正在加载视频...

视频加载失败

返回首页

Matt Pocock (TypeScript wizard, ex-Vercel): "Opus 5 got addicted to writing tests that just repeat the code back to itself." in a 22-min talk at AI Engineer Paris, Matt walks through how to stop AI PRs from turning your repo into a slop cannon: 5:30 → the tests AI...

0xShoopy's profile picture

Shoopy

1,427 subscribers

174,215 次观看 • 18 天前 •via X (Twitter)

教育科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

35 条评论

Squizer 的头像
Squizer18 天前

the reviewer-should-commit-not-comment point is underrated. most AI review setups still route fixes back through a human typing the same patch by hand, which defeats half the point of having a reviewer agent

Shoopy 的头像
Shoopy18 天前

spot on, reviewer that comments instead of committing just creates more work

Anders Abjorn | sales → AI 的头像
Anders Abjorn | sales → AI18 天前

Tests that echo the code are a quiet fail. I ask for a case that would break if the function lied. Mirror tests feel green and teach nothing.

Shoopy 的头像
Shoopy18 天前

"mirror tests feel green and teach nothing" is a great way to put it

Anders Abjorn | sales → AI 的头像
Anders Abjorn | sales → AI18 天前

Yeah, I believe so. 😊

Daniel Nim 的头像
Daniel Nim18 天前

The idea of making the reviewer fix things instead of just leaving comments is huge!

Shoopy 的头像
Shoopy18 天前

right? half my review time used to be reading bot comments i then fixed myself

half_cto 的头像
half_cto18 天前

I wonder what has he built? Ohh right he's just talking, thats enough.

Shoopy 的头像
Shoopy18 天前

fair to judge the ideas, not the guy. the reviewer-commits-fixes part works regardless of who said it

half_cto 的头像
half_cto18 天前

yeah you are right, i'm just puzzled what have people been doing if this is something new? I get dude is "announcing skills" for "real engineers" though is he one? If i would like to be influencer there is a lot to learn from him, can't deny that.

Shoopy 的头像
Shoopy18 天前

full 3-layer system in one image ↓

Alexey Samoylov 的头像
Alexey Samoylov18 天前

That guy has a slop skill set and nothing more. He knows very little about the AI pull request review.

Shoopy 的头像
Shoopy18 天前

what would you do differently? genuinely curious what's working for you on AI PR review

Alexey Samoylov 的头像
Alexey Samoylov18 天前

I got my own AI review solution with the "bring your own agent" approach. It writes summaries and comments, performs issues classification, does the PR gating on the github/azure/gitlab.

Abdul Ahad 的头像
Abdul Ahad18 天前

@grok from this video explain step by step the whole process so i can replicate it

Crio Songo 的头像
Crio Songo18 天前

These points hit exactly the pain points of current AI coding. I'm gonna go watch this full talk right now.

Shoopy 的头像
Shoopy18 天前

the part at 15:34 is the one to steal first, reviewer commits instead of commenting

Akos 的头像
Akos18 天前

this was happening with older models too - 4.8. we also figured out what was the problem and created domain specific review agents which fixed the entire set of the problems!

Shoopy 的头像
Shoopy18 天前

domain-specific reviewers is the move. how many did you end up with, one per area of the codebase?

chuplung 的头像
chuplung18 天前

this talk is way more useful than most ai coding advice

Shoopy 的头像
Shoopy18 天前

glad it landed, practical > theoretical every time

࣪˖ sofi z, 的头像
࣪˖ sofi z,18 天前

Couldn't agree more

Shoopy 的头像
Shoopy18 天前

thanks

soooz 的头像
soooz18 天前

5 is the slide number. The permission story is still the footnote.

Shoopy 的头像
Shoopy18 天前

true, permissions get the headlines but the tests are the silent risk

qwinsi 的头像
qwinsi18 天前

Thx for sharing this broski, saved

Shoopy 的头像
Shoopy18 天前

appreciate it

CryptoNinjas 的头像
CryptoNinjas18 天前

Watching that exact part now and circular test generation is way too common lately.

Shoopy 的头像
Shoopy18 天前

circular tests are everywhere now. green CI, zero coverage of what the code actually does

GratefulPle₿ 🏴‍☠️⚡️ 的头像
GratefulPle₿ 🏴‍☠️⚡️18 天前

Ex vercel? Wasn’t it ex-voice coach now building hobby apps with ai?

