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

1/ Reviewing agent-written code usually comes down to reading a diff and hoping. That is the part of the workflow nobody solved. The models got very good at producing code, and the burden quietly moved to the person who has to decide whether it is safe to merge. You... show more

Chubby♨️

143,275 subscribers

16,711 просмотров • 1 месяц назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 16

Фото профиля Chubby♨️

Chubby♨️1 месяц назад

2/ Because the stack is really up, the test suite really runs. The agent builds the app, executes the tests, then opens a browser and clicks through the flow the way a user would. That run gets recorded, and the video is attached to the PR. So when the PR arrives, you watch the feature do the thing it claims to do, and then you approve the merge. It turns review from an act of trust into a few minutes of watching.

Фото профиля Chubby♨️

Chubby♨️1 месяц назад

3/ The full loop is plan, build, test, review, merge. You set the destination with two links and a sentence, and the plan comes back to you for approval before anything gets built. From there you supervise by exception. If something drifts, you correct it. If it does not, you approve the result. That plan-approval step matters more than it sounds. It is where you catch a wrong interpretation for the price of one message instead of one wasted afternoon.

Фото профиля Chubby♨️

Chubby♨️1 месяц назад

4/ Who is behind it: Prasanna Sankar, co-founder and former CTO of Rippling. Vorflux came out of stealth with a $15M seed led by Y Combinator, joined by Peak XV, Powerset and Alliance. They do not train their own models. They route across providers and assign per task, which is the sane call when the hard part sits in the harness around the model. 5/ Honest framing: this is built for teams carrying a real backlog and real testing debt. If you are poking at a small side project, it is more machinery than you need. For bigger installs their team configures the harness with you directly. You can sign up and run sessions yourself at @vorfluxai

Фото профиля Hussain Hashim | Building SundayBack

Hussain Hashim | Building SundayBack1 месяц назад

@kimmonismus totally get this. it's like we're outsourcing code review stress to devs now. trained models but human headaches.

Фото профиля Ian

Ian1 месяц назад

It sounds great but does it offer more benefits than just using a dual monitor and having an agent build and QA there. Instead of paying for a service to host your runs? It makes sense for the upcoming cloud dev wave and for agents but on cost and efficacy how does it compare?

Фото профиля Meshak

Meshak1 месяц назад

testing by watching a video, sounds really good

Фото профиля 安叫兽|Bird🕊️ 🔶 BNB

安叫兽|Bird🕊️ 🔶 BNB1 месяц назад

生成快了，审查反而成了新的瓶颈。

Фото профиля Dani Debatte

Dani Debatte1 месяц назад

That more or less resembles my Rails dev workflow with TDD and the Spec-kit extension MAQA. Gonna take a look...

Фото профиля Elodie 3DFontaine

Elodie 3DFontaine1 месяц назад

After reviewing agent-written code for the fourth time this quarter, I’ve concluded that instinct and hope are the final boss of every merge.

Фото профиля DeDi

DeDi1 месяц назад

代码审查会成为代理工作流的主要瓶颈

Фото профиля DP (Durgaprasad)

DP (Durgaprasad)1 месяц назад

Thanks for featuring us

Фото профиля Crio Songo

Crio Songo1 месяц назад

That’s a really smart approach, right? Running AI-written code in a real production-like environment directly exposes hidden issues you can’t catch just reading diffs. This moves the verification burden back from humans to the platform, which is exactly what AI code workflow has been missing.

Фото профиля Sharon Riley

Sharon Riley1 месяц назад

Real environments make agent reviews safer

Фото профиля Ryan Tech Future

Ryan Tech Future1 месяц назад

That's great

Фото профиля Michael R Dawley Jr

Michael R Dawley Jr1 месяц назад

Strong thread. Moving review from reading a diff to watching evidence from a live stack is real progress. The next test is reproducibility: diverse model checks, replayable runs, idempotent retries, rollback and recovery. Otherwise the human bottleneck just moves.

