Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Delete all your E2E tests, seriously Okay, not the coverage, the code I’ve written Playwright tests, they’re great Maintaining hundreds of browser scripts while the UI keeps changing is not so much Honestly, AI feels more naturally suited to this than half the coding use cases we keep forcing...

DanielGlejzner's profile picture

Daniel Glejzner

7,387 subscribers

90,340 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

23 Kommentare

Profilbild von Éverton Toffanetto
Éverton Toffanettovor 1 Monat

Tests are written as scripts because they need to be deterministic. Using AI introduces a variable you don’t fully control. I see them as complementary approaches, not as one replacing the other.

Profilbild von Daniel Glejzner
Daniel Glejznervor 1 Monat

The control part is the part that you need to weight, since full control comes with a cost as well. If you don't want to pay by hour for developers to maintain tests but want to have a regression testing path. It's an easy way to get it done without even thinking much about it :)

Profilbild von Kevin Möchel
Kevin Möchelvor 1 Monat

Have the AI write playwright tests Run them on a schedule If failed, have an agent fix them Run tests for free instead of a paid sub

Profilbild von Daniel Glejzner
Daniel Glejznervor 1 Monat

You could do that but it's still not free, takes your time, validation and you have to physically be responsible for them It's a decision between your own time or just having it handled by a third party where all you maintain are written user stories

Profilbild von AI Apps API
AI Apps APIvor 1 Monat

The maintenance cost is real and it comes from the same place every time, selectors encode layout instead of intent. A test that says click the button labeled Save survives a redesign, one pinned to a generated class name does not. Agents help most when the step is described that way, and the flaky part left over is usually waiting, asserting on state that has actually settled rather than a fixed timeout.

Profilbild von Paweł Kubiak 🅰️
Paweł Kubiak 🅰️vor 1 Monat

Ok, but what about costs? I assume that TesterArmy agent can interact with website by sending screenshot/html/a11y tree to LLM to identify crucial elements to interact with. If so, then it is expensive in terms of costs. In that case I would keep e2e tests.

Profilbild von Daniel Glejzner
Daniel Glejznervor 1 Monat

From what I understand from docs it's mostly based on visuals and it charges you per run with a monthly subscription With regular E2E it all depends how much maintenance you have around them. If you have an app that doesn't change that much, you don't feel the pain. In fast paced env tools like TesterArmy remove the burden of updating tests and adding new is super simple Gonna dig around how actual internals work other than screenshots :)

Profilbild von Daniel Glejzner
Daniel Glejznervor 1 Monat

I actually found out they’re not relying on vision by default. They use accessibility APIs first (DOM on the web, native APIs on mobile), and only fall back to vision when needed since it’s much slower and more expensive However you are paying per run so they need to care about the tokens not you :)

Profilbild von AI Alpha By Mario
AI Alpha By Mariovor 1 Monat

The maintenance burden is the real killer — AI handling intent while the UI changes underneath feels like the right split

Profilbild von Daniel Glejzner
Daniel Glejznervor 1 Monat

So far I had a really good and consistent results :)

Profilbild von AI Mastery Guide
AI Mastery Guidevor 1 Monat

Plain English tests instead of babysitting selectors sounds so much easier.

Profilbild von Daniel Glejzner
Daniel Glejznervor 1 Monat

Indeed! it's much more convenient not to think about all the selectors and code around them when you don't have to :)

Profilbild von AI Mastery Guide
AI Mastery Guidevor 1 Monat

Less brittle scripts, more time actually shipping features.

Profilbild von Pavan K Jadda
Pavan K Jaddavor 1 Monat

Looks interesting

Profilbild von Daniel Glejzner
Daniel Glejznervor 1 Monat

Give it a try :)

Profilbild von Shahar Nechmad
Shahar Nechmadvor 1 Monat

Agree. Maintaining selectors is probably one of the worst parts of E2E tests. These days, agents are smart enough, and computer use has become so much better. Check out also what Cloudflare is doing. They released a lot of infra in the past two weeks, to build this at scale.