Shoopy 的头像
Shoopy18 天前

both actually. voice coach before he got into typescript, then vercel. the talk still slaps either way

Konrad 的头像
Konrad18 天前

what happend to him

Shoopy 的头像
Shoopy18 天前

reviewed one too many AI PRs lol

Alex Martossy 的头像
Alex Martossy18 天前

Saying Matt is ex-Vercel is like how Lex Fridman is ex-MIT.

Gaetan Semet 的头像
Gaetan Semet18 天前

Thanks @mattpocockuk for this good video. Couple remarks: - "coding standards belong in a separate review agent" => yes, this confirms recent changes in all major "SDD" frameworks, converging to way I called "The Canonical Implementation Loop". You have a Coder agent and a Reviewer Agent. - "AI reviewer shouldn't comment. it should commit the fixes" => ok for the review once the PR is created, but I won't say that for the in-loop reviewer (I called "Task Inspector"). If you start an implementation loop in the reviewer, it can starts drifting from its goal of findings all the missed acceptance criteria and do it properly. It can "try" to do the fix if it is very small issue, to avoid restarting a new coder to fix the issue, but things like incomplete feature, it should sent the task back to the coder agent.

相关视频

Old way of using Claude Code: Prompt → wait → review → prompt → wait → review → repeat 20 times. You are the loop. You are the condition check. You are the reason it keeps going. New way: /goal all tests pass and lint is clean Claude works. You do something else. You come back to a result. Here's exactly how to set it up — and how to write conditions that actually work ↓
0:24

Old way of using Claude Code: Prompt → wait → review → prompt → wait → review → repeat 20 times. You are the loop. You are the condition check. You are the reason it keeps going. New way: /goal all tests pass and lint is clean Claude works. You do something else. You come back to a result. Here's exactly how to set it up — and how to write conditions that actually work ↓

Rahul

38,382 次观看 • 5 个月前

Lauren Tan is shipping 1000 of PRs a month with AI agents Matt Pocock just sat down with her to unpack how the system actually works: · 04:35 - how Lauren got to thousands of PRs without drowning in AI slop · 13:20 - why pstack starts with skills, not bigger prompts · 24:10 - verification: make the agent prove its work before you trust it · 36:45 - redesign the codebase so agents naturally take the right path · 49:30 - how to turn one coding agent into a high-velocity software factory the biggest lesson isn’t “run more agents.” it’s making one agent trustworthy enough that you can safely run 10, 20, then hundreds of tasks in parallel. skills → constraints → verification → cloud agents → parallel execution Lauren basically treats the codebase as infrastructure for the agents themselves. Humans decide what matters. Agents do the work, prove it works, and keep the loop moving. Probably one of the best conversations on agentic engineering right now. watch it before you add another 20-page prompt to your coding agent.
1:03:08

Lauren Tan is shipping 1000 of PRs a month with AI agents Matt Pocock just sat down with her to unpack how the system actually works: · 04:35 - how Lauren got to thousands of PRs without drowning in AI slop · 13:20 - why pstack starts with skills, not bigger prompts · 24:10 - verification: make the agent prove its work before you trust it · 36:45 - redesign the codebase so agents naturally take the right path · 49:30 - how to turn one coding agent into a high-velocity software factory the biggest lesson isn’t “run more agents.” it’s making one agent trustworthy enough that you can safely run 10, 20, then hundreds of tasks in parallel. skills → constraints → verification → cloud agents → parallel execution Lauren basically treats the codebase as infrastructure for the agents themselves. Humans decide what matters. Agents do the work, prove it works, and keep the loop moving. Probably one of the best conversations on agentic engineering right now. watch it before you add another 20-page prompt to your coding agent.

