviour - If it's hard for you it's hard for everyone - Seek truth - Understand it first, then break it - Building is harder than breaking - Tools are substitutes for thinking - A fully understood Low is better than an untested fix - If it's not tested, it's broken - AI is a brainstorming tool - Work with Progressive Escalation - Understand the meaning of being average - Formally verify stateless libraries to extract constraints - There are no easy paths, you have to get better - Understand when to clamp and when not to - Rewrite it your way and compare notes - Peak experiences are like a wave. - Most Contest winners have a brutal track record - There's no rush in writing a report and POC - it's always a very serious deal or just don't bother - Start with the end in mind - Read the code until you can't anymore, then try something else - You don't understand the intensity of reviewing code, until you've seen it - If you're done before the end of the engagement, you're probably wrong - Understand your edge and use it to your advantage - There is no overnight success, only the world catching up to you - The path to mastery is simple, do the thing with 100% of intention, review the results, learn - Model people that inspire you - Forge your own path - Read about common bugs - Create your own category defining bugs - Resting is work - Be careful about your own biases - The only constant is you

Recon

15,364 просмотров • 8 месяцев назад

Finally, a database can generate its own embeddings now. When you add semantic search to an app, the standard step is to wire up an external embedding service, sync the vectors to a separate store, and write glue to keep everything updated as data changes. While this is a standard setup, problems show up later when your data changes, but your pipeline has already run, and search quality starts degrading in ways that are hard to pin down because nothing is explicitly broken. MongoDB Atlas handles this with auto-embedding. You point an index at a text field, specify a Voyage AI model, and Atlas generates the vectors inside the database. When a document changes, it re-embeds itself automatically, so that the search always stays grounded to the current context. I tested this against MongoDB's sample movies collection, 21,000 plots indexed with one config. A plain English query about dystopian machine-controlled futures returned semantically relevant results, despite having no keyword overlap. You can try it yourself here: One index config replaced the embedding service, the vector store, and the sync layer you used to maintain separately. The video below depicts this in action, and I worked with the MongoDB team to put this together. I have also put together a full LLM engineering roadmap covering what it actually takes to build and ship production AI systems in 2026. Read it below.

Finally, a database can generate its own embeddings now. When you add semantic search to an app, the standard step is to wire up an external embedding service, sync the vectors to a separate store, and write glue to keep everything updated as data changes. While this is a standard setup, problems show up later when your data changes, but your pipeline has already run, and search quality starts degrading in ways that are hard to pin down because nothing is explicitly broken. MongoDB Atlas handles this with auto-embedding. You point an index at a text field, specify a Voyage AI model, and Atlas generates the vectors inside the database. When a document changes, it re-embeds itself automatically, so that the search always stays grounded to the current context. I tested this against MongoDB's sample movies collection, 21,000 plots indexed with one config. A plain English query about dystopian machine-controlled futures returned semantically relevant results, despite having no keyword overlap. You can try it yourself here: One index config replaced the embedding service, the vector store, and the sync layer you used to maintain separately. The video below depicts this in action, and I worked with the MongoDB team to put this together. I have also put together a full LLM engineering roadmap covering what it actually takes to build and ship production AI systems in 2026. Read it below.

Avi Chawla

14,463 просмотров • 21 дней назад

New: Joe Rogan completely understands the hatred Luigi Mangione held toward the American healthcare system as he tells comedian Joe DeRosa the entire business model of the health insurance industry is to deny as many claims as possible: Rogan is not just saying the system is broken. He is saying the incentives are backwards: health insurance companies market themselves as if they exist to protect you, but financially benefit when they pay out less. That anger is not coming from nowhere. A 2026 KFF analysis of federal ACA marketplace plans found insurers denied 19% of in-network claims and 37% of out-of-network claims in 2024. DEROSA: “Healthcare is a dirty business.” ROGAN: “Even when your claims are justified they still want to try to deny it because their goal is to make as much money as possible.” DEROSA: “I 100% agree.” ROGAN: “They’re really in the making money business, but they pretend like they’re in the we’re going to take care of you business.” The business model creates a brutal conflict of interest: the patient wants care covered, while the insurer has a financial incentive to limit payouts. This is why healthcare anger cuts across politics. Almost everyone knows someone who paid premiums for years, then got denied when they actually needed help. When people feel like the system profits from saying no to sick people, public trust eventually breaks.