Profilbild von incpo
incpovor 1 Monat

at leats playwright is free

Profilbild von Daniel Glejzner
Daniel Glejznervor 1 Monat

yes it is, but your time is not :) Gotta decide what is worth more

Profilbild von Vivek Nayyar
Vivek Nayyarvor 1 Monat

The issue is the latency and cost plus unpredictability. Will the model always find the right button to click and test 😅

Profilbild von Daniel Glejzner
Daniel Glejznervor 1 Monat

Give it a try :) it comes with a free trial, cost is per run - pretty convenient as well. In my experience it does a pretty damn good job at clicking the right things. Not sure about the latency? What's the issue there?

Profilbild von Vivek Nayyar
Vivek Nayyarvor 1 Monat

Take screenshot, call llm to find the right element and then simulate click - this would have higher latency than a data test id click

Profilbild von fudes
fudesvor 1 Monat

Quoting a VC as an authority on building is like quoting a food critic as an authority on cooking.

Profilbild von Mitchell Agoma
Mitchell Agomavor 1 Monat

Deleting brittle scripts while preserving meaningful coverage is the right distinction. AI can reduce maintenance, but teams still need deterministic checks and ownership of release risk. Related QA view:

Ähnliche Videos

Have you seen this browser feature in GitHub Copilot app? I just stumbled across it - didn't realize it could do this! 🌟 1️⃣ Had it generate some code based on a plan 2️⃣ Once done, it automatically launched the front-end server and backend APIs 3️⃣ It launched the browser canvas in the app 4️⃣ It then loaded pages, searched for products, and clicked through the app all the way to the checkout screen to verify the features were implemented correctly. What!?🤯 First time I've seen that. Normally I'd have to write Playwright tests but it verified it's work automatically. 🚀
4:36

Have you seen this browser feature in GitHub Copilot app? I just stumbled across it - didn't realize it could do this! 🌟 1️⃣ Had it generate some code based on a plan 2️⃣ Once done, it automatically launched the front-end server and backend APIs 3️⃣ It launched the browser canvas in the app 4️⃣ It then loaded pages, searched for products, and clicked through the app all the way to the checkout screen to verify the features were implemented correctly. What!?🤯 First time I've seen that. Normally I'd have to write Playwright tests but it verified it's work automatically. 🚀

Dan Wahlin

20,673 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 4 Monaten

You don't need to know how to code to turn a messy spreadsheet into something you can actually use. I had an Excel file of 20 brands I want to pitch. I dropped it in a folder, opened Qoder, and typed one sentence: turn this into a dashboard with search. Then I watched. It read the file, made a plan, wrote the code, opened the page in the browser, and tested the search on its own. I added a /goal so it knew when it was done: every brand shows, search works. The model: Qwen3.8-Flash, free through September 30. Zero Credits for this whole run. Want to try it? Enter my code BPU7C6 at first, then download Qoder and sign in. You will get 600 Credits: 300 from the trial and 300 from my code.
1:04

You don't need to know how to code to turn a messy spreadsheet into something you can actually use. I had an Excel file of 20 brands I want to pitch. I dropped it in a folder, opened Qoder, and typed one sentence: turn this into a dashboard with search. Then I watched. It read the file, made a plan, wrote the code, opened the page in the browser, and tested the search on its own. I added a /goal so it knew when it was done: every brand shows, search works. The model: Qwen3.8-Flash, free through September 30. Zero Credits for this whole run. Want to try it? Enter my code BPU7C6 at first, then download Qoder and sign in. You will get 600 Credits: 300 from the trial and 300 from my code.

Jay

143,303 Aufrufe • vor 5 Tagen

To me, microduck looks like a droid. So I made it sound like one Microduck is open source and hackable. That means you can program it to do whatever you want! I trained a 1.3m parameter LLM to output droid like responses. It is running in the browser The model has learned to respond with an emotion, alongside English like Happy, Excited, Sad Then the emotion is fed into a Rust based synthesizer to generate R2D2 like sounds that are aligned with the emotion --- completely procedurally, no wav files, no copyright violation You can chat with it. You can also customize it, give it a name and set your own colors! All set in a spaceship hangar backdrop with other friendly ducks---simulated with realistic physics and microduck's actual walking and skating policies! All in the browser, with WASM!!! I can put literally the SAME code in the browser, and then compile it into an ARM binary and put it in the actual robot in real life 🤯 If you like this and want to see more of it, please like and share so that my boss puts me in the priority list for the first microduck batch 😎 All open source of course! Microquack! 🦆 Hugging Face Space:
0:58

