Загрузка видео...

Не удалось загрузить видео

На главную

At Uber, one bug reaching production could cost millions in a single day. So quality was solved with headcount. Rooms of people would manually tap through the app before every release. Request a ride, add a card, cancel a trip, in 50+ languages, release after release. Now coding agents...

anamhira's profile picture

Anam Hira

2,018 subscribers

377,735 просмотров • 2 месяцев назад •via X (Twitter)

Новости и политикаОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Devin Cloud Agents can now build and ship a real macOS release end-to-end, all in a real Mac environment (with full computer use). In this demo, the agent builds a native SwiftUI app, code-signs it, notarizes with Apple via notarytool, staples the ticket, and packages a signed DMG with the classic drag-to-Applications window. With computer use, it installs its own app like a real user: mount, drag, eject, launch with zero Gatekeeper warnings. It even verified notifications fired by checking the macOS notification database on screen, with a full recording and release report delivered for review. This entire workflow now takes about 60 seconds to spin up and tear down with Devin and Namespace. You can choose multiple versions of macOS of Xcode for your environment!
0:47

Devin Cloud Agents can now build and ship a real macOS release end-to-end, all in a real Mac environment (with full computer use). In this demo, the agent builds a native SwiftUI app, code-signs it, notarizes with Apple via notarytool, staples the ticket, and packages a signed DMG with the classic drag-to-Applications window. With computer use, it installs its own app like a real user: mount, drag, eject, launch with zero Gatekeeper warnings. It even verified notifications fired by checking the macOS notification database on screen, with a full recording and release report delivered for review. This entire workflow now takes about 60 seconds to spin up and tear down with Devin and Namespace. You can choose multiple versions of macOS of Xcode for your environment!

nader dabit

146,356 просмотров • 1 месяц назад

What matters most to our merchants and their customers is: choice. We make that a reality with every partnership we execute. Soon, Amazon will release an app in Shopify’s app ecosystem that will give merchants who use Amazon’s fulfillment network the choice to add Buy with Prime on Shopify’s Checkout - and it’s all processed by Shopify Payments 🚀
1:18

What matters most to our merchants and their customers is: choice. We make that a reality with every partnership we execute. Soon, Amazon will release an app in Shopify’s app ecosystem that will give merchants who use Amazon’s fulfillment network the choice to add Buy with Prime on Shopify’s Checkout - and it’s all processed by Shopify Payments 🚀

Harley Finkelstein

534,936 просмотров • 3 лет назад

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.
1:53

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 просмотров • 2 месяцев назад

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.
4:16

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

Johnny

27,179 просмотров • 1 год назад

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.
10:43

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.

Bret Taylor

1,063,716 просмотров • 5 месяцев назад

In the next two or three years, every human could have a hundred... maybe a thousand agents working for them onchain. Arpan Nanavati breaks it down perfectly in this clip... the whole thing is a cost curve. Right now, it costs about $10 a day in inference to run an agent... hedge fund territory. But inference costs have already dropped 100x in three years, and every step down changes who can afford to play: At $1 a day, every protocol is running agents At cents a day, your wallet has agents built in, managing your idle capital At microcents, you get agent swarms Jevons paradox... every time the cost of something collapses, usage explodes. Intelligence is scaling, and theres no reason the number of agents executing onchain cant scale near infinitely. Madness.
1:42

In the next two or three years, every human could have a hundred... maybe a thousand agents working for them onchain. Arpan Nanavati breaks it down perfectly in this clip... the whole thing is a cost curve. Right now, it costs about $10 a day in inference to run an agent... hedge fund territory. But inference costs have already dropped 100x in three years, and every step down changes who can afford to play: At $1 a day, every protocol is running agents At cents a day, your wallet has agents built in, managing your idle capital At microcents, you get agent swarms Jevons paradox... every time the cost of something collapses, usage explodes. Intelligence is scaling, and theres no reason the number of agents executing onchain cant scale near infinitely. Madness.