New: Joe Rogan completely understands the hatred Luigi Mangione held toward the American healthcare system as he tells comedian Joe DeRosa the entire business model of the health insurance industry is to deny as many claims as possible: Rogan is not just saying the system is broken. He is saying the incentives are backwards: health insurance companies market themselves as if they exist to protect you, but financially benefit when they pay out less. That anger is not coming from nowhere. A 2026 KFF analysis of federal ACA marketplace plans found insurers denied 19% of in-network claims and 37% of out-of-network claims in 2024. DEROSA: “Healthcare is a dirty business.” ROGAN: “Even when your claims are justified they still want to try to deny it because their goal is to make as much money as possible.” DEROSA: “I 100% agree.” ROGAN: “They’re really in the making money business, but they pretend like they’re in the we’re going to take care of you business.” The business model creates a brutal conflict of interest: the patient wants care covered, while the insurer has a financial incentive to limit payouts. This is why healthcare anger cuts across politics. Almost everyone knows someone who paid premiums for years, then got denied when they actually needed help. When people feel like the system profits from saying no to sick people, public trust eventually breaks.

Fan Commentary: Joe Rogan Recaps

25,607 просмотров • 17 дней назад

McKinsey surveyed 2,000 companies in 2025. 51% said AI backfired on them. Top reason? Inaccuracy. From what I can tell, most of these systems weren't broken. They were unreliable. And unreliable is wayyyy worse because you can't predict when it fails. So I got Ash Tilawat (the Mr. Miyagi of teaching AI) from Gauntlet AI to walk me through the solution. Here's his 2026 framework for evaluating if your AI is trustworthy, reliable, and production-ready: 1. build your golden set Identify 30–50 core requests your AI must handle correctly. The stuff that, if broken, makes the whole system useless. And sit with the person whose job this AI is doing/automating/replacing/helping with. 2. test the weird stuff Your golden set covers common requests. But in production, users don't only ask common requests. So build a matrix of categories (topic x complexity) and fill the gaps. Every gap is a corner where failures can hide behind. 3. build a replay harness Record the exact state of every interaction so you can test prompt changes without burning API calls. Think of it like game film... you don't put players back on the field just to review the play. 4. create your rubric Use an LLM to grade outputs on accuracy, completeness, and tone. But calibrate it first -> run 50–100 examples through human and LLM scoring, find disagreements, fix the rubric, repeat until they match. 5. run experiments New model? Prompt rewrite? Run your eval suite against both versions. Ship if the golden set passes, no regressions, and the cost is acceptable. The teams still running production AI on vibes will be f***** in 2026. But the teams building eval libraries are compounding an advantage that gets harder to catch every month. Competitors can copy your product. They can't copy your test cases. h/t Austen Allred for helping put this together. Full playbook + vid below 👇

McKinsey surveyed 2,000 companies in 2025. 51% said AI backfired on them. Top reason? Inaccuracy. From what I can tell, most of these systems weren't broken. They were unreliable. And unreliable is wayyyy worse because you can't predict when it fails. So I got Ash Tilawat (the Mr. Miyagi of teaching AI) from Gauntlet AI to walk me through the solution. Here's his 2026 framework for evaluating if your AI is trustworthy, reliable, and production-ready: 1. build your golden set Identify 30–50 core requests your AI must handle correctly. The stuff that, if broken, makes the whole system useless. And sit with the person whose job this AI is doing/automating/replacing/helping with. 2. test the weird stuff Your golden set covers common requests. But in production, users don't only ask common requests. So build a matrix of categories (topic x complexity) and fill the gaps. Every gap is a corner where failures can hide behind. 3. build a replay harness Record the exact state of every interaction so you can test prompt changes without burning API calls. Think of it like game film... you don't put players back on the field just to review the play. 4. create your rubric Use an LLM to grade outputs on accuracy, completeness, and tone. But calibrate it first -> run 50–100 examples through human and LLM scoring, find disagreements, fix the rubric, repeat until they match. 5. run experiments New model? Prompt rewrite? Run your eval suite against both versions. Ship if the golden set passes, no regressions, and the cost is acceptable. The teams still running production AI on vibes will be f***** in 2026. But the teams building eval libraries are compounding an advantage that gets harder to catch every month. Competitors can copy your product. They can't copy your test cases. h/t Austen Allred for helping put this together. Full playbook + vid below 👇

Alex Lieberman

84,725 просмотров • 7 месяцев назад

Traditional Chinese Medicine has believed for thousands of years that the liver impacts far more than just “detoxification.” In TCM, the liver is tied to energy flow, digestion, mood, inflammation, and the body’s ability to properly metabolize fat. Chinese medicine master @chentaomed shares a simple morning drink traditionally used to support “liver stagnation”, or the sluggish energy flow and congestion in the body. 🐌 The recipe: 💧 2 cups boiling water 🧂 A pinch of salt 🌿 1 tsp cinnamon 🍋 Juice of 1/2 lemon Let it simmer for 8 minutes and drink warm on an empty stomach in the morning. As I have said for decades, always start with your liver! When your liver is overloaded from processed foods, environmental toxins, alcohol, seed oils, medications, and chronic stress, your entire body can feel it. Most people try to fix symptoms. But most never support the organ that runs it all. 🧬 Even something as easy as this lemon water drink 🍋🫙in the morning can help support the liver and kickstart detox. But that’s just the beginning. That’s why I created a simple place to start. Here’s my FREE 2-Day Liver Detox to get your body moving in the right direction: Start at the root, not the symptom. Blessings and truth, Dr. Edward Group, DC