To me, microduck looks like a droid. So I made it sound like one Microduck is open source and hackable. That means you can program it to do whatever you want! I trained a 1.3m parameter LLM to output droid like responses. It is running in the browser The model has learned to respond with an emotion, alongside English like Happy, Excited, Sad Then the emotion is fed into a Rust based synthesizer to generate R2D2 like sounds that are aligned with the emotion --- completely procedurally, no wav files, no copyright violation You can chat with it. You can also customize it, give it a name and set your own colors! All set in a spaceship hangar backdrop with other friendly ducks---simulated with realistic physics and microduck's actual walking and skating policies! All in the browser, with WASM!!! I can put literally the SAME code in the browser, and then compile it into an ARM binary and put it in the actual robot in real life 🤯 If you like this and want to see more of it, please like and share so that my boss puts me in the priority list for the first microduck batch 😎 All open source of course! Microquack! 🦆 Hugging Face Space:

Onur Solmaz

33,500 Aufrufe • vor 1 Monat

AIDesigner is officially live! I think we can all agree that vibe coded apps look horrible, so I built an AI UI designer that creates actually beautiful UI in seconds. • Stunning designs from the simplest of prompts. • Design, edit, iterate all on a single canvas. • Copy styles from any URL. • Publish in a single click (subdomain or custom). • Designs for both web and mobile. • Export to code and image. Great UI design doesn't have to be difficult. Components, mobile apps, websites, AIDesigner does it all. Try it for free:
1:31

AIDesigner is officially live! I think we can all agree that vibe coded apps look horrible, so I built an AI UI designer that creates actually beautiful UI in seconds. • Stunning designs from the simplest of prompts. • Design, edit, iterate all on a single canvas. • Copy styles from any URL. • Publish in a single click (subdomain or custom). • Designs for both web and mobile. • Export to code and image. Great UI design doesn't have to be difficult. Components, mobile apps, websites, AIDesigner does it all. Try it for free:

Wiz

17,068 Aufrufe • vor 8 Monaten

Zuckerberg says Meta's Llama race changes in the next 12-18 months: most of the code will be written by AI - not autocomplete, but agents that run tests and improve the model loop. "We're not trying to build a general developer tool. We are trying to build a coding agent and an AI research agent that basically advances Llama research specifically." "Sometime in the next 12 to 18 months, we'll reach the point where most of the code that's going towards these efforts is written by AI." "And I don't mean autocomplete." "I'm talking more like you give it a goal, it can run tests, it can improve things, it can find issues." "It writes higher quality code than the average very good person on the team already." The hidden bottleneck is not chat UX. It is closing the loop between AI research, code, tests, and self-improvement inside the lab.
1:00

Zuckerberg says Meta's Llama race changes in the next 12-18 months: most of the code will be written by AI - not autocomplete, but agents that run tests and improve the model loop. "We're not trying to build a general developer tool. We are trying to build a coding agent and an AI research agent that basically advances Llama research specifically." "Sometime in the next 12 to 18 months, we'll reach the point where most of the code that's going towards these efforts is written by AI." "And I don't mean autocomplete." "I'm talking more like you give it a goal, it can run tests, it can improve things, it can find issues." "It writes higher quality code than the average very good person on the team already." The hidden bottleneck is not chat UX. It is closing the loop between AI research, code, tests, and self-improvement inside the lab.

Karl Mehta

36,347 Aufrufe • vor 3 Monaten

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base
1:47

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

125,326 Aufrufe • vor 9 Monaten

I made the worlds best Clipboard for your AI Agents Its called Bluey and its a dumb pointer which you can use to give 10x better context to your agent And you can point at your screen, talk to it, and it will generate a really good annotated screenshot which you can now give to your AI Agent You can use it while designing your website You can use it while explaining something on your screen. And it understands you and you can be really vague about things like "move this" , modify the color "here" and it will understand what you are pointing at. Im loving using it and I built it for myself as I was tired of clicking screenshots all the time and attaching it to my codex or claude code sessions Now I can just point, speak or type and drag and drop it anywhere I am giving free access to it in the comments and I would love for you to try it out. Join the discord and I am sharing the download link there. By the way everything stays 100 percent local. No screenshots are shared anywhere!
2:59