Morlex

22,614 次观看 • 11 天前

got Jev to review my PRs. ~200x cheaper than Claude and it answers in half a second 6 real PRs in the video. $0.00007 each. 1,000 PRs = 7 cents vs ~$14.50 on Opus 5 paste a diff → ONE call to TypeSafe AI → 14 typed checks come back as probabilities: hardcoded secret, sql injection, touches auth, deletes tests, breaks api, migration, debug leftovers, does the description actually match the diff, blast radius, reviewer effort… code turns that into a verdict: BLOCK / security review / nits / merge. anything a critical check isn't sure about (0.35–0.65) gets escalated to a human or a big model instead of guessed
0:32

got Jev to review my PRs. ~200x cheaper than Claude and it answers in half a second 6 real PRs in the video. $0.00007 each. 1,000 PRs = 7 cents vs ~$14.50 on Opus 5 paste a diff → ONE call to TypeSafe AI → 14 typed checks come back as probabilities: hardcoded secret, sql injection, touches auth, deletes tests, breaks api, migration, debug leftovers, does the description actually match the diff, blast radius, reviewer effort… code turns that into a verdict: BLOCK / security review / nits / merge. anything a critical check isn't sure about (0.35–0.65) gets escalated to a human or a big model instead of guessed

Paolo Rosson

359,546 次观看 • 27 天前

Free 3-hour course from an ex-Google engineer. AI agents, graph engineering, harness, agent loops. Covers more than most $500 paid courses. This is the exact playbook to learn how to actually build and monetize AI agents. Don't miss your shot, save it now. • 0:00 - Design an AI agent system from scratch • 7:38 - When your agent should hand off to a human • 19:27 - RAG and vector databases explained simply • 52:38 - Deploy your AI agent to Google Cloud • 1:25:57 - Turn AI agents into a paid business via WhatsApp • 1:33:00 - Turn conversations into real leads automatically • 2:24:01 - Loop engineering vs graphs, the real difference • 2:33:08 - Build your own multi-tool agent graph Save this video, because it's the only one that can actually take you to your $2,000+ profit.
2:45:36

Free 3-hour course from an ex-Google engineer. AI agents, graph engineering, harness, agent loops. Covers more than most $500 paid courses. This is the exact playbook to learn how to actually build and monetize AI agents. Don't miss your shot, save it now. • 0:00 - Design an AI agent system from scratch • 7:38 - When your agent should hand off to a human • 19:27 - RAG and vector databases explained simply • 52:38 - Deploy your AI agent to Google Cloud • 1:25:57 - Turn AI agents into a paid business via WhatsApp • 1:33:00 - Turn conversations into real leads automatically • 2:24:01 - Loop engineering vs graphs, the real difference • 2:33:08 - Build your own multi-tool agent graph Save this video, because it's the only one that can actually take you to your $2,000+ profit.

unicode

144,239 次观看 • 2 个月前

Google engineer: “Just delete your IDE—you don’t need it anymore. Ask Claude Code to run Claude Code for you. 85% of PRs at Google are already shipped by AI agents. If you aren’t building the harness around your agents, it’s crazy how far behind you are.” In this 90-minute talk, a Google engineer with 30 years of experience explains what the future of AI engineering will look like. Worth more than 10 paid agentic engineering courses. Watch it today, then read the article below to learn how to build a harness for reliable, self-improving AI agents.
1:32:54

Google engineer: “Just delete your IDE—you don’t need it anymore. Ask Claude Code to run Claude Code for you. 85% of PRs at Google are already shipped by AI agents. If you aren’t building the harness around your agents, it’s crazy how far behind you are.” In this 90-minute talk, a Google engineer with 30 years of experience explains what the future of AI engineering will look like. Worth more than 10 paid agentic engineering courses. Watch it today, then read the article below to learn how to build a harness for reliable, self-improving AI agents.

Ichigo

84,697 次观看 • 1 个月前

"Vibe coding is NOT the same as using AI to write code that's reviewed, tested, and maintained." Here's my new episode with Lee Robinson (Cursor's Head of AI Education) where he shows how to build AI apps properly using planning, test-driven development, agent workflows, and more. Some tips from Lee: 1. Work with AI to create a detailed technical plan upfront including requirements, design preferences, and your preferred tech stack. 2. Ask AI to write tests so that it can check its own work. Add this to the plan: "Write unit tests for business logic, e2e tests for core user journeys." 3. Add "make descriptive commits" to your initial plan so that you can track what AI changed and why. 📌 Watch our beginner-friendly tutorial now: Also available on: Spotify: Apple: Newsletter:
0:52