Traditional Chinese Medicine has believed for thousands of years that the liver impacts far more than just “detoxification.” In TCM, the liver is tied to energy flow, digestion, mood, inflammation, and the body’s ability to properly metabolize fat. Chinese medicine master @chentaomed shares a simple morning drink traditionally used to support “liver stagnation”, or the sluggish energy flow and congestion in the body. 🐌 The recipe: 💧 2 cups boiling water 🧂 A pinch of salt 🌿 1 tsp cinnamon 🍋 Juice of 1/2 lemon Let it simmer for 8 minutes and drink warm on an empty stomach in the morning. As I have said for decades, always start with your liver! When your liver is overloaded from processed foods, environmental toxins, alcohol, seed oils, medications, and chronic stress, your entire body can feel it. Most people try to fix symptoms. But most never support the organ that runs it all. 🧬 Even something as easy as this lemon water drink 🍋🫙in the morning can help support the liver and kickstart detox. But that’s just the beginning. That’s why I created a simple place to start. Here’s my FREE 2-Day Liver Detox to get your body moving in the right direction: Start at the root, not the symptom. Blessings and truth, Dr. Edward Group, DC

Dr. Edward Group, DC

19,344 просмотров • 3 месяцев назад

🚨🇺🇸 ELON'S CONFESSION PROVES WASHINGTON IS DESIGNED TO DESTROY ITS REFORMERS This is the message we send to anyone who tries to clean up Washington: Try to help us, and we’ll destroy you and everything you’ve built... When Elon says he wouldn't do DOGE again knowing people would burn his cars in response, he's not being weak; he's acknowledging that our political system has evolved into an organism that attacks its own antibodies. Consider what Elon accomplished before touching government: revolutionized electric vehicles against every established automaker, landed rockets backwards on floating platforms when NASA said it was impossible, created a satellite constellation providing internet to war zones and disaster areas, pioneered neural interfaces that help paralyzed people walk. Each achievement required defeating entrenched interests who said he'd fail. But those were merely corporate competitors and skeptics. Washington is a different beast. Washington doesn't just resist change; it destroys change agents. The burning cars tell the real story. When you try to cut government spending, you're not debating policy; you're threatening thousands of interconnected interests that survive on waste. Every inefficiency has a constituency. Every redundant program has defenders. Every dollar saved is someone's dollar lost, and they'll make you pay personally for threatening their revenue stream. They don't argue your proposals; they attack your existence. This is why government never shrinks, only grows. The system selects for people willing to play along, not those who might fix it. Anyone competent enough to reform government is successful enough to have something to lose, and the system ensures they lose it. Elon has billions of dollars and still concluded the personal destruction wasn't worth the attempt. What chance does anyone else have? The tragedy isn't that Elon regrets trying to help. It's that his regret is rational. When fixing waste makes you more enemies than friends, when efficiency threatens more interests than inefficiency, when the reward for public service is public destruction, the system isn't broken. It's performing exactly as designed: protecting itself from anyone who might actually change it. Source: Katie Miller Elon Musk

🚨🇺🇸 ELON'S CONFESSION PROVES WASHINGTON IS DESIGNED TO DESTROY ITS REFORMERS This is the message we send to anyone who tries to clean up Washington: Try to help us, and we’ll destroy you and everything you’ve built... When Elon says he wouldn't do DOGE again knowing people would burn his cars in response, he's not being weak; he's acknowledging that our political system has evolved into an organism that attacks its own antibodies. Consider what Elon accomplished before touching government: revolutionized electric vehicles against every established automaker, landed rockets backwards on floating platforms when NASA said it was impossible, created a satellite constellation providing internet to war zones and disaster areas, pioneered neural interfaces that help paralyzed people walk. Each achievement required defeating entrenched interests who said he'd fail. But those were merely corporate competitors and skeptics. Washington is a different beast. Washington doesn't just resist change; it destroys change agents. The burning cars tell the real story. When you try to cut government spending, you're not debating policy; you're threatening thousands of interconnected interests that survive on waste. Every inefficiency has a constituency. Every redundant program has defenders. Every dollar saved is someone's dollar lost, and they'll make you pay personally for threatening their revenue stream. They don't argue your proposals; they attack your existence. This is why government never shrinks, only grows. The system selects for people willing to play along, not those who might fix it. Anyone competent enough to reform government is successful enough to have something to lose, and the system ensures they lose it. Elon has billions of dollars and still concluded the personal destruction wasn't worth the attempt. What chance does anyone else have? The tragedy isn't that Elon regrets trying to help. It's that his regret is rational. When fixing waste makes you more enemies than friends, when efficiency threatens more interests than inefficiency, when the reward for public service is public destruction, the system isn't broken. It's performing exactly as designed: protecting itself from anyone who might actually change it. Source: Katie Miller Elon Musk