Фото профиля Synapse Brief

Synapse Brief1 месяц назад

The real unlock here isn’t the agent — it’s the harness. Vorflux doesn’t train models; it routes across providers per task. That’s the sane architectural call when the hard part is orchestration, not generation. Prasanna Sankar built Rippling’s HR automation layer from the ground up as CTO. The man knows enterprise workflow stitching. Vorflux is that same “single source of truth” muscle applied to the dev loop — plan, build, test, review, merge. The video proof attached to every PR is the killer signal. Review shifts from reading a diff on instinct to watching the feature execute in a real cloud stack. That’s not a coding agent — it’s a verification engine. $15M seed from YC, Peak XV, and Balaji Srinivasan. The bet: tokens are cheap, human attention is the bottleneck. Vorflux spends tokens to save the one resource that actually scales a team.

Похожие видео

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!

GREG ISENBERG

30,787 просмотров • 29 дней назад

Claude Code creator: "implementation is no longer the scarce resource" if writing the code is free, the real question is what is scarce now. it's everything you have to hand the model before it can start. your stack, your conventions, the decisions you already made. none of that got cheaper, because you re-supply it from scratch every session. the model got faster at building. it never got faster at learning who you are. read the article below for what changed when it finally did.

Claude Code creator: "implementation is no longer the scarce resource" if writing the code is free, the real question is what is scarce now. it's everything you have to hand the model before it can start. your stack, your conventions, the decisions you already made. none of that got cheaper, because you re-supply it from scratch every session. the model got faster at building. it never got faster at learning who you are. read the article below for what changed when it finally did.

Mnimiy

11,086 просмотров • 2 месяцев назад

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

The Startup Ideas Podcast (SIP) 🧃

17,326 просмотров • 1 месяц назад

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Santiago

64,438 просмотров • 10 месяцев назад

Workflows vs. Graphs, clearly explained! workflows are great, and almost everyone has one. here is the ceiling: a workflow decides every step before it runs. you drew eight boxes in March. six months later the same three fire, every single time, and the other five have never once been reached. then a case arrives that nobody drew, and it goes to the closest wrong box. quietly, with a green status, because from the inside that looks exactly like success. Graph engineering fixes this by moving the decision: not what the steps do, but when the steps get chosen. you need both, and here is the sentence that resolves the whole confusion: a workflow decides the steps before it runs. a graph decides them while it runs. ↳ drawn in advance: the boxes, the branches, the order, the error path ↳ decided at runtime: how many units exist, what each one is allowed to see, which ones get created at all Prompts → Context → Harness → Loops → Graphs branches do not make it a graph. the branches were drawn in advance too, which means every one of them is a case you already thought of. the trick is knowing which part is allowed to be fixed. the node kinds are fixed. a splitter is a splitter, a gate is a gate, a merge is code. what is not fixed is how many of them exist this run, and that is decided after something has been read. one thing to know before you scale it. a workflow fails in a way that never pages anyone. ↳ the wrong branch ran, every check inside it passed, and the output is well formed ↳ nothing errored, because routing to the wrong box is not an error, it is a route that last one catches careful people. you cannot test your way out of it either, because the test suite was written from the same diagram that has the gap in it. and the one that eats whole nights: a workflow that has never surprised you is not stable, it is narrow. if it has run four hundred times and produced the same three shapes, it is not handling your work. it is handling the part of your work that fits it, and you have quietly stopped sending it the rest. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Workflows vs. Graphs, clearly explained! workflows are great, and almost everyone has one. here is the ceiling: a workflow decides every step before it runs. you drew eight boxes in March. six months later the same three fire, every single time, and the other five have never once been reached. then a case arrives that nobody drew, and it goes to the closest wrong box. quietly, with a green status, because from the inside that looks exactly like success. Graph engineering fixes this by moving the decision: not what the steps do, but when the steps get chosen. you need both, and here is the sentence that resolves the whole confusion: a workflow decides the steps before it runs. a graph decides them while it runs. ↳ drawn in advance: the boxes, the branches, the order, the error path ↳ decided at runtime: how many units exist, what each one is allowed to see, which ones get created at all Prompts → Context → Harness → Loops → Graphs branches do not make it a graph. the branches were drawn in advance too, which means every one of them is a case you already thought of. the trick is knowing which part is allowed to be fixed. the node kinds are fixed. a splitter is a splitter, a gate is a gate, a merge is code. what is not fixed is how many of them exist this run, and that is decided after something has been read. one thing to know before you scale it. a workflow fails in a way that never pages anyone. ↳ the wrong branch ran, every check inside it passed, and the output is well formed ↳ nothing errored, because routing to the wrong box is not an error, it is a route that last one catches careful people. you cannot test your way out of it either, because the test suite was written from the same diagram that has the gap in it. and the one that eats whole nights: a workflow that has never surprised you is not stable, it is narrow. if it has run four hundred times and produced the same three shapes, it is not handling your work. it is handling the part of your work that fits it, and you have quietly stopped sending it the rest. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