"Vibe coding is NOT the same as using AI to write code that's reviewed, tested, and maintained." Here's my new episode with Lee Robinson (Cursor's Head of AI Education) where he shows how to build AI apps properly using planning, test-driven development, agent workflows, and more. Some tips from Lee: 1. Work with AI to create a detailed technical plan upfront including requirements, design preferences, and your preferred tech stack. 2. Ask AI to write tests so that it can check its own work. Add this to the plan: "Write unit tests for business logic, e2e tests for core user journeys." 3. Add "make descriptive commits" to your initial plan so that you can track what AI changed and why. 📌 Watch our beginner-friendly tutorial now: Also available on: Spotify: Apple: Newsletter:

Peter Yang

108,418 次观看 • 1 年前

They built an AI agent in 20 minutes and sold it to Anthropic for $100k - and at Stanford showed how to repeat it from scratch: 02:00 - how to build your first agent with Opus 5 in 20 minutes 22:34 - one agent replaces an Anthropic engineering team worth $200k a year 49:47 - how to make $1.2M a year selling agents to Anthropic and Google after watching I spent 20 minutes in Claude Code - the agent replaced 10 Anthropic engineers and they paid $100k and asked for more. save & watch - the article below shows how to build an agent in Claude Code in 20 minutes and reach $1.2M a year.
1:09:01

They built an AI agent in 20 minutes and sold it to Anthropic for $100k - and at Stanford showed how to repeat it from scratch: 02:00 - how to build your first agent with Opus 5 in 20 minutes 22:34 - one agent replaces an Anthropic engineering team worth $200k a year 49:47 - how to make $1.2M a year selling agents to Anthropic and Google after watching I spent 20 minutes in Claude Code - the agent replaced 10 Anthropic engineers and they paid $100k and asked for more. save & watch - the article below shows how to build an agent in Claude Code in 20 minutes and reach $1.2M a year.

Noisy

135,108 次观看 • 1 个月前

They built an AI agent in 20 minutes and sold it to Anthropic for $100k - and at Stanford showed how to repeat it from scratch: 02:00 - how to build your first agent with Opus 5 in 20 minutes 22:34 - one agent replaces an Anthropic engineering team worth $200k a year 49:47 - how to make $1.2M a year selling agents to Anthropic and Google after watching I spent 20 minutes in Claude Code - the agent replaced 10 Anthropic engineers and they paid $100k and asked for more. save & watch - the article below shows how to build an agent in Claude Code in 20 minutes and reach $1.2M a year.
1:09:01

They built an AI agent in 20 minutes and sold it to Anthropic for $100k - and at Stanford showed how to repeat it from scratch: 02:00 - how to build your first agent with Opus 5 in 20 minutes 22:34 - one agent replaces an Anthropic engineering team worth $200k a year 49:47 - how to make $1.2M a year selling agents to Anthropic and Google after watching I spent 20 minutes in Claude Code - the agent replaced 10 Anthropic engineers and they paid $100k and asked for more. save & watch - the article below shows how to build an agent in Claude Code in 20 minutes and reach $1.2M a year.

shobhanai

82,227 次观看 • 24 天前

Anthropic just dropped a free 1-hour AI engineering workshop On how their engineers actually build with AI in 2026: 00:26 - Why prompting is becoming the old way 16:57 - The loop that builds, tests, and fixes its own work 25:27 - How one engineer can do the work of a 5-person team 36:25 - Build your first AI loop from scratch This 1-hour watch is worth more than most paid AI engineering courses Writing code is becoming the easy part Building the loop is the new skill Bookmark and watch it today Then build your own loop with the guide below
1:11:54

Anthropic just dropped a free 1-hour AI engineering workshop On how their engineers actually build with AI in 2026: 00:26 - Why prompting is becoming the old way 16:57 - The loop that builds, tests, and fixes its own work 25:27 - How one engineer can do the work of a 5-person team 36:25 - Build your first AI loop from scratch This 1-hour watch is worth more than most paid AI engineering courses Writing code is becoming the easy part Building the loop is the new skill Bookmark and watch it today Then build your own loop with the guide below