I made the worlds best Clipboard for your AI Agents Its called Bluey and its a dumb pointer which you can use to give 10x better context to your agent And you can point at your screen, talk to it, and it will generate a really good annotated screenshot which you can now give to your AI Agent You can use it while designing your website You can use it while explaining something on your screen. And it understands you and you can be really vague about things like "move this" , modify the color "here" and it will understand what you are pointing at. Im loving using it and I built it for myself as I was tired of clicking screenshots all the time and attaching it to my codex or claude code sessions Now I can just point, speak or type and drag and drop it anywhere I am giving free access to it in the comments and I would love for you to try it out. Join the discord and I am sharing the download link there. By the way everything stays 100 percent local. No screenshots are shared anywhere!

Milind S

12,085 Aufrufe • vor 3 Monaten

We made an MCP for your phone. Your laptop is just half of your life, and the other half is in your phone. Now your agent gets the mobile screen too. No connectors, no complex setup, it has access to everything that lives on your phone, all the logged-in apps, your notes, your calls, you name it. It sees the screen, taps it, types on it, from Claude Code, Codex, or any MCP client. Live now at $20 in credits, $20 more for the first 100 who connect a phone and run a task. Comment "discord" if you want the invite to the builder Discord, I'll DM it to you.
2:25

We made an MCP for your phone. Your laptop is just half of your life, and the other half is in your phone. Now your agent gets the mobile screen too. No connectors, no complex setup, it has access to everything that lives on your phone, all the logged-in apps, your notes, your calls, you name it. It sees the screen, taps it, types on it, from Claude Code, Codex, or any MCP client. Live now at $20 in credits, $20 more for the first 100 who connect a phone and run a task. Comment "discord" if you want the invite to the builder Discord, I'll DM it to you.

Div Garg

43,993 Aufrufe • vor 1 Monat

Head of Claude Code Boris Cherny at Anthropic's annual developer conference in San Francisco on how his life changed in the last 6 months with AI writing all the code. "About six months ago what happened is all the code that I used to have written by hand now Claude writes. And I just prompt Claude. So I talk to Claude and I'm like, hey, let's build this feature. It builds a feature and it tests it. And then it shows me. And I'm like, yeah, that's good. Or no, wait, make this change. And then it makes the change. " --- From 'CNBC Television' YT channel (link in comment)
0:42

Head of Claude Code Boris Cherny at Anthropic's annual developer conference in San Francisco on how his life changed in the last 6 months with AI writing all the code. "About six months ago what happened is all the code that I used to have written by hand now Claude writes. And I just prompt Claude. So I talk to Claude and I'm like, hey, let's build this feature. It builds a feature and it tests it. And then it shows me. And I'm like, yeah, that's good. Or no, wait, make this change. And then it makes the change. " --- From 'CNBC Television' YT channel (link in comment)

Rohan Paul

99,075 Aufrufe • vor 3 Monaten

Thanks to Qnoox I discovered this: Dr. Sbaitso from 1992 (33 years ago!) One of the first AI chat apps, I guess you could call it a highly primitive LLM, running on MS-DOS The cool thing is it already had speech synthesis so it could speak back via TTS! And when I was talking to it, within a few questions it was already asking for more compute, it wanted to become ChatGPT :D Installed it on now, you have to exit to DOS first, then CD SBAITSO, and then run SBAITSO2.BAT
1:23

Thanks to Qnoox I discovered this: Dr. Sbaitso from 1992 (33 years ago!) One of the first AI chat apps, I guess you could call it a highly primitive LLM, running on MS-DOS The cool thing is it already had speech synthesis so it could speak back via TTS! And when I was talking to it, within a few questions it was already asking for more compute, it wanted to become ChatGPT :D Installed it on now, you have to exit to DOS first, then CD SBAITSO, and then run SBAITSO2.BAT

@levelsio

259,439 Aufrufe • vor 11 Monaten

I asked Astra to create a Catan game in three.js and it came out incredibly well. I played it, and the animations make it so much fun. The instructions and info cards make the game easy to learn. It even has AI players and trading. Astra used another game I had started building as a reference. The more games I build, the more skills and assets I have for the next one. It can remix the UI, 3D models, pages, and sounds instead of rebuilding everything. Now I want to see how many other board games I can make from this foundation.
1:26

I asked Astra to create a Catan game in three.js and it came out incredibly well. I played it, and the animations make it so much fun. The instructions and info cards make the game easy to learn. It even has AI players and trading. Astra used another game I had started building as a reference. The more games I build, the more skills and assets I have for the next one. It can remix the UI, 3D models, pages, and sounds instead of rebuilding everything. Now I want to see how many other board games I can make from this foundation.