16,810 просмотров • 1 месяц назад

The part people sleep on: ask your agent to help manage the portfolio after it's built. Set conditions, run it on a schedule, have it flag anything worth your attention. You get a push notification every time it trades and real-time P&L in the app, so you're never out of the loop.

The part people sleep on: ask your agent to help manage the portfolio after it's built. Set conditions, run it on a schedule, have it flag anything worth your attention. You get a push notification every time it trades and real-time P&L in the app, so you're never out of the loop.

Robinhood

83,659 просмотров • 2 месяцев назад

XBOW raised $117M to build AI hacking agents. Now someone just open-sourced it for FREE. Strix deploys autonomous AI agents that act like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proof-of-concepts. Why it matters: The biggest problem with traditional security testing is that it doesn't keep up with development speed. Strix solves this by integrating directly into your workflow: ↳ Run it in CI/CD to catch vulnerabilities before production ↳ Get real proof-of-concepts, not false positives from static analysis ↳ Test everything: injection attacks, access control, business logic flaws The best part? You don't need to be a security expert. Strix includes a complete hacker toolkit - HTTP proxy, browser automation, and Python runtime for exploit development. It's like having a security team that works at the speed of your CI/CD pipeline. The best part is that the tool runs locally in Docker containers, so your code never leaves your environment. Getting started is simple: - pipx install strix-agent - Point it at your codebase (app, repo, or directory) Everything is 100% open-source! I've shared link to the GitHub repo in the replies!

XBOW raised $117M to build AI hacking agents. Now someone just open-sourced it for FREE. Strix deploys autonomous AI agents that act like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proof-of-concepts. Why it matters: The biggest problem with traditional security testing is that it doesn't keep up with development speed. Strix solves this by integrating directly into your workflow: ↳ Run it in CI/CD to catch vulnerabilities before production ↳ Get real proof-of-concepts, not false positives from static analysis ↳ Test everything: injection attacks, access control, business logic flaws The best part? You don't need to be a security expert. Strix includes a complete hacker toolkit - HTTP proxy, browser automation, and Python runtime for exploit development. It's like having a security team that works at the speed of your CI/CD pipeline. The best part is that the tool runs locally in Docker containers, so your code never leaves your environment. Getting started is simple: - pipx install strix-agent - Point it at your codebase (app, repo, or directory) Everything is 100% open-source! I've shared link to the GitHub repo in the replies!

Akshay 🚀

96,875 просмотров • 11 месяцев 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

194,698 просмотров • 6 месяцев назад

You probably know OpenClaw🦞, one of the fastest-growing open-source projects around. An OpenClaw harness lets you build, code, analyze, and take real control of your machine. But the more access an agent has to your machine, the more it matters where your data goes & who can see it. With QVAC, you can run your OpenClaw agent fully on your own machine in a few minutes. Nothing leaves your computer. Full setup guide on the blog, see first comment below. 💡 Pro tip: already running OpenClaw? Send the blog article to your agent and let the it do the set up.

You probably know OpenClaw🦞, one of the fastest-growing open-source projects around. An OpenClaw harness lets you build, code, analyze, and take real control of your machine. But the more access an agent has to your machine, the more it matters where your data goes & who can see it. With QVAC, you can run your OpenClaw agent fully on your own machine in a few minutes. Nothing leaves your computer. Full setup guide on the blog, see first comment below. 💡 Pro tip: already running OpenClaw? Send the blog article to your agent and let the it do the set up.

QVAC

15,019,651 просмотров • 3 месяцев назад

Agents write code faster than we can review it. A huge PR is essentially a long list of files in alphabetical order. We think reviews can be more fun if you swap the limiting pages for a canvas, which is why we built PR canvas. You read the change in the order the logic runs. - A short summary shown on each card to help you understand what the piece of code does. - The canvas shows the relationship between each group. - Possible issues to check before approving, with standby agents of choice ready to attend to any of them. - Comment, mark as issue, and approve PRs. - Agents can also locally clarify on feedback before you mark as an issue. - It runs on your Mac, with your gh and your Claude Code/Codex/any available agent.