Lunar

15,125 次观看 • 2 个月前

.Postman is now natively available in your favorite coding agent! The new Postman CLI is designed to bring API engineering for agents: 1️⃣ Works in Git and your code repo - Just drop Postman where your agent lives and works. 2️⃣ No GUI - Work in your coding agent. Bring up the Postman UI for review and approval. 3️⃣ No sign-up - Get started right away. Sign-up when you have to save your work and want more. Install once, work in your agent. Run npm install -g postman-cli, then postman init. This loads Postman's skills into your coding agent so it can create collections, write tests, and much more. Available as a plugin for all coding agents! The skills cover the API lifecycle: find APIs your org already has, generate tests that catch regressions, mock an API before it exists, watch live endpoints for downtime and drift, run checks in CI on every commit, and run performance tests. You can also extend the abilities of your agent with the Context Graph. An agent often sees only the code that is accessible to them. The Context Graph API gives it a map of your team's infrastructure, APIs, and services, and how they depend on each other. As your agent works, you stay the reviewer. Your agent does the work from the command line. Open Postman when you want to review or approve it. Check out more at
0:37

.Postman is now natively available in your favorite coding agent! The new Postman CLI is designed to bring API engineering for agents: 1️⃣ Works in Git and your code repo - Just drop Postman where your agent lives and works. 2️⃣ No GUI - Work in your coding agent. Bring up the Postman UI for review and approval. 3️⃣ No sign-up - Get started right away. Sign-up when you have to save your work and want more. Install once, work in your agent. Run npm install -g postman-cli, then postman init. This loads Postman's skills into your coding agent so it can create collections, write tests, and much more. Available as a plugin for all coding agents! The skills cover the API lifecycle: find APIs your org already has, generate tests that catch regressions, mock an API before it exists, watch live endpoints for downtime and drift, run checks in CI on every commit, and run performance tests. You can also extend the abilities of your agent with the Context Graph. An agent often sees only the code that is accessible to them. The Context Graph API gives it a map of your team's infrastructure, APIs, and services, and how they depend on each other. As your agent works, you stay the reviewer. Your agent does the work from the command line. Open Postman when you want to review or approve it. Check out more at

Abhinav Asthana

493,402 次观看 • 13 天前

this AI agentic stack is f*cking crazy 8 open-source repos that cover everything you need to run AI agents for free. not a random "top tools" dump. each one handles a different part of the job: BUILD > video-use - drop raw footage in a folder, tell Claude Code "make a launch video", get back final.mp4. it cuts filler words, adds subtitles, grades color > > Univer - a full office suite made for agents. they edit your sheets, docs and slides in a draft, you review and merge > ORCHESTRATE > Superpowers - stops your coding agent from writing code blindly. it plans first, splits work into 2–5 min tasks, tests everything > > Treg - OpenRouter, but for agent tools. one key, ~2,600 endpoints from 40+ providers: scraping, SEO, email finding > ACT > Mobile MCP - your agent controls a real iPhone or Android. taps, swipes, installs apps, records the screen > > security-audit-skill - Cloudflare's own skill that turns your coding agent into a security auditor. one agent hunts bugs, a different one double-checks every finding > REMEMBER · TEST · SHIP > Hindsight - memory that actually learns. it doesn't just recall old chats, it builds beliefs and updates them over time > > Graphify - turns your whole codebase into a map your agent can query instead of grepping files blindly. zero LLM cost to build it > the cool part isn't any single repo. it's that your agent can now: edit video -> work in Excel -> plan like a senior dev -> use 2,600 tools -> drive a phone -> audit its own code -> learn -> know your codebase you don't have to build an AI employee from scratch anymore. every part is already on GitHub. you just put it together. bookmark this before you start your next agent.
0:37

