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

The best programmers don't write code anymore. They write a spec. A test. An eval. T Then they turn the AI on and walk away for hours. It runs. It ships. They review. Evals are the unlock most devs are sleeping on. Here's how top agent teams build them right.

Rohit

24,427 subscribers

691,571 просмотров • 5 месяцев назад •via X (Twitter)

Образование Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

LeetCode is dead. Developers don't write code line-by-line anymore. They orchestrate AI agents working in parallel, review AI-generated code, and make architectural decisions. That's the job now. But most interview processes haven't caught up. They still test algorithm memorization instead of AI fluency, code review, and judgment. We're building assessments for next-gen hiring that mirror how developers actually work. Here's how we think about it:

LeetCode is dead. Developers don't write code line-by-line anymore. They orchestrate AI agents working in parallel, review AI-generated code, and make architectural decisions. That's the job now. But most interview processes haven't caught up. They still test algorithm memorization instead of AI fluency, code review, and judgment. We're building assessments for next-gen hiring that mirror how developers actually work. Here's how we think about it:

HackerRank

344,255 просмотров • 4 месяцев назад

Head of Claude Code, Boris Cherny: "You're not supposed to write code anymore. You're supposed to build a graph that writes itself." In 30 minutes he breaks down how engineers at Anthropic build graphs that write the code, catch the bugs, and ships. The missing piece most developers skip: how to wire those agents into a graph that runs, verifies, and improves without you. Watch it, then read the full guide on graph engineering below.

Head of Claude Code, Boris Cherny: "You're not supposed to write code anymore. You're supposed to build a graph that writes itself." In 30 minutes he breaks down how engineers at Anthropic build graphs that write the code, catch the bugs, and ships. The missing piece most developers skip: how to wire those agents into a graph that runs, verifies, and improves without you. Watch it, then read the full guide on graph engineering below.

Mahax

416,527 просмотров • 1 месяц назад

Today, teams ship AI-generated code faster than they can verify it. AI will write most of the world's code, Momentic will make sure it works. We've raised a $15M Series A led by Standard Capital to build the definitive source of truth for software.

Today, teams ship AI-generated code faster than they can verify it. AI will write most of the world's code, Momentic will make sure it works. We've raised a $15M Series A led by Standard Capital to build the definitive source of truth for software.

wei-wei

2,645,343 просмотров • 9 месяцев назад

Former CEO of Google, Eric Schmidt: "traditional programming is over, and i'm mourning the identity i built around it" Programmers don't write code anymore — they wake up, assign objectives to AI agents, go to lunch, and let them run overnight For anyone still coding the old way: "stop. it's over"

Former CEO of Google, Eric Schmidt: "traditional programming is over, and i'm mourning the identity i built around it" Programmers don't write code anymore — they wake up, assign objectives to AI agents, go to lunch, and let them run overnight For anyone still coding the old way: "stop. it's over"

Haider.

155,562 просмотров • 3 месяцев назад

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓

Sprytix

66,333 просмотров • 29 дней назад

We are in a technological war with China, we really are. There are three countries that spend the most on AI. Number one is the US, number two is China, number three is the UAE. The UAE is friendly to the US, they work on American chips, they work with Nvidia. And so if we didn't give them chips and we starved them from technology, they would simply buy them from Huawei. The problem with that is that the chip is the queen bee. You set a chip out into the ecosphere, all the honeybees gather around it, they're the programmers, and they make the honey, they write the code, they create the value of the hive. Every time the queen bee's DNA is upgraded, all the other bees know how to write that code and make that honey. Do we want American honey out there or do we want Chinese honey?

We are in a technological war with China, we really are. There are three countries that spend the most on AI. Number one is the US, number two is China, number three is the UAE. The UAE is friendly to the US, they work on American chips, they work with Nvidia. And so if we didn't give them chips and we starved them from technology, they would simply buy them from Huawei. The problem with that is that the chip is the queen bee. You set a chip out into the ecosphere, all the honeybees gather around it, they're the programmers, and they make the honey, they write the code, they create the value of the hive. Every time the queen bee's DNA is upgraded, all the other bees know how to write that code and make that honey. Do we want American honey out there or do we want Chinese honey?

Kevin O'Leary aka Mr. Wonderful

24,193 просмотров • 1 год назад

Andrej Karpathy's advice for beginners getting into AI: "Put in 10,000 hours of work." He's right. But most builders waste the first 1,000 hours on the wrong things. They write code before understanding context windows. They build agents before understanding token limits. They ship products before understanding what models can't do. The builders who compound fastest aren't the ones who code the most. They're the ones who understood the fundamentals before touching a single line. These are the 10 concepts that make the first 1,000 hours count ↓ Bookmark this before you start.