Agents write code faster than we can review it. A huge PR is essentially a long list of files in alphabetical order. We think reviews can be more fun if you swap the limiting pages for a canvas, which is why we built PR canvas. You read the change in the order the logic runs. - A short summary shown on each card to help you understand what the piece of code does. - The canvas shows the relationship between each group. - Possible issues to check before approving, with standby agents of choice ready to attend to any of them. - Comment, mark as issue, and approve PRs. - Agents can also locally clarify on feedback before you mark as an issue. - It runs on your Mac, with your gh and your Claude Code/Codex/any available agent.

Seyi

11,688 просмотров • 7 дней назад

The biggest marketplace on Earth won't be the assets humans own. It'll be the data AI needs. Everything that can be digitised is getting pulled in to train the next models. Every scientific dataset, every piece of research sitting in a university, every sensor reading off every John Deere tractor in a field. All of it feeds the machine, and almost none of it is visible to us. What comes out is an agentic economy running at machine speed. You plug your data into a vault, and agents monetise it on your behalf, trading with other agents in real time, in a marketplace we never see. The company sitting on proprietary data becomes part of it without even knowing. This is what the Economic Singularity actually looks like from the inside. The real economy stops being the one we can see and price, and moves somewhere we can't follow. You own a piece of it, or you get priced out of it. Jordi Visser.

The biggest marketplace on Earth won't be the assets humans own. It'll be the data AI needs. Everything that can be digitised is getting pulled in to train the next models. Every scientific dataset, every piece of research sitting in a university, every sensor reading off every John Deere tractor in a field. All of it feeds the machine, and almost none of it is visible to us. What comes out is an agentic economy running at machine speed. You plug your data into a vault, and agents monetise it on your behalf, trading with other agents in real time, in a marketplace we never see. The company sitting on proprietary data becomes part of it without even knowing. This is what the Economic Singularity actually looks like from the inside. The real economy stops being the one we can see and price, and moves somewhere we can't follow. You own a piece of it, or you get priced out of it. Jordi Visser.

Raoul Pal

79,211 просмотров • 2 месяцев назад

Anthropic Claude Code engineer: "The moment you're reviewing every line Claude writes, you became its tester. You weren't hired for that." this 36 min talk is the clearest breakdown of how to get yourself out of the loop entirely the shift is simple: you stop prompting and start building agents that work instead of you agents that run, check themselves, and keep going while your laptop is closed watch it, then build your own with the step-by-step guide below

Anthropic Claude Code engineer: "The moment you're reviewing every line Claude writes, you became its tester. You weren't hired for that." this 36 min talk is the clearest breakdown of how to get yourself out of the loop entirely the shift is simple: you stop prompting and start building agents that work instead of you agents that run, check themselves, and keep going while your laptop is closed watch it, then build your own with the step-by-step guide below

Anatoli Kopadze

28,042 просмотров • 3 месяцев назад

Build it once. Earn every time someone uses it. Wrap your workflow with input and output nodes, hit publish, and your one-click app goes live to millions of creators. You choose how it lives: Keep it private, share with your team, or let the whole community run it. And every single time someone runs your app? Credits land in your account. No extra work. No maintenance. Just your creativity quietly paying you back, on repeat. Your workflow. Your rules. Your credits.

Build it once. Earn every time someone uses it. Wrap your workflow with input and output nodes, hit publish, and your one-click app goes live to millions of creators. You choose how it lives: Keep it private, share with your team, or let the whole community run it. And every single time someone runs your app? Credits land in your account. No extra work. No maintenance. Just your creativity quietly paying you back, on repeat. Your workflow. Your rules. Your credits.