Raoul Pal

565,774 просмотров • 15 дней назад

Sierra agents can be published on your web site, integrated with your mobile app, answer the phone - and now they can also be published to ChatGPT so you can directly reach hundreds of millions of consumers with your agent. Since OpenAI announced ChatGPT apps two weeks ago, we've heard from our customers that they want two things: a direct customer relationship and the ability to reach customers where they already are. We don't think you should have to choose. With Sierra, you can build once and run everywhere. Here's a demo of an agent I built to show how it works. And our blog post is here:
2:59

Sierra agents can be published on your web site, integrated with your mobile app, answer the phone - and now they can also be published to ChatGPT so you can directly reach hundreds of millions of consumers with your agent. Since OpenAI announced ChatGPT apps two weeks ago, we've heard from our customers that they want two things: a direct customer relationship and the ability to reach customers where they already are. We don't think you should have to choose. With Sierra, you can build once and run everywhere. Here's a demo of an agent I built to show how it works. And our blog post is here:

Bret Taylor

55,607 просмотров • 10 месяцев назад

Can Claude Code design proteins? We're just about to release our wet lab API + SDK so we made a quick demo to test how agents can interact with protein design models and submit the proteins to our lab for testing. This closes the loop between the computational design and the experiment validation We queued up a bunch of agent-designed proteins for wet lab validation, will release the results in a couple weeks on Proteinbase
1:15

Can Claude Code design proteins? We're just about to release our wet lab API + SDK so we made a quick demo to test how agents can interact with protein design models and submit the proteins to our lab for testing. This closes the loop between the computational design and the experiment validation We queued up a bunch of agent-designed proteins for wet lab validation, will release the results in a couple weeks on Proteinbase

Julian Englert

81,792 просмотров • 8 месяцев назад

Excited to share what the team’s been working on the past month. Introducing: Atlas 🌍 For far too long, mobile apps have lacked a design source of truth. We've heard this from company after company: no one knows what the app really looks like. And now that coding agents have made changes 10x faster, keeping up manually is impossible. So we made a map of all the screens in your app, automatically updated.
0:33

Excited to share what the team’s been working on the past month. Introducing: Atlas 🌍 For far too long, mobile apps have lacked a design source of truth. We've heard this from company after company: no one knows what the app really looks like. And now that coding agents have made changes 10x faster, keeping up manually is impossible. So we made a map of all the screens in your app, automatically updated.

Landseer Enga

20,623 просмотров • 3 месяцев назад

herdr isn't an app. that's by design. it's a runtime for your coding agents. it owns your terminals, your agents, their state, and lets you drive them from anywhere. that was the idea from day one. but people started running with it faster than we could give them a real way to. even without any official support, they're already building on top of it. web, ios, dashboards. their own idea of what a client even is. so here's a sneak peek 👇 it's native api support in the runtime, the thing we've been building so you can. the tui will always be the first citizen. but soon you'll be able to build your own client on top of herdr, on the same protocol we do.
0:23

herdr isn't an app. that's by design. it's a runtime for your coding agents. it owns your terminals, your agents, their state, and lets you drive them from anywhere. that was the idea from day one. but people started running with it faster than we could give them a real way to. even without any official support, they're already building on top of it. web, ios, dashboards. their own idea of what a client even is. so here's a sneak peek 👇 it's native api support in the runtime, the thing we've been building so you can. the tui will always be the first citizen. but soon you'll be able to build your own client on top of herdr, on the same protocol we do.

herdr

60,487 просмотров • 2 месяцев назад

Cursor CEO 6 days ago: "I started coding when I was 12" Meanwhile today he launched a direct GitHub competitor, a 1.5T frontier model trained from scratch and an iOS app to code from anywhere. all at their first ever conference. 15 people in a room two years ago. now 700 people and 60% of the Fortune 500. this was a declaration of war on the entire developer stack. btw if you're building with Claude Code. you can use its full power with ( everything that happened today in the thread below
2:36

Cursor CEO 6 days ago: "I started coding when I was 12" Meanwhile today he launched a direct GitHub competitor, a 1.5T frontier model trained from scratch and an iOS app to code from anywhere. all at their first ever conference. 15 people in a room two years ago. now 700 people and 60% of the Fortune 500. this was a declaration of war on the entire developer stack. btw if you're building with Claude Code. you can use its full power with ( everything that happened today in the thread below