this AI agentic stack is f*cking crazy 8 open-source repos that cover everything you need to run AI agents for free. not a random "top tools" dump. each one handles a different part of the job: BUILD > video-use - drop raw footage in a folder, tell Claude Code "make a launch video", get back final.mp4. it cuts filler words, adds subtitles, grades color > > Univer - a full office suite made for agents. they edit your sheets, docs and slides in a draft, you review and merge > ORCHESTRATE > Superpowers - stops your coding agent from writing code blindly. it plans first, splits work into 2–5 min tasks, tests everything > > Treg - OpenRouter, but for agent tools. one key, ~2,600 endpoints from 40+ providers: scraping, SEO, email finding > ACT > Mobile MCP - your agent controls a real iPhone or Android. taps, swipes, installs apps, records the screen > > security-audit-skill - Cloudflare's own skill that turns your coding agent into a security auditor. one agent hunts bugs, a different one double-checks every finding > REMEMBER · TEST · SHIP > Hindsight - memory that actually learns. it doesn't just recall old chats, it builds beliefs and updates them over time > > Graphify - turns your whole codebase into a map your agent can query instead of grepping files blindly. zero LLM cost to build it > the cool part isn't any single repo. it's that your agent can now: edit video -> work in Excel -> plan like a senior dev -> use 2,600 tools -> drive a phone -> audit its own code -> learn -> know your codebase you don't have to build an AI employee from scratch anymore. every part is already on GitHub. you just put it together. bookmark this before you start your next agent.

kiosa

12,887 次观看 • 16 天前

AI didn't make code cheap. it made bad code lethal. Matt Pocock: "Software fundamentals matter more than ever" AI in a good codebase ships gold. AI in a bad codebase ships garbage. framework mastery doesn't compound. fundamentals do. if you're starting with AI agents, build these 5 patterns before anything else: > Tool Use Design Pattern. tool calling is the core of every useful agent. > Agentic RAG. grounded answers over hallucination. maps to real products. > Planning Design Pattern. agents that break a goal into steps before acting. > Multi-Agent Design Pattern. orchestrator-subagent is the only shape that ships in production. > Building Trustworthy AI Agents. reliability, safety, knowing when not to use one. this article covers what to learn, build, and skip in AI agents in 2026. bookmark and read this today. repo with 500 more in comments
4:00

AI didn't make code cheap. it made bad code lethal. Matt Pocock: "Software fundamentals matter more than ever" AI in a good codebase ships gold. AI in a bad codebase ships garbage. framework mastery doesn't compound. fundamentals do. if you're starting with AI agents, build these 5 patterns before anything else: > Tool Use Design Pattern. tool calling is the core of every useful agent. > Agentic RAG. grounded answers over hallucination. maps to real products. > Planning Design Pattern. agents that break a goal into steps before acting. > Multi-Agent Design Pattern. orchestrator-subagent is the only shape that ships in production. > Building Trustworthy AI Agents. reliability, safety, knowing when not to use one. this article covers what to learn, build, and skip in AI agents in 2026. bookmark and read this today. repo with 500 more in comments

Rohit

28,480 次观看 • 5 个月前

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 👇
29:58

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

846,608 次观看 • 4 个月前

APPLE JUST SHOWED HOW TO RUN 10 AI AGENTS LOCALLY ON MAC - NO CLOUD, NO API KEYS, ZERO COSTS 00:10 Apple engineer says: "your data stays on your device, AI available anywhere at any time, zero usage costs" agent reads your code, checks GitHub, finds what needs attention and writes a report - all on your Mac, nothing goes to the internet 10 agents work simultaneously - one writes code, another tests, third fixes bugs - parallel with no queue built a full iPad app from scratch in 2 minutes, fixed its own mistakes and compiled without issues takes 5 minutes to set up - and you never pay again for a bot that runs 24/7
13:29

APPLE JUST SHOWED HOW TO RUN 10 AI AGENTS LOCALLY ON MAC - NO CLOUD, NO API KEYS, ZERO COSTS 00:10 Apple engineer says: "your data stays on your device, AI available anywhere at any time, zero usage costs" agent reads your code, checks GitHub, finds what needs attention and writes a report - all on your Mac, nothing goes to the internet 10 agents work simultaneously - one writes code, another tests, third fixes bugs - parallel with no queue built a full iPad app from scratch in 2 minutes, fixed its own mistakes and compiled without issues takes 5 minutes to set up - and you never pay again for a bot that runs 24/7

Noisy

526,822 次观看 • 3 个月前

"The one thing that's going to be truly future proof is judgment. What is the biggest challenge when you have a thousand AI engineers writing code? AI slop. In an era when you can do everything, the question is which of these things matter. On the engineer side, it is evaluating the code. Which of this code is even valuable? You can have AI engineers writing beautiful code that could be wrong, that could have bugs in it, that could be vulnerable. Someone needs to review it. Make sure to have a human review at some point, especially critical code that is in the core of your system. On the product side is judgment around what needs to be built and evaluating. And similarly in design, you have to have judgment around, does it make sense in the broader design system. I think this judgment is the number one thing that humans are going to bring in an era of infinite productivity."
1:12