Andrej Karpathy's advice for beginners getting into AI: "Put in 10,000 hours of work." He's right. But most builders waste the first 1,000 hours on the wrong things. They write code before understanding context windows. They build agents before understanding token limits. They ship products before understanding what models can't do. The builders who compound fastest aren't the ones who code the most. They're the ones who understood the fundamentals before touching a single line. These are the 10 concepts that make the first 1,000 hours count ↓ Bookmark this before you start.

Rahul

377,753 просмотров • 3 месяцев назад

I don't think most PMs realize the PRD is becoming obsolete. For the last decade, the PM's core artifact was a qualitative spec. Clear requirements, user stories, acceptance criteria. The engineering team interpreted it, built something close, and the PM spent two weeks reconciling what shipped with what they wrote. The best AI companies replaced that entire loop with evals. A set of inputs your product needs to handle. A task that generates outputs. A scoring function that produces a number between 0 and 1. No ambiguity. No interpretation gap. Ankur Goyal built the eval platform behind Vercel, Replit, Ramp, Notion, and Airtable. An $800M company. He walked through building an eval from zero on this episode and the score went from 0 to 0.75 in under 20 minutes. That's a PM shipping a measurable quality bar before a single line of product code exists. Here's the part that changes the PM role permanently. When the product passes the eval and users still hate it, the eval is wrong. That's on the PM. Evals make PM judgment quantifiable in a way PRDs never did. You can't hide behind "the spec was ambiguous." There's a number now. Six months ago, PM interviews asked "how do you use AI in your workflow." The next wave of interviews is going to ask you to write an eval. The PMs who can encode user intent as a scoring function are building the one skill that survives every model change, every framework swap, every agent rewrite. Write the eval.

I don't think most PMs realize the PRD is becoming obsolete. For the last decade, the PM's core artifact was a qualitative spec. Clear requirements, user stories, acceptance criteria. The engineering team interpreted it, built something close, and the PM spent two weeks reconciling what shipped with what they wrote. The best AI companies replaced that entire loop with evals. A set of inputs your product needs to handle. A task that generates outputs. A scoring function that produces a number between 0 and 1. No ambiguity. No interpretation gap. Ankur Goyal built the eval platform behind Vercel, Replit, Ramp, Notion, and Airtable. An $800M company. He walked through building an eval from zero on this episode and the score went from 0 to 0.75 in under 20 minutes. That's a PM shipping a measurable quality bar before a single line of product code exists. Here's the part that changes the PM role permanently. When the product passes the eval and users still hate it, the eval is wrong. That's on the PM. Evals make PM judgment quantifiable in a way PRDs never did. You can't hide behind "the spec was ambiguous." There's a number now. Six months ago, PM interviews asked "how do you use AI in your workflow." The next wave of interviews is going to ask you to write an eval. The PMs who can encode user intent as a scoring function are building the one skill that survives every model change, every framework swap, every agent rewrite. Write the eval.

Aakash Gupta

78,275 просмотров • 5 месяцев назад

Don't let AI write code blindly. In Antigravity, request an "Implementation Plan" artifact first. Review the architecture, edit the markdown logic, and then approve execution. Control the outcome, don't just hope for it.

Don't let AI write code blindly. In Antigravity, request an "Implementation Plan" artifact first. Review the architecture, edit the markdown logic, and then approve execution. Control the outcome, don't just hope for it.

Google Antigravity

185,118 просмотров • 6 месяцев назад

Katie Phang on Todd Blanche's latest response in her Epstein lawsuit: "The fact it took them seven days to write two and a third pages of nothing ... They don't know what they're doing. They are swimming in the deep end and they don't have their baby floaties to help them."

Katie Phang on Todd Blanche's latest response in her Epstein lawsuit: "The fact it took them seven days to write two and a third pages of nothing ... They don't know what they're doing. They are swimming in the deep end and they don't have their baby floaties to help them."

MeidasClips

93,447 просмотров • 1 месяц назад

🚨 Jeffrey Epstein says the best traders act on intuition they don't fully understand "If you talk to really experienced and successful traders and you ask them how they know what's going on, they can't give you an answer. They don't know. They feel it. They can feel the way the market's moving. They can feel the way the stock's moving. And that these are not very well-defined terms. Great traders feel it and then act on their feelings. That's the difference. Many people feel it but are afraid because they want a mathematical justification before they take that next step."