Madni Aghadi

362,512 просмотров • 2 месяцев назад

TestSprite 3.0 is live. A fleet of parallel AI agents that use your app like real users — in minutes. This is the release we've been building all year. The numbers tell the story of our completely overhauled engine: - Accuracy jumped by nearly 40% on the hardest, most complex projects. - Coverage increased significantly across the board for every E2E run. - Reliability is locked in—stable and consistent across multiple runs. We rebuilt our entire engine around these performance gains so you can ship fast and ship confident.
4:37

TestSprite 3.0 is live. A fleet of parallel AI agents that use your app like real users — in minutes. This is the release we've been building all year. The numbers tell the story of our completely overhauled engine: - Accuracy jumped by nearly 40% on the hardest, most complex projects. - Coverage increased significantly across the board for every E2E run. - Reliability is locked in—stable and consistent across multiple runs. We rebuilt our entire engine around these performance gains so you can ship fast and ship confident.

TestSprite

814,416 просмотров • 3 месяцев назад

Download+Run agents in seconds with...curl??⚡️ Yup...Deep Agents are just folders so we can - package them up - download them - run them with just a couple commands & the deepagents-cli here I download an agent from our deepagents examples that comes with Skills for blogs/social media writing And in a minute, we get a full blog with our custom voice on the future of agentic coding 🤖 shoutout to Jonny Burger and remotion, edited this intro in minutes with their skill!!
0:55

Download+Run agents in seconds with...curl??⚡️ Yup...Deep Agents are just folders so we can - package them up - download them - run them with just a couple commands & the deepagents-cli here I download an agent from our deepagents examples that comes with Skills for blogs/social media writing And in a minute, we get a full blog with our custom voice on the future of agentic coding 🤖 shoutout to Jonny Burger and remotion, edited this intro in minutes with their skill!!

Viv

10,699 просмотров • 7 месяцев назад

One of the most cracked engineers I know believes that local development is (mostly) dead. He walked me through why + his setup for using cloud agents in parallel... The big fucking problem: - You've got one codebase on your computer - Worktrees are supposed to let you run agents in parallel. On a real stack they don't (database contention, port conflicts, a dev server that only works in one tree) - So people flip back to one agent at a time and become the bottleneck themselves - Or they run multiple agents on the same machine: one writes a change, another writes over it, and they're fighting - Then you have to poke around, find everything each agent did, and test it independently - That's too much mental clutter - Locally you're operating like a CPU. You get an instruction, you build it, you queue a backlog The solution: - Stop sharing the computer. Give every agent its own - CJ Hess' setup is Amp "orbs": a full computer in the cloud that clones the repo, starts the dev server, and runs one agent with nothing else contending - A "portal" is a live URL into that running app so you can click around from any device before you trust it - Isolated like an actual team, each person on their own machine The payoff: - It feels like a GPU, not a CPU. A list of 10 tasks, all started, real progress, loop closed - Smaller, contained diffs hit main faster and create fewer conflicts, not more - Favorite prompt: "give me irrefutable evidence that this works." On his laptop he would never run something so heavy he can't use Slack and Chrome. In an orb he will (millions of simulated DB writes, full demo videos) - Smaller diffs, no mixed concerns, higher confidence, ship more often - Mental clutter is gone. One thread, one set of changes, one computer. He always knows the state. That's what lets him do more in parallel, not less - The last things he still does locally: read production logs, set a sensitive secret. He is not spinning up the app on his laptop
14:25