"The one thing that's going to be truly future proof is judgment. What is the biggest challenge when you have a thousand AI engineers writing code? AI slop. In an era when you can do everything, the question is which of these things matter. On the engineer side, it is evaluating the code. Which of this code is even valuable? You can have AI engineers writing beautiful code that could be wrong, that could have bugs in it, that could be vulnerable. Someone needs to review it. Make sure to have a human review at some point, especially critical code that is in the core of your system. On the product side is judgment around what needs to be built and evaluating. And similarly in design, you have to have judgment around, does it make sense in the broader design system. I think this judgment is the number one thing that humans are going to bring in an era of infinite productivity."

Patrick OShaughnessy

24,818 次观看 • 8 个月前

ANTHROPIC LEAKED 6 RULES THAT RUN 8 LOOPS AT ONCE - AND ONE ENGINEER DOES THE WORK OF A TEAM one engineer with this system replaces an entire team - and costs the company 8 times less You → Opus 5 plan → Fable 5 ×8 execute → Fable 5 review → you: 5 min Opus 5 takes your intent and breaks it into subtasks - a bad plan multiplied across every loop gives the same number of disasters - the plan is the only thing you read carefully one repo - isolated worktrees for each loop - nobody stands on anyone's file - parallel PRs ship while you do nothing the agent runs the tests and fixes until green PR - a red build never reaches your eyes one CLAUDE.md for the whole fleet - without it you get different opinions from every loop and one merge hell the average engineer closes 3-4 tasks a day - this system closes a full sprint overnight with zero working hours Fable 5 pre-reviews every PR before it reaches you - you spend 5 minutes - your throughput is now measured in diffs read per hour bookmark and paste into Claude Code - your first fleet can start tonight
1:15

ANTHROPIC LEAKED 6 RULES THAT RUN 8 LOOPS AT ONCE - AND ONE ENGINEER DOES THE WORK OF A TEAM one engineer with this system replaces an entire team - and costs the company 8 times less You → Opus 5 plan → Fable 5 ×8 execute → Fable 5 review → you: 5 min Opus 5 takes your intent and breaks it into subtasks - a bad plan multiplied across every loop gives the same number of disasters - the plan is the only thing you read carefully one repo - isolated worktrees for each loop - nobody stands on anyone's file - parallel PRs ship while you do nothing the agent runs the tests and fixes until green PR - a red build never reaches your eyes one CLAUDE.md for the whole fleet - without it you get different opinions from every loop and one merge hell the average engineer closes 3-4 tasks a day - this system closes a full sprint overnight with zero working hours Fable 5 pre-reviews every PR before it reaches you - you spend 5 minutes - your throughput is now measured in diffs read per hour bookmark and paste into Claude Code - your first fleet can start tonight

Sprytix

37,904 次观看 • 2 个月前

My friend makes $850,000/year as an Anthropic AI engineer. No MIT. No Stanford. No PhD. I asked him how he broke into AI from scratch. He sent me a course that was never supposed to get out. A developer teaching to build self-improving AI agents from scratch. You will learn exactly how AI agents like Claude Code and OpenClaw are actually built. You won't find anything better about becoming an AI engineer in 2026 than this video. I watched it last night. Halfway through, I realized I could land a role at a top AI lab in months, not years. Bookmark this and read the article below.
3:05:57

My friend makes $850,000/year as an Anthropic AI engineer. No MIT. No Stanford. No PhD. I asked him how he broke into AI from scratch. He sent me a course that was never supposed to get out. A developer teaching to build self-improving AI agents from scratch. You will learn exactly how AI agents like Claude Code and OpenClaw are actually built. You won't find anything better about becoming an AI engineer in 2026 than this video. I watched it last night. Halfway through, I realized I could land a role at a top AI lab in months, not years. Bookmark this and read the article below.

