Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

claude code now writes its own test plan and runs it on a live iphone. i didn't write the tests. i didn't run the tests. i didn't even open the app. it caught the bug too.

LandseerEnga's profile picture

Landseer Enga

2,389 subscribers

30,714 görüntüleme • 2 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Cosine CLI is your AI pair programmer. It writes code, fixes bugs, runs tests – all from the command line. Live now on our website + Product Hunt.
3:33

Cosine CLI is your AI pair programmer. It writes code, fixes bugs, runs tests – all from the command line. Live now on our website + Product Hunt.

Cosine

324,345 görüntüleme • 10 ay önce

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 görüntüleme • 1 ay önce

"I just didn't make the play. I own it, I own it all." Jalen Hurts on not converting on the final fourth down vs. the 49ers.
0:27

"I just didn't make the play. I own it, I own it all." Jalen Hurts on not converting on the final fourth down vs. the 49ers.

NFL on ESPN

412,059 görüntüleme • 6 ay önce

today is the last day fable 5 is in the claude code plan, so i gave it something i've always wanted to build: polytopia rebuilt in pure C, RL agents trained from scratch, playable in the browser completely vibecoded. i didn't write a line. even the game assets were ai-generated using a pipeline fable created. 🧵 below
0:32

today is the last day fable 5 is in the claude code plan, so i gave it something i've always wanted to build: polytopia rebuilt in pure C, RL agents trained from scratch, playable in the browser completely vibecoded. i didn't write a line. even the game assets were ai-generated using a pipeline fable created. 🧵 below

Binh Pham

45,753 görüntüleme • 9 gün önce

“ I even hit my mouth with the mic while dancing but i didn't even feel it. I performed with my lip bleeding and didn't even feel the pain. It was a moment that I want to experience again.” oh Hoshi 😭
0:36

“ I even hit my mouth with the mic while dancing but i didn't even feel it. I performed with my lip bleeding and didn't even feel the pain. It was a moment that I want to experience again.” oh Hoshi 😭

Sumaiyah

151,899 görüntüleme • 1 yıl önce

$2,300 profit from OpenClaw running on its own. I didn't touch it. Didn't monitor it. Just let it run. Kinda scary how autonomous this is now. Replicate this setup in 7 days using Claude + laptop + 1 hour daily. Target: $5,000/month passive. I created the full guide, step-by-step. Free for the next 24 hours. Get it now: 1. Comment "OpenClaw" below 2. Like and Retweet 3. Follow Himanshu Kumar to receive the DM
8:14

$2,300 profit from OpenClaw running on its own. I didn't touch it. Didn't monitor it. Just let it run. Kinda scary how autonomous this is now. Replicate this setup in 7 days using Claude + laptop + 1 hour daily. Target: $5,000/month passive. I created the full guide, step-by-step. Free for the next 24 hours. Get it now: 1. Comment "OpenClaw" below 2. Like and Retweet 3. Follow Himanshu Kumar to receive the DM

Himanshu Kumar

157,515 görüntüleme • 4 ay önce

BREAKING: Replit just launched mobile apps. Now you can build in Replit ⠕ and submit straight to the App Store for review. Describe your app → build it on Replit → test on your phone → publish to the App Store. I built a unicorn pet app for my niece: - Worked with Replit Agent to build it out - Scanned a QR code to download and test on my phone - One click to send to App Store Connect for review - A couple submissions later, it's live in the App Store! 🙌 I didn't write a single line of code! Just described what I wanted to Agent. Amazing! 😅 Go build something!! 👇
1:42

BREAKING: Replit just launched mobile apps. Now you can build in Replit ⠕ and submit straight to the App Store for review. Describe your app → build it on Replit → test on your phone → publish to the App Store. I built a unicorn pet app for my niece: - Worked with Replit Agent to build it out - Scanned a QR code to download and test on my phone - One click to send to App Store Connect for review - A couple submissions later, it's live in the App Store! 🙌 I didn't write a single line of code! Just described what I wanted to Agent. Amazing! 😅 Go build something!! 👇

Manny Bernabe

30,925 görüntüleme • 6 ay önce

Pair programming with ChatGPT with access to my file system that can: - edit files on its own - run ANY bash command - write, run, debug Python & JS code - create & run Git commands I didn't even know has been the most exhilarating experience since I started coding 11 years ago
0:30

Pair programming with ChatGPT with access to my file system that can: - edit files on its own - run ANY bash command - write, run, debug Python & JS code - create & run Git commands I didn't even know has been the most exhilarating experience since I started coding 11 years ago

YK aka CS Dojo 📺🐦

234,664 görüntüleme • 3 yıl önce

Kim Caldwell on the timeout after Ohio State's 16-0 run. "I didn't have to say anything and that's when our team is the best. I didn't even need to be here today. They had it handled." #LadyVols
0:21

Kim Caldwell on the timeout after Ohio State's 16-0 run. "I didn't have to say anything and that's when our team is the best. I didn't even need to be here today. They had it handled." #LadyVols

Sam Rothman

421,601 görüntüleme • 1 yıl önce

This is Beervana, an iOS app I built entirely with HTML and a YAML file. It's powered by Ruby Native and available in the App Store today. I didn't write a single line of Swift. Or even open Xcode.
0:41

This is Beervana, an iOS app I built entirely with HTML and a YAML file. It's powered by Ruby Native and available in the App Store today. I didn't write a single line of Swift. Or even open Xcode.