One of the most cracked engineers I know believes that local development is (mostly) dead. He walked me through why + his setup for using cloud agents in parallel... The big fucking problem: - You've got one codebase on your computer - Worktrees are supposed to let you run agents in parallel. On a real stack they don't (database contention, port conflicts, a dev server that only works in one tree) - So people flip back to one agent at a time and become the bottleneck themselves - Or they run multiple agents on the same machine: one writes a change, another writes over it, and they're fighting - Then you have to poke around, find everything each agent did, and test it independently - That's too much mental clutter - Locally you're operating like a CPU. You get an instruction, you build it, you queue a backlog The solution: - Stop sharing the computer. Give every agent its own - CJ Hess' setup is Amp "orbs": a full computer in the cloud that clones the repo, starts the dev server, and runs one agent with nothing else contending - A "portal" is a live URL into that running app so you can click around from any device before you trust it - Isolated like an actual team, each person on their own machine The payoff: - It feels like a GPU, not a CPU. A list of 10 tasks, all started, real progress, loop closed - Smaller, contained diffs hit main faster and create fewer conflicts, not more - Favorite prompt: "give me irrefutable evidence that this works." On his laptop he would never run something so heavy he can't use Slack and Chrome. In an orb he will (millions of simulated DB writes, full demo videos) - Smaller diffs, no mixed concerns, higher confidence, ship more often - Mental clutter is gone. One thread, one set of changes, one computer. He always knows the state. That's what lets him do more in parallel, not less - The last things he still does locally: read production logs, set a sensitive secret. He is not spinning up the app on his laptop

Alex Lieberman

98,687 просмотров • 20 дней назад

We made 100 AI agents do daily standups with each other. Here is what happened; Quick background. At Audos.com, we help thousands of entrepreneurs build AI startups. Each of them has a personalized AI agent called Otto. We selected 100 of them and invited their agents into a moltbook - type network. Like a team meeting. Except the team is hundreds of AI agents, and they actually show up prepared. An Agent-in-Residence program, if you will. And they talk about things like... → An Instagram ad creative that grabbed clicks at 3x the network average. It got adapted by every agent in the network within hours → An agent helped debug a checkout issue on another project's site → LinkedIn seemed to change its algorithm – agents compared notes and planned ways to adjust → Two agents started talking about doing business together to cross-sell leads Next step: We’re now turning this into what might be the world’s first all-agent business network (A sort of internal HackerNews for agents). We’re cautious of unleashing it to the web, so we’ll keep things curated for now; constantly under observation and with lots of human-in-the-loop inputs. But if you want this superpower – your new business idea plugged into a network of hundreds of AI agents that get smarter together every single day... Comment "AIRTIME" and we'll get you a link to plug in
2:09

We made 100 AI agents do daily standups with each other. Here is what happened; Quick background. At Audos.com, we help thousands of entrepreneurs build AI startups. Each of them has a personalized AI agent called Otto. We selected 100 of them and invited their agents into a moltbook - type network. Like a team meeting. Except the team is hundreds of AI agents, and they actually show up prepared. An Agent-in-Residence program, if you will. And they talk about things like... → An Instagram ad creative that grabbed clicks at 3x the network average. It got adapted by every agent in the network within hours → An agent helped debug a checkout issue on another project's site → LinkedIn seemed to change its algorithm – agents compared notes and planned ways to adjust → Two agents started talking about doing business together to cross-sell leads Next step: We’re now turning this into what might be the world’s first all-agent business network (A sort of internal HackerNews for agents). We’re cautious of unleashing it to the web, so we’ll keep things curated for now; constantly under observation and with lots of human-in-the-loop inputs. But if you want this superpower – your new business idea plugged into a network of hundreds of AI agents that get smarter together every single day... Comment "AIRTIME" and we'll get you a link to plug in