Roan

70,905 次观看 • 3 个月前

My friend applied to 200 tech jobs in two years. No MIT. No Stanford. Last month SpaceXAI offered him $750,000. I asked him how he broke in from zero. He sent me the exact video that got him in. A 1 hour course on "Complete AI Engineering in 2026". Matt Pocock shows you how to architect & build AI agents like Grok Bot from scratch. The exact AI-assisted coding workflow that lets agents ship code while you sleep. I watched it last night. Halfway through, I realized I could break into an AI lab in days, not years. Bookmark this and read the article below.
1:34:32

My friend applied to 200 tech jobs in two years. No MIT. No Stanford. Last month SpaceXAI offered him $750,000. I asked him how he broke in from zero. He sent me the exact video that got him in. A 1 hour course on "Complete AI Engineering in 2026". Matt Pocock shows you how to architect & build AI agents like Grok Bot from scratch. The exact AI-assisted coding workflow that lets agents ship code while you sleep. I watched it last night. Halfway through, I realized I could break into an AI lab in days, not years. Bookmark this and read the article below.

Roan

36,220 次观看 • 1 个月前

Obsidian CEO actually released the skill that lets your AI agent run your entire vault for you. It's called obsidian-skills. Install it into Claude Code, Codex, or OpenCode, and your agent can read, create, search, and organize notes directly, plus handle Markdown, Bases, and Canvas files without you touching a thing. This is the missing piece for an AI second brain. Your notes live in Obsidian, and now the agent actually knows how to work them. Want the full picture? We broke down how to build a complete AI second brain from scratch in the article below.
0:23

Obsidian CEO actually released the skill that lets your AI agent run your entire vault for you. It's called obsidian-skills. Install it into Claude Code, Codex, or OpenCode, and your agent can read, create, search, and organize notes directly, plus handle Markdown, Bases, and Canvas files without you touching a thing. This is the missing piece for an AI second brain. Your notes live in Obsidian, and now the agent actually knows how to work them. Want the full picture? We broke down how to build a complete AI second brain from scratch in the article below.

Simplifying AI

68,025 次观看 • 2 个月前

AI isn't just changing the tools designers use. It's changing how they build, ship, and stand out. In this episode of Design Review, Stephen Haney, founder of AI-native design tool Paper, joins YC's Aaron Epstein to demo the agent-first workflow that's making Paper one of the fastest-growing design tools since Figma. Using live redesigns of user-submitted websites as examples, they break down the most common AI design tells, show how to fix them in seconds, and explain why the biggest risk for founders isn't moving too slow, it's shipping something that looks like everyone else. 01:04 - What is Paper and why build it? 03:17 - What makes Paper agent-native 05:11 - Demo: Shaders, image generation, and brand design 11:32 - Design-to-code and the new agent stack 16:48 - Design Review: Legion Health 24:11 - How to avoid AI design slop 28:26 - Design Review: Sytex 32:42 - The biggest tells of AI-generated design 37:39 - Design Review: Moreta 41:11 - Can AI learn taste? 43:56 - How Paper uses agents internally 46:52 - Building a community around Paper 49:15 - Lessons from Steven’s first startup 53:30 - What’s next for design and Paper
56:01

AI isn't just changing the tools designers use. It's changing how they build, ship, and stand out. In this episode of Design Review, Stephen Haney, founder of AI-native design tool Paper, joins YC's Aaron Epstein to demo the agent-first workflow that's making Paper one of the fastest-growing design tools since Figma. Using live redesigns of user-submitted websites as examples, they break down the most common AI design tells, show how to fix them in seconds, and explain why the biggest risk for founders isn't moving too slow, it's shipping something that looks like everyone else. 01:04 - What is Paper and why build it? 03:17 - What makes Paper agent-native 05:11 - Demo: Shaders, image generation, and brand design 11:32 - Design-to-code and the new agent stack 16:48 - Design Review: Legion Health 24:11 - How to avoid AI design slop 28:26 - Design Review: Sytex 32:42 - The biggest tells of AI-generated design 37:39 - Design Review: Moreta 41:11 - Can AI learn taste? 43:56 - How Paper uses agents internally 46:52 - Building a community around Paper 49:15 - Lessons from Steven’s first startup 53:30 - What’s next for design and Paper

Y Combinator

119,049 次观看 • 2 个月前