Mario Nawfal

448,511 просмотров • 8 месяцев назад

TESLA: Is the major growth behind the company - or ahead of it?? That is always an important question to ask. But Tesla has Elon Musk. And Elon Musk thinks at scales that might cause other CEO’s brains to short-circuit. While they are planning a flashy product demo; Elon Musk is planning for: ♦️ A BILLION AI Chips ♦️100 MILLION Robots ♦️A Terawatt of Power Plans this big require vertical integration; an obsessive focus on locking down supply chains (moving suppliers to YOUR timeline); and removing all obstacles, unnecessary parts or processes —especially when the full ecosystem must align to deliver at this scale. Plans this big can dwarf Tesla’s 43% compounded returns to date. Spectacular which made Larry Fink suggest you should invest in growth, specifically in Elon Musk. Spectacular returns which Larry Fink contrasted to Blackrock’s own returns of ~21%. ♦️Do you think Elon Musk can do it? I follow the infrastructure moves closely — ground broken on the Terafab research fab lab, industrial machines being ordered, job listings for chip experts in Seoul and Taiwan, and the Optimus line taking over the Model S/X floor space in Fremont. ♦️My answer is Elon Musk ALREADY IS. Doubters can get out of his way. Elon Musk will bend reality to achieve his ambition.

TESLA: Is the major growth behind the company - or ahead of it?? That is always an important question to ask. But Tesla has Elon Musk. And Elon Musk thinks at scales that might cause other CEO’s brains to short-circuit. While they are planning a flashy product demo; Elon Musk is planning for: ♦️ A BILLION AI Chips ♦️100 MILLION Robots ♦️A Terawatt of Power Plans this big require vertical integration; an obsessive focus on locking down supply chains (moving suppliers to YOUR timeline); and removing all obstacles, unnecessary parts or processes —especially when the full ecosystem must align to deliver at this scale. Plans this big can dwarf Tesla’s 43% compounded returns to date. Spectacular which made Larry Fink suggest you should invest in growth, specifically in Elon Musk. Spectacular returns which Larry Fink contrasted to Blackrock’s own returns of ~21%. ♦️Do you think Elon Musk can do it? I follow the infrastructure moves closely — ground broken on the Terafab research fab lab, industrial machines being ordered, job listings for chip experts in Seoul and Taiwan, and the Optimus line taking over the Model S/X floor space in Fremont. ♦️My answer is Elon Musk ALREADY IS. Doubters can get out of his way. Elon Musk will bend reality to achieve his ambition.

Amy

12,507 просмотров • 3 месяцев назад

You can’t make anyone else change; all you can do is create the conditions where change is more likely to happen. I remember speaking with an administrator and hearing him complain that his staff wasn’t moving forward. Instead of commiserating with him at that moment, I said, “Maybe it’s you?” It caught him off guard, but there was a point. Too often, myself included, when we try to lead people to new ideas, and they don’t immediately embrace them, we blame them instead of looking at where we may be deficient. Sometimes, the new “approach” is sharing the ideas over again, only louder. That approach rarely works. In this week’s newsletter, I shared 3 things that have helped me rethink how to help create better conditions for others to embrace change. 1. Truly listen to their thoughts and viewpoints, and be open to the idea that your way might not be the best. 2. Recognize that you also had resistance to new ideas, including things that you might consistently do and believe today. Be open with your own story of resistance and what made you change. 3. Start by focusing on the areas in which others are excelling, as opposed to your perception of their deficits. People who feel valued are more likely to move forward. People who feel you are trying to “fix” them will fight you non-stop. You can only control your own actions. What do others see in you that will make them want to move forward, by your side? People are more likely to take steps forward on a path if they see footprints from others already on the ground. Read the entire newsletter here:

You can’t make anyone else change; all you can do is create the conditions where change is more likely to happen. I remember speaking with an administrator and hearing him complain that his staff wasn’t moving forward. Instead of commiserating with him at that moment, I said, “Maybe it’s you?” It caught him off guard, but there was a point. Too often, myself included, when we try to lead people to new ideas, and they don’t immediately embrace them, we blame them instead of looking at where we may be deficient. Sometimes, the new “approach” is sharing the ideas over again, only louder. That approach rarely works. In this week’s newsletter, I shared 3 things that have helped me rethink how to help create better conditions for others to embrace change. 1. Truly listen to their thoughts and viewpoints, and be open to the idea that your way might not be the best. 2. Recognize that you also had resistance to new ideas, including things that you might consistently do and believe today. Be open with your own story of resistance and what made you change. 3. Start by focusing on the areas in which others are excelling, as opposed to your perception of their deficits. People who feel valued are more likely to move forward. People who feel you are trying to “fix” them will fight you non-stop. You can only control your own actions. What do others see in you that will make them want to move forward, by your side? People are more likely to take steps forward on a path if they see footprints from others already on the ground. Read the entire newsletter here:

