Loading video...

Video Failed to Load

Go Home

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 views • 1 month ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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 views • 9 months ago

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 views • 23 days ago

"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 views • 5 months ago

“ 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 views • 1 year ago

$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

157,043 views • 3 months ago

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 views • 5 months ago

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 views • 3 years ago

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 views • 1 year ago

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

19,911 views • 2 months ago

I didn't really plan to address this video too much, but after seeing that even ministers shared it, I realized the situation is more serious than I thought. Is the game rigged from the start?
2:19

I didn't really plan to address this video too much, but after seeing that even ministers shared it, I realized the situation is more serious than I thought. Is the game rigged from the start?

GAZAWOOD - the PALLYWOOD saga

417,760 views • 1 year ago

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

542,026 views • 1 month ago

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

384,792 views • 3 years ago

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 views • 8 months ago

Moore "But in the past 10 years as a political leader, as a cabinet minister, as a parliamentary secretary to the justice minister, as a minister of public safety, he didn't do any of these things." "He had the full opportunity to do this in a majority Liberal government." "He had the full opportunity through three successive parliaments." "And now he says if you give me a fourth parliament, give me a fourth mandate and I really will do it this time. I mean, it's. Come on." "It fails on the sincerity test and the credibility test to say that I didn't do it the first time, didn't do it the second time, didn't do it the third time, but the fourth time I really promise I'll get serious about this now." James Moore
1:51

Moore "But in the past 10 years as a political leader, as a cabinet minister, as a parliamentary secretary to the justice minister, as a minister of public safety, he didn't do any of these things." "He had the full opportunity to do this in a majority Liberal government." "He had the full opportunity through three successive parliaments." "And now he says if you give me a fourth parliament, give me a fourth mandate and I really will do it this time. I mean, it's. Come on." "It fails on the sincerity test and the credibility test to say that I didn't do it the first time, didn't do it the second time, didn't do it the third time, but the fourth time I really promise I'll get serious about this now." James Moore

cbcwatcher

23,530 views • 1 year ago

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 views • 2 years ago

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

86,843 views • 3 months ago

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 views • 8 months ago

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

416,314 views • 3 months ago