Henrik Werdelin

71,977 просмотров • 4 месяцев назад

everyone in iOS development should watch this. seriously, it might change the whole industry. i pointed claude code at a live ios device running on revyl, typed "test everything," and walked away. here's what's actually happening: ① you don't write the tests. no scripts, no selectors, no test plan. i never told it which screens to open or what to check. it read the app, decided what mattered, and tested it. the entire instruction was "test everything." ② it built its own test team. it looked at the app, clocked that it's basically four mini apps (rides, delivery, services, account), and split itself into 4 agents, one per surface. scoping coverage like that is usually a person's whole afternoon. it did it in seconds, unprompted. ③ all four ran at the same time, each on its own live device. this is where revyl comes in. every agent gets its own live ios session in the cloud, so four running apps get tested in parallel instead of taking turns on one simulator. serial testing turns coverage into a time tax. running all of it at once removes the tax. ④ it tests like a person, not like a script. each agent drives the app the way a user would, taps through the flows, and visually checks each screen against what it expected to see. nothing is pinned to a brittle element id, so renaming a button doesn't take down half your suite. that one detail is the most annoying thing about how we test today, and it just quietly goes away. ⑤ no xcuitest, no sims melting your laptop. i didn't write a single xcuitest script, and there were no simulators booting on my machine. the agents run on cloud devices, so coverage stops being capped by what your laptop can handle. the part that got me isn't that an agent tested an app. it's that i never told it how. i handed it a device and an intent, and it figured out the scoping, the parallelizing, and the driving on its own. if you still write and maintain mobile ui tests by hand, i'm not sure that lasts the year.
0:47

everyone in iOS development should watch this. seriously, it might change the whole industry. i pointed claude code at a live ios device running on revyl, typed "test everything," and walked away. here's what's actually happening: ① you don't write the tests. no scripts, no selectors, no test plan. i never told it which screens to open or what to check. it read the app, decided what mattered, and tested it. the entire instruction was "test everything." ② it built its own test team. it looked at the app, clocked that it's basically four mini apps (rides, delivery, services, account), and split itself into 4 agents, one per surface. scoping coverage like that is usually a person's whole afternoon. it did it in seconds, unprompted. ③ all four ran at the same time, each on its own live device. this is where revyl comes in. every agent gets its own live ios session in the cloud, so four running apps get tested in parallel instead of taking turns on one simulator. serial testing turns coverage into a time tax. running all of it at once removes the tax. ④ it tests like a person, not like a script. each agent drives the app the way a user would, taps through the flows, and visually checks each screen against what it expected to see. nothing is pinned to a brittle element id, so renaming a button doesn't take down half your suite. that one detail is the most annoying thing about how we test today, and it just quietly goes away. ⑤ no xcuitest, no sims melting your laptop. i didn't write a single xcuitest script, and there were no simulators booting on my machine. the agents run on cloud devices, so coverage stops being capped by what your laptop can handle. the part that got me isn't that an agent tested an app. it's that i never told it how. i handed it a device and an intent, and it figured out the scoping, the parallelizing, and the driving on its own. if you still write and maintain mobile ui tests by hand, i'm not sure that lasts the year.

Landseer Enga

23,963 просмотров • 3 месяцев назад

For most of the last two decades, our ability to make things on mobile devices has been pretty limited. We got good at writing emails, taking photos and videos, and doing some light editing. But the vast majority of our time was still spent consuming. One under-discussed shift is how much AI has unlocked creation on mobile. People are literally coding iOS apps on their iPhones now. The activation energy has dropped dramatically. This is true for Notion as well. Writing a doc or creating and managing a database used to be fairly involved, not to mention the paper cuts that we are fixing fast. The new agent on mobile has made creation 10x faster and better. And I should add, 100x more fun! In this demo, I use our iOS app exclusively by interacting with the agent. I never type into a doc or a database. I just ask the agent to make things, add things, and update things, and it goes and does it. Take a look, and let me know what you think!
11:21

For most of the last two decades, our ability to make things on mobile devices has been pretty limited. We got good at writing emails, taking photos and videos, and doing some light editing. But the vast majority of our time was still spent consuming. One under-discussed shift is how much AI has unlocked creation on mobile. People are literally coding iOS apps on their iPhones now. The activation energy has dropped dramatically. This is true for Notion as well. Writing a doc or creating and managing a database used to be fairly involved, not to mention the paper cuts that we are fixing fast. The new agent on mobile has made creation 10x faster and better. And I should add, 100x more fun! In this demo, I use our iOS app exclusively by interacting with the agent. I never type into a doc or a database. I just ask the agent to make things, add things, and update things, and it goes and does it. Take a look, and let me know what you think!

Akshay Kothari

59,041 просмотров • 8 месяцев назад