George Couros

15,739 просмотров • 2 лет назад

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

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

GREG ISENBERG

193,721 просмотров • 4 месяцев назад

$REPLAY FILES BROKEN (FIXED + STEP BY STEP GUIDE) Hey! Currently there's a bug with replay files that prevents replays from before the latest Rocket League patch to load/work. As a creator, this severely impacts my workflow, and waiting for a patch could take a while. So to make sure I, and everyone else out there can continue to work, I've tried to find a solution. Initially I messed around with installing older Rocket League versions through the steam console, and trying to get the Injector from Bakkesmod to downgrade to the matching Rocket League version, however this proved to be tedious and honestly fruitless. So instead I turned to the modding community where I was quickly directed towards Martin, who ended up fixing the replay issue and building a handy tool. WHAT YOU'LL NEED: RocketRP: Microsoft. NET 9.0 Runtime: HOW TO: Step 1: Download (if your antivirus flags it, allow list it. Running unknown files is ALWAYS at your own risk, however I run the setup as well and the sourcecode is available to check for when you're in doubt). Step 2: Download the .NET 9.0 console framework for windows, or your respective platform. Step 3: Install the .NET 9.0 console framework through the downloaded .exe Step 4: Unzip/Extract the "RocketRP .cli .zip" file Step 5: Right click the extracted folder and select "Open in Terminal". If that option doesn't appear you need to click more options, and / or open with, and manually select Powershell or your preferred terminal of choice. Step 6: leave the terminal window open and go to: %USERPROFILE%\Documents\My Games\Rocket League\TAGame\Demos Step 7: Select the replays you want and place these in a new folder somewhere easily accessible. Make sure to back them up just in case* Step 8: Right click the replay you want to fix, and then select "copy as path" Step 9: In notepad or similar, copy this command: .\RocketRP.CLI.exe -r " " -m Repack --backup --legacy-fix true Make sure to replace the " " with the link you copied from the replay in step 8. For a breakdown of the command, check the video or use the help command in the terminal. Step 10: In the terminal, paste the command we created in step 9, then press enter. This should create a backup file of your replay, and it should create a new replay file that has the patch applied. NOTE: Right now, doing full folders isn't working, therefore you'll have to do this 1 replay at a time, untill I post a fix in the comments. Step 11: Put the newly generated replay in the demos folder (step 6) and load back into Rocket League. Your replay should now work as intended! Please note if you get any errors, you mostlikely didn't install the .NET 9.0 console correctly, or you have to check your command for typos. Huge thanks to Martin for helping me out with this, here's his paypal if you want to show him some appreciation: And if you're feeling EXTRA generous, here's my youtube. Consider subscribing if this helped you out!: If you have any questions, leave them below and I'll try to answer them the best I can!$

REPLAY FILES BROKEN (FIXED + STEP BY STEP GUIDE) Hey! Currently there's a bug with replay files that prevents replays from before the latest Rocket League patch to load/work. As a creator, this severely impacts my workflow, and waiting for a patch could take a while. So to make sure I, and everyone else out there can continue to work, I've tried to find a solution. Initially I messed around with installing older Rocket League versions through the steam console, and trying to get the Injector from Bakkesmod to downgrade to the matching Rocket League version, however this proved to be tedious and honestly fruitless. So instead I turned to the modding community where I was quickly directed towards Martin, who ended up fixing the replay issue and building a handy tool. WHAT YOU'LL NEED: RocketRP: Microsoft. NET 9.0 Runtime: HOW TO: Step 1: Download (if your antivirus flags it, allow list it. Running unknown files is ALWAYS at your own risk, however I run the setup as well and the sourcecode is available to check for when you're in doubt). Step 2: Download the .NET 9.0 console framework for windows, or your respective platform. Step 3: Install the .NET 9.0 console framework through the downloaded .exe Step 4: Unzip/Extract the "RocketRP .cli .zip" file Step 5: Right click the extracted folder and select "Open in Terminal". If that option doesn't appear you need to click more options, and / or open with, and manually select Powershell or your preferred terminal of choice. Step 6: leave the terminal window open and go to: %USERPROFILE%\Documents\My Games\Rocket League\TAGame\Demos Step 7: Select the replays you want and place these in a new folder somewhere easily accessible. Make sure to back them up just in case* Step 8: Right click the replay you want to fix, and then select "copy as path" Step 9: In notepad or similar, copy this command: .\RocketRP.CLI.exe -r " " -m Repack --backup --legacy-fix true Make sure to replace the " " with the link you copied from the replay in step 8. For a breakdown of the command, check the video or use the help command in the terminal. Step 10: In the terminal, paste the command we created in step 9, then press enter. This should create a backup file of your replay, and it should create a new replay file that has the patch applied. NOTE: Right now, doing full folders isn't working, therefore you'll have to do this 1 replay at a time, untill I post a fix in the comments. Step 11: Put the newly generated replay in the demos folder (step 6) and load back into Rocket League. Your replay should now work as intended! Please note if you get any errors, you mostlikely didn't install the .NET 9.0 console correctly, or you have to check your command for typos. Huge thanks to Martin for helping me out with this, here's his paypal if you want to show him some appreciation: And if you're feeling EXTRA generous, here's my youtube. Consider subscribing if this helped you out!: If you have any questions, leave them below and I'll try to answer them the best I can!