🚨 Jeffrey Epstein says the best traders act on intuition they don't fully understand "If you talk to really experienced and successful traders and you ask them how they know what's going on, they can't give you an answer. They don't know. They feel it. They can feel the way the market's moving. They can feel the way the stock's moving. And that these are not very well-defined terms. Great traders feel it and then act on their feelings. That's the difference. Many people feel it but are afraid because they want a mathematical justification before they take that next step."

Red Panda Koala

1,629,720 просмотров • 7 месяцев назад

A TURING AWARD WINNER STOOD UP AND TOLD A ROOM OF ENGINEERS THAT ALMOST NONE OF THEM DO THE ONE THING THAT ACTUALLY SEPARATES REAL ENGINEERING FROM TYPING, THEY WRITE CODE BUT THEY NEVER WRITE THE BLUEPRINT 56 minutes from Leslie Lamport -- Turing Award winner, creator of the tech behind almost every distributed system on earth. -> His claim: architects draw plans before a brick is laid. Programmers just start coding and hope. That gap is where complex systems quietly break. 04:10 -- A blueprint for software is called a spec. Write what the system must DO before touching how it does it. 10:13 -- Thinking above the code is the skill. The language is just the last, easiest step. 43:23 -- What programmers should really know isn't syntax. It's thinking clearly enough that "done" actually means done. 48:15 -- Thinking is hard, so we skip it. We jump straight to code because typing feels like progress. And this is exactly the wall the new "Loop engineering" hype is about to hit -- people now design loops of agents that write and check code while they walk away. But an unattended loop with no spec just ships broken work faster. Lamport is the missing half: the discipline that makes it safe to leave a loop running at all. You thought the leverage moved into better prompts and better loops. This is the man showing it moved above the code, where almost no one is willing to think. Save this. Read it before you trust a single agent loop ↓

A TURING AWARD WINNER STOOD UP AND TOLD A ROOM OF ENGINEERS THAT ALMOST NONE OF THEM DO THE ONE THING THAT ACTUALLY SEPARATES REAL ENGINEERING FROM TYPING, THEY WRITE CODE BUT THEY NEVER WRITE THE BLUEPRINT 56 minutes from Leslie Lamport -- Turing Award winner, creator of the tech behind almost every distributed system on earth. -> His claim: architects draw plans before a brick is laid. Programmers just start coding and hope. That gap is where complex systems quietly break. 04:10 -- A blueprint for software is called a spec. Write what the system must DO before touching how it does it. 10:13 -- Thinking above the code is the skill. The language is just the last, easiest step. 43:23 -- What programmers should really know isn't syntax. It's thinking clearly enough that "done" actually means done. 48:15 -- Thinking is hard, so we skip it. We jump straight to code because typing feels like progress. And this is exactly the wall the new "Loop engineering" hype is about to hit -- people now design loops of agents that write and check code while they walk away. But an unattended loop with no spec just ships broken work faster. Lamport is the missing half: the discipline that makes it safe to leave a loop running at all. You thought the leverage moved into better prompts and better loops. This is the man showing it moved above the code, where almost no one is willing to think. Save this. Read it before you trust a single agent loop ↓

slash1s

15,371 просмотров • 1 месяц назад

American is seeing young students unable to answer basic questions and she’s horrified “The kids aren't learning how to learn anymore — We are now witnessing the first generation to grow up with the skill of thinking as optional” “internet. I have never seen more comments asking me basic common sense questions — They don't have to learn math. They could just take a picture of the math problem and have it solved. They don't have to learn how to write essays. They could just have AI write the essay for them. They don't have to learn how to read or write, let alone write cursive. I am so afraid” “We might literally see the end of humanity” She’s right American kids are failing miserably in schools - 40% of 4th graders now score below the most basic reading level - 33% of 8th graders score below basic in reading. This is the worst in history - Only 28% of 8th graders are proficient in math

American is seeing young students unable to answer basic questions and she’s horrified “The kids aren't learning how to learn anymore — We are now witnessing the first generation to grow up with the skill of thinking as optional” “internet. I have never seen more comments asking me basic common sense questions — They don't have to learn math. They could just take a picture of the math problem and have it solved. They don't have to learn how to write essays. They could just have AI write the essay for them. They don't have to learn how to read or write, let alone write cursive. I am so afraid” “We might literally see the end of humanity” She’s right American kids are failing miserably in schools - 40% of 4th graders now score below the most basic reading level - 33% of 8th graders score below basic in reading. This is the worst in history - Only 28% of 8th graders are proficient in math