Joe Masilotti

19,970 görüntüleme • 3 ay önce

My brother (Daniel Cohen Hillel) and I worked on a fun project tonight, inspired by Yohei : Coding Agent that follows the Test Driven Development (TDD) methodology! You write the tests - and the agent runs in a loop until it creates the feature properly! 1/6 #buildinpublic
0:49

My brother (Daniel Cohen Hillel) and I worked on a fun project tonight, inspired by Yohei : Coding Agent that follows the Test Driven Development (TDD) methodology! You write the tests - and the agent runs in a loop until it creates the feature properly! 1/6 #buildinpublic

Adam

384,813 görüntüleme • 3 yıl önce

Spencer Pratt: "I didn't run for it to be a political party. I didn't run to be a politician." "I'm the citizen. I'm the angry taxpayer... The only people who don't love me are communists and socialists and I don't want them to love me."
0:30

Spencer Pratt: "I didn't run for it to be a political party. I didn't run to be a politician." "I'm the citizen. I'm the angry taxpayer... The only people who don't love me are communists and socialists and I don't want them to love me."

Defiant L’s

542,168 görüntüleme • 2 ay önce

It finally happened. I was so excited I didn't even see the alpha in the background.
0:29

It finally happened. I was so excited I didn't even see the alpha in the background.

Mithzan

334,094 görüntüleme • 9 ay önce

What is Francisco Lindor feeling right now? "A lot. I failed at the job, failed the mission. It was something that, it was on us, on me and on the players to get it done and we didn't execute. We didn't get it done."
0:45

What is Francisco Lindor feeling right now? "A lot. I failed at the job, failed the mission. It was something that, it was on us, on me and on the players to get it done and we didn't execute. We didn't get it done."

SNY

285,423 görüntüleme • 9 ay önce

Agents can one shot mobile apps, but testing is still the bottleneck. So we built a CLI that gives Claude Code the one thing it was missing - eyes and hands The best part? t's fully vision-based: - No scripts, no selectors, no element IDs - It interacts with the app exactly like a human would Claude now writes code → tests it on the app → sees what broke → fixes it Spawn a cloud agent, go to sleep, and wake up knowing it actually worked.
0:38

Agents can one shot mobile apps, but testing is still the bottleneck. So we built a CLI that gives Claude Code the one thing it was missing - eyes and hands The best part? t's fully vision-based: - No scripts, no selectors, no element IDs - It interacts with the app exactly like a human would Claude now writes code → tests it on the app → sees what broke → fixes it Spawn a cloud agent, go to sleep, and wake up knowing it actually worked.

Landseer Enga

86,891 görüntüleme • 4 ay önce

The first open-source implementation of the paper that will change automatic test generation is now available! In February, Meta published a paper introducing a tool to automatically increase test coverage, guaranteeing improvements over an existing code base. This is a big deal, but Meta didn't release the code. Fortunately, we now have Cover-Agent, an open-source tool you can install that implements Meta's paper to generate unit tests automatically: I recorded a quick video showing Cover-Agent in action. There are two things I want to mention: 1. Automatically generating unit tests is not new, but doing it right is difficult. If you ask ChatGPT to do it, you'll get duplicate, non-working, and meaningless tests that don't improve your code. Meta's solution only generates unique tests that run and increase code coverage. 2. People who write tests before writing the code (TDD) will find this less helpful. That's okay. Not everyone does TDD, but we all need to improve test coverage. There are many good and bad applications of AI, but this is one I'm looking forward to make part of my life.
1:05

The first open-source implementation of the paper that will change automatic test generation is now available! In February, Meta published a paper introducing a tool to automatically increase test coverage, guaranteeing improvements over an existing code base. This is a big deal, but Meta didn't release the code. Fortunately, we now have Cover-Agent, an open-source tool you can install that implements Meta's paper to generate unit tests automatically: I recorded a quick video showing Cover-Agent in action. There are two things I want to mention: 1. Automatically generating unit tests is not new, but doing it right is difficult. If you ask ChatGPT to do it, you'll get duplicate, non-working, and meaningless tests that don't improve your code. Meta's solution only generates unique tests that run and increase code coverage. 2. People who write tests before writing the code (TDD) will find this less helpful. That's okay. Not everyone does TDD, but we all need to improve test coverage. There are many good and bad applications of AI, but this is one I'm looking forward to make part of my life.

Santiago

774,488 görüntüleme • 2 yıl önce

You can now use Claude Code and GitHub CLI directly inside Perplexity Computer. We gave it an open issue on Openclaw. Computer: → Forked the repo → Wrote a plan to fix the bug → Opened Claude Code and implemented it → Submitted a PR via GitHub CLI
0:28

You can now use Claude Code and GitHub CLI directly inside Perplexity Computer. We gave it an open issue on Openclaw. Computer: → Forked the repo → Wrote a plan to fix the bug → Opened Claude Code and implemented it → Submitted a PR via GitHub CLI

Computer

416,607 görüntüleme • 4 ay önce