GGM1 Yota

14,018 просмотров • 1 год назад

A SLAVE TO YOU. 2001 was her peak. It is easy and safe to say “Glad it was not me” and “I would have done it differently”. I see. Fame and Fortune is like dancing with a very large poisons snake and they always win. I have had, in a parallel former life, the chance to work with the very famous on their way up. The first thing I say is: “What goes up, will go down. Your career, your money (maybe) and your brain (most definitely) and just about every friendship”. This will happen to every single complex and all too human, human, some just do a good just a good job hiding it. No one is prepared for wealth and fame. Oh we all talk a big game, but no one is prepared. And the wealth and fame are a guarantee that when you fall, you fall hard. Oh you have the money to protect your fall but because of it your mind falls further than one could think is possible. You are so alone. Your parents, your grand parents, your siblings, your kids they all become part of what I call “The Elvis Syndrome”. To everything your constellation of folks around you say “Yes Elvis, that’s a real good idea”, to everything. See they assume, even if they don’t say it, that you must be a “genius” because they didn’t do what you did and they don’t have the money and fame. They assign genius to you and lesser to themselves. They dare not speak up. They prefer “Yes Elvis, have another fried peanut butter and bacon sandwich. You are not getting fat”. Long ago your burning starlight chased away any true friends, because even if they were strong to say truth, you believed your own public persona like everyone around you. You can not listen, you are the genius they have some job someplace. You also have just two options to anyone around you: 1) Your “crew” 2) People you pay And ironically they merge in to one and the same. All see your public persona and all see you as a means to get paid. Oh you go to “parties” with other rich and famous people but they are one of the above ultimately. Hierarchy forms around you and they naturally form a protection barrier. You have tantrums as fame rips you apart and you desperately try to become your public persona. Each layer you build to protect your all too human center moves you into more and more isolation. Shielded from real and needed pressures of life you are in your beautiful and well stocked velvet prison. You are now just a vehicle for moving money efficiently and surrounded by people that live off this largess. At the peak you may have advisors and they may seem to help. But they dare not tell you what they see even if they could see it. And most can’t see it because no one is prepared for it so they don’t have any better insight. This spans the enter ensemble of people that are now your satellites from gurus to lawyers, from plastic surgery doctors and fitness trainers. So what now? What if your dreams to “make it big”? Abundance does not fix a broken soul. And we all have this. Trauma is a great fuel, it will absolutely get you to orbit and you will shine, but trauma in orbit is the breaks that break you and when gravity wins, and it always does, you have no idea how to navigate going down. Trauma is what I have seen build everyone from Elvis to Steve Jobs. Trauma unresolved took them out. I am not saying your dreams are invalid and should not be your goal, I am saying that you don’t get a pass. No one does. And with fame and fortune it is nearly impossible to address it, because your ego can’t fit in a zip code. As you prepare for you fortune, and if you are reading this, you will have one, prepare your mind. Deal with the dark places that drive you. Make peace with the past, the people that did you wrong and mostly with yourself. But in this bargain you will remove some fuel for your rocket. It is the bargain. But it is the better path. We all will dance with the snake. But hopefully will know it. And you may have fame. Just don’t become a: “Slave to you”.