Wall Street Apes

68,416 просмотров • 18 дней назад

BREAKING: Employee at a Build-A-Bear Workshop in Tukwila, WA, REFUSED a request to write Charlie Kirk's name on the bear's birth certificate for a customer. Evi McCormick, who requested it be named after Charlie, said that the employee said "We're not doing this" before crumpling up the certificate and throwing it away. Build-A-Bear says they are handling the case "internally" and later apologized for the incident, claiming they are retraining staff in the area.

BREAKING: Employee at a Build-A-Bear Workshop in Tukwila, WA, REFUSED a request to write Charlie Kirk's name on the bear's birth certificate for a customer. Evi McCormick, who requested it be named after Charlie, said that the employee said "We're not doing this" before crumpling up the certificate and throwing it away. Build-A-Bear says they are handling the case "internally" and later apologized for the incident, claiming they are retraining staff in the area.

Libs of TikTok

2,666,910 просмотров • 11 месяцев назад

Robotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From NVIDIA Berkeley AI Research CMU Robotics Institute Stanford AI Lab 🧵

Robotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From NVIDIA Berkeley AI Research CMU Robotics Institute Stanford AI Lab 🧵

Max Fu

178,082 просмотров • 5 месяцев назад

The hard part of building is no longer writing code. Code is easy. Nobody wins by writing more code or doing it faster. If you want to win, you need better thinking. There are a ton of startups focusing on using AI to write more code. I think they are missing the plot. We need a mental shift. We need tools that help us think faster, make better decisions, and focus on the right problems. I want you to check out Atoms because they are doing exactly this. They don't focus on the code, but on helping you build the right structure: 1. It starts by deep-researching marketing insights 2. It turns that into an execution plan 3. It builds both frontend and backend 4. It helps with deployment, SEO, growth, and analytics More importantly, it specializes in the core components you need to build and sell software online: • Authentication flows • Stripe payments • Infrastructure Their goal here is not to be another autocomplete tool or a copilot to help you write software. Their goal is to become a "vibe business team" that helps you build a business from the ground up. Here is a link for you to check them out: Thanks to the team for helping me onboard on the platform and collaborating with me on the post.

The hard part of building is no longer writing code. Code is easy. Nobody wins by writing more code or doing it faster. If you want to win, you need better thinking. There are a ton of startups focusing on using AI to write more code. I think they are missing the plot. We need a mental shift. We need tools that help us think faster, make better decisions, and focus on the right problems. I want you to check out Atoms because they are doing exactly this. They don't focus on the code, but on helping you build the right structure: 1. It starts by deep-researching marketing insights 2. It turns that into an execution plan 3. It builds both frontend and backend 4. It helps with deployment, SEO, growth, and analytics More importantly, it specializes in the core components you need to build and sell software online: • Authentication flows • Stripe payments • Infrastructure Their goal here is not to be another autocomplete tool or a copilot to help you write software. Their goal is to become a "vibe business team" that helps you build a business from the ground up. Here is a link for you to check them out: Thanks to the team for helping me onboard on the platform and collaborating with me on the post.

Santiago

79,010 просмотров • 7 месяцев назад

my first thought when I saw Figma's sidebar showing component code was, "I really hope they add a way for devs to write the code that's displayed there" — and today they launched that functionality! watch Jake give us a whirlwind tour of how it works

my first thought when I saw Figma's sidebar showing component code was, "I really hope they add a way for devs to write the code that's displayed there" — and today they launched that functionality! watch Jake give us a whirlwind tour of how it works

Jason Lengstorf

113,163 просмотров • 2 лет назад

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇

darkzodchi

845,087 просмотров • 3 месяцев назад

Shotzzy answer's on which top teams look the best right now 🗣️🌶️ "Paris know what they're doing on the map, one of the few teams" "LAT are pretty inconsistent at it" "FaZe... I just think they are sh*t right now" "I think Toronto is a good team" 👀😳

Shotzzy answer's on which top teams look the best right now 🗣️🌶️ "Paris know what they're doing on the map, one of the few teams" "LAT are pretty inconsistent at it" "FaZe... I just think they are sh*t right now" "I think Toronto is a good team" 👀😳

CDL Hater Central

167,973 просмотров • 8 месяцев назад