ImagineArt

323,644 просмотров • 5 месяцев назад

My new favorite way to build with agents is to organize them into a factory. This is the 4-step workflow: 1) Station. - A custom order gets its own station, so the order does not interfere with the rest of production. - In software, this station is a branch or a work tree. 2) Assembly line. - The agent writes code, changes files, and adds structure. 3) Quality control. - Does it turn on? - Does it fit? - Does it break under pressure? - In software, you run tests, open a preview, and read the logs and screenshots. 4) Shipping. - The product goes out the door. - You merge, deploy the PR, and write release notes. If a product fails quality control, you send feedback to the product team. Then you do the loop again. Write each step of your agent workflow as a factory job.

My new favorite way to build with agents is to organize them into a factory. This is the 4-step workflow: 1) Station. - A custom order gets its own station, so the order does not interfere with the rest of production. - In software, this station is a branch or a work tree. 2) Assembly line. - The agent writes code, changes files, and adds structure. 3) Quality control. - Does it turn on? - Does it fit? - Does it break under pressure? - In software, you run tests, open a preview, and read the logs and screenshots. 4) Shipping. - The product goes out the door. - You merge, deploy the PR, and write release notes. If a product fails quality control, you send feedback to the product team. Then you do the loop again. Write each step of your agent workflow as a factory job.

The Startup Ideas Podcast (SIP) 🧃

13,017 просмотров • 28 дней назад

THIS GUY VIBE CODED AN APP WITH CLAUDE CODE THAT SCANS YOUR RUBIKS CUBE AND SHOWS YOU HOW TO SOLVE IT IN 20 MOVES OR LESS theres a math fact called gods number. no matter how badly a rubiks cube is scrambled, it can always be solved in 20 moves or fewer this app actually shows you how: > point your camera at the cube and it reads the sticker colors on each side > it captures all 6 faces and figures out the exact state of the scrambled cube > then it computes the shortest solution, always 20 moves or under > you follow a 3d guide that walks you through each move until its solved so instead of being stuck on a scrambled cube forever, you scan it and get the shortest possible path to solved. the cool part is it all runs right in your browser, no install, no backend. it uses opencv to detect the cube, reads the colors in a way thats way more reliable under bad lighting, and runs the actual solving algorithm in the background so it keeps searching until the answer is 20 moves or fewer. in theory you only need to show it 3 sides for it to work

THIS GUY VIBE CODED AN APP WITH CLAUDE CODE THAT SCANS YOUR RUBIKS CUBE AND SHOWS YOU HOW TO SOLVE IT IN 20 MOVES OR LESS theres a math fact called gods number. no matter how badly a rubiks cube is scrambled, it can always be solved in 20 moves or fewer this app actually shows you how: > point your camera at the cube and it reads the sticker colors on each side > it captures all 6 faces and figures out the exact state of the scrambled cube > then it computes the shortest solution, always 20 moves or under > you follow a 3d guide that walks you through each move until its solved so instead of being stuck on a scrambled cube forever, you scan it and get the shortest possible path to solved. the cool part is it all runs right in your browser, no install, no backend. it uses opencv to detect the cube, reads the colors in a way thats way more reliable under bad lighting, and runs the actual solving algorithm in the background so it keeps searching until the answer is 20 moves or fewer. in theory you only need to show it 3 sides for it to work

Om Patel

85,695 просмотров • 3 месяцев назад

Your AI agent is writing code nobody reviewed and running it on your machine. Most teams answer "where does it run" with a container and a hope. Introducing CreateOS Sandbox. Run code you cannot trust, with the networking, egress control, and self-hosting you need. 🧵

Your AI agent is writing code nobody reviewed and running it on your machine. Most teams answer "where does it run" with a container and a hope. Introducing CreateOS Sandbox. Run code you cannot trust, with the networking, egress control, and self-hosting you need. 🧵

CreateOS

14,000 просмотров • 3 месяцев назад

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."

The Pragmatic Engineer

39,073 просмотров • 4 месяцев назад

If you're new to apps, you need to use XcodeBuildMCP. It takes all the rough edges out of working with Codex or Claude Code and Xcode. Your agent can build and run your app, and even check the UI to see if it looks good via Apple Accessibility APIs.

If you're new to apps, you need to use XcodeBuildMCP. It takes all the rough edges out of working with Codex or Claude Code and Xcode. Your agent can build and run your app, and even check the UI to see if it looks good via Apple Accessibility APIs.

Paul Solt

53,825 просмотров • 9 месяцев назад

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.

ComfyUI

185,508 просмотров • 1 месяц назад