A SLAVE TO YOU. 2001 was her peak. It is easy and safe to say “Glad it was not me” and “I would have done it differently”. I see. Fame and Fortune is like dancing with a very large poisons snake and they always win. I have had, in a parallel former life, the chance to work with the very famous on their way up. The first thing I say is: “What goes up, will go down. Your career, your money (maybe) and your brain (most definitely) and just about every friendship”. This will happen to every single complex and all too human, human, some just do a good just a good job hiding it. No one is prepared for wealth and fame. Oh we all talk a big game, but no one is prepared. And the wealth and fame are a guarantee that when you fall, you fall hard. Oh you have the money to protect your fall but because of it your mind falls further than one could think is possible. You are so alone. Your parents, your grand parents, your siblings, your kids they all become part of what I call “The Elvis Syndrome”. To everything your constellation of folks around you say “Yes Elvis, that’s a real good idea”, to everything. See they assume, even if they don’t say it, that you must be a “genius” because they didn’t do what you did and they don’t have the money and fame. They assign genius to you and lesser to themselves. They dare not speak up. They prefer “Yes Elvis, have another fried peanut butter and bacon sandwich. You are not getting fat”. Long ago your burning starlight chased away any true friends, because even if they were strong to say truth, you believed your own public persona like everyone around you. You can not listen, you are the genius they have some job someplace. You also have just two options to anyone around you: 1) Your “crew” 2) People you pay And ironically they merge in to one and the same. All see your public persona and all see you as a means to get paid. Oh you go to “parties” with other rich and famous people but they are one of the above ultimately. Hierarchy forms around you and they naturally form a protection barrier. You have tantrums as fame rips you apart and you desperately try to become your public persona. Each layer you build to protect your all too human center moves you into more and more isolation. Shielded from real and needed pressures of life you are in your beautiful and well stocked velvet prison. You are now just a vehicle for moving money efficiently and surrounded by people that live off this largess. At the peak you may have advisors and they may seem to help. But they dare not tell you what they see even if they could see it. And most can’t see it because no one is prepared for it so they don’t have any better insight. This spans the enter ensemble of people that are now your satellites from gurus to lawyers, from plastic surgery doctors and fitness trainers. So what now? What if your dreams to “make it big”? Abundance does not fix a broken soul. And we all have this. Trauma is a great fuel, it will absolutely get you to orbit and you will shine, but trauma in orbit is the breaks that break you and when gravity wins, and it always does, you have no idea how to navigate going down. Trauma is what I have seen build everyone from Elvis to Steve Jobs. Trauma unresolved took them out. I am not saying your dreams are invalid and should not be your goal, I am saying that you don’t get a pass. No one does. And with fame and fortune it is nearly impossible to address it, because your ego can’t fit in a zip code. As you prepare for you fortune, and if you are reading this, you will have one, prepare your mind. Deal with the dark places that drive you. Make peace with the past, the people that did you wrong and mostly with yourself. But in this bargain you will remove some fuel for your rocket. It is the bargain. But it is the better path. We all will dance with the snake. But hopefully will know it. And you may have fame. Just don’t become a: “Slave to you”.

Brian Roemmele

115,188 просмотров • 7 месяцев назад

Alright, this one’s worth your attention if you’re building or deploying agents. Future AGI just open-sourced their entire platform and i don’t mean a trimmed-down version. this is the full stack: UI, backend, simulation engine, evals, optimization loop, observability, guardrails, gateway, docs. all in one repo. Apache 2.0. I’ve been putting it through its paces on production agents, and what stands out isn’t just the breadth it’s the architecture. Most of the current “agent reliability” stack is fragmented. tracing lives in one tool, evals in another, guardrails somewhere else. you end up manually connecting dots, and the agent itself doesn’t really improve you just keep patching prompts and hoping for the best. This flips that model. It’s built as a closed feedback loop: simulate failures → evaluate in real time → detect production issues → learn from them → generate fixes → validate against real traffic → check regressions → redeploy → monitor again And when something new breaks, the loop just runs again. no manual glue. The simulation piece is especially strong. instead of static test cases, it generates adversarial, multi-turn conversations based on how your agent actually behaves basically hunting for the exact scenarios where your system fails confidently. ran a few thousand simulations on our side… caught things we definitely would’ve missed. Evals run fast (sub-50ms) across modalities. not LLM-as-judge trained classifiers. guardrails are built-in, not layered on top. observability gives you step-level visibility into reasoning, cost, latency, quality. But the real shift is the optimization loop. Most tools tell you *what* broke. this system actually fixes it, validates the fix, and ensures nothing else regresses. That’s the missing layer. It’s clearly built with production in mind not a research demo. and the fact that it’s self-hostable makes it even more relevant if you’re running serious workloads. If you’ve been duct-taping together infra around your agents, this is probably the closest thing to a unified system i’ve seen so far. Worth checking out. If you're serious about deploying reliable AI agents, this is worth a look: 👉 You can also try it instantly (no setup) via their cloud version:

Alright, this one’s worth your attention if you’re building or deploying agents. Future AGI just open-sourced their entire platform and i don’t mean a trimmed-down version. this is the full stack: UI, backend, simulation engine, evals, optimization loop, observability, guardrails, gateway, docs. all in one repo. Apache 2.0. I’ve been putting it through its paces on production agents, and what stands out isn’t just the breadth it’s the architecture. Most of the current “agent reliability” stack is fragmented. tracing lives in one tool, evals in another, guardrails somewhere else. you end up manually connecting dots, and the agent itself doesn’t really improve you just keep patching prompts and hoping for the best. This flips that model. It’s built as a closed feedback loop: simulate failures → evaluate in real time → detect production issues → learn from them → generate fixes → validate against real traffic → check regressions → redeploy → monitor again And when something new breaks, the loop just runs again. no manual glue. The simulation piece is especially strong. instead of static test cases, it generates adversarial, multi-turn conversations based on how your agent actually behaves basically hunting for the exact scenarios where your system fails confidently. ran a few thousand simulations on our side… caught things we definitely would’ve missed. Evals run fast (sub-50ms) across modalities. not LLM-as-judge trained classifiers. guardrails are built-in, not layered on top. observability gives you step-level visibility into reasoning, cost, latency, quality. But the real shift is the optimization loop. Most tools tell you what broke. this system actually fixes it, validates the fix, and ensures nothing else regresses. That’s the missing layer. It’s clearly built with production in mind not a research demo. and the fact that it’s self-hostable makes it even more relevant if you’re running serious workloads. If you’ve been duct-taping together infra around your agents, this is probably the closest thing to a unified system i’ve seen so far. Worth checking out. If you're serious about deploying reliable AI agents, this is worth a look: 👉 You can also try it instantly (no setup) via their cloud version:

Aakash Verma

22,910 просмотров • 4 месяцев назад

Jocko Willink says the answer to tasks piling up is a small notebook, two consolidations a day, and 15 minutes of list review scheduled like an appointment. "First, first of all, definitely write the things down in one place." "It sounds like, since you're moving all the time or you're going to meetings, carry just a nice little notebook with you and write the things down as you get tasked with them." "Then on top of that, you have to have a master list of some kind, either paper or digital." "So if you get tasked something in a meeting in your little notebook, you come back, you put it in the right place in the master task list." "And then like twice a day to consolidate the information that's in the little notebook you have into the big master list." "Before you go to bed at night, you organize those things by priority on the master list. You put the most important thing at the top and that's what you're going to attack the next day." "That's part one on how you get these things organized. Now the part two is you got to schedule this stuff. And actually, I always say this when people have trouble with tasks, put them on the calendar." "Jamie does that for me. When Jamie's got something for me to do, she just doesn't email me and say, hey, you need to do this. She puts it on the calendar. So I look at my calendar, boom, there it is." "Put these things on your calendar. And that includes scheduling time on your calendar so that you can have time to consolidate your list and do a review of your lists." There is no "try harder" anywhere in his answer. The notebook catches it, the list ranks it, the calendar gives it a time, and the fifteen-minute review keeps the whole thing honest, so his head never has to hold any of it. That is the real fix for the kind of overload where none of the tasks are hard but they never stop coming: everything gets a place and a time, and whatever is still floating in your head is the thing taxing you. - Jocko Willink (Jocko Willink) on the Jocko Podcast (Jocko Willink)

Jocko Willink says the answer to tasks piling up is a small notebook, two consolidations a day, and 15 minutes of list review scheduled like an appointment. "First, first of all, definitely write the things down in one place." "It sounds like, since you're moving all the time or you're going to meetings, carry just a nice little notebook with you and write the things down as you get tasked with them." "Then on top of that, you have to have a master list of some kind, either paper or digital." "So if you get tasked something in a meeting in your little notebook, you come back, you put it in the right place in the master task list." "And then like twice a day to consolidate the information that's in the little notebook you have into the big master list." "Before you go to bed at night, you organize those things by priority on the master list. You put the most important thing at the top and that's what you're going to attack the next day." "That's part one on how you get these things organized. Now the part two is you got to schedule this stuff. And actually, I always say this when people have trouble with tasks, put them on the calendar." "Jamie does that for me. When Jamie's got something for me to do, she just doesn't email me and say, hey, you need to do this. She puts it on the calendar. So I look at my calendar, boom, there it is." "Put these things on your calendar. And that includes scheduling time on your calendar so that you can have time to consolidate your list and do a review of your lists." There is no "try harder" anywhere in his answer. The notebook catches it, the list ranks it, the calendar gives it a time, and the fifteen-minute review keeps the whole thing honest, so his head never has to hold any of it. That is the real fix for the kind of overload where none of the tasks are hard but they never stop coming: everything gets a place and a time, and whatever is still floating in your head is the thing taxing you. - Jocko Willink (Jocko Willink) on the Jocko Podcast (Jocko Willink)

Jay McHale

212,843 просмотров • 1 месяц назад