Meng To

577,286 Aufrufe • vor 22 Tagen

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at
0:35

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

Binh

122,482 Aufrufe • vor 3 Monaten

Imagine a computer where you don’t need to learn 10 apps to get work done. You just tell it what you want, and it adapts to how you work. I tested Happycapy with a real use case and created an image and a video. No coding, no complex software. Do this: - Build automations that run on schedule - Deploy agent teams that work for you AI molds how you work, not the other way around. If you can use a computer, you can make anything happen. Start your first Automation and Agent teams today.
0:24

Imagine a computer where you don’t need to learn 10 apps to get work done. You just tell it what you want, and it adapts to how you work. I tested Happycapy with a real use case and created an image and a video. No coding, no complex software. Do this: - Build automations that run on schedule - Deploy agent teams that work for you AI molds how you work, not the other way around. If you can use a computer, you can make anything happen. Start your first Automation and Agent teams today.

Aaliya

17,042 Aufrufe • vor 7 Monaten

I was the first Korean in the world to take a ride in a Tesla Cybercab, and I’m incredibly proud of that. 🇰🇷 You can probably tell from these raw, unedited videos just how excited I was getting into it for the very first time. No steering wheel. No pedals. No driver. Just me getting into a Cybercab and trusting it to take me where I needed to go. Even now, it still feels surreal that this is actually live and operating in the real world. I’ve followed Tesla and believed in this future for 10+ years, so getting to experience it firsthand, being one of the select few to be invited to the launch event, and represent Korea while doing it… is something I’ll never forget. These are the raw moments from my very first ride. You can see it from my reactions… I was like a kid experiencing the future for the first time.
9:12

I was the first Korean in the world to take a ride in a Tesla Cybercab, and I’m incredibly proud of that. 🇰🇷 You can probably tell from these raw, unedited videos just how excited I was getting into it for the very first time. No steering wheel. No pedals. No driver. Just me getting into a Cybercab and trusting it to take me where I needed to go. Even now, it still feels surreal that this is actually live and operating in the real world. I’ve followed Tesla and believed in this future for 10+ years, so getting to experience it firsthand, being one of the select few to be invited to the launch event, and represent Korea while doing it… is something I’ll never forget. These are the raw moments from my very first ride. You can see it from my reactions… I was like a kid experiencing the future for the first time.

Teslaconomics

15,893 Aufrufe • vor 15 Tagen

I wanted to see how far you can take the idea of “just describe a game.” So I gave Gear Zero a game concept in plain English and watched it go from an idea to a playable game in the browser. No game engine. No coding. No project files. No setup. Gear’s AI handles the planning, code, visuals, and level building and the first version can come together in around 20 minutes. But that’s not even the part I find most interesting. You can keep talking to it, ask for changes, refine the gameplay, and keep building on the same game instead of starting over every time. And because it’s designed for collaboration, other people can join the conversation and help shape the game too. That makes Gear Zero feel less like a one-click AI game generator and more like an AI-powered game-building workspace. If you’ve ever had a game idea but never opened a game engine, this is worth trying: Gear Zero
0:28

I wanted to see how far you can take the idea of “just describe a game.” So I gave Gear Zero a game concept in plain English and watched it go from an idea to a playable game in the browser. No game engine. No coding. No project files. No setup. Gear’s AI handles the planning, code, visuals, and level building and the first version can come together in around 20 minutes. But that’s not even the part I find most interesting. You can keep talking to it, ask for changes, refine the gameplay, and keep building on the same game instead of starting over every time. And because it’s designed for collaboration, other people can join the conversation and help shape the game too. That makes Gear Zero feel less like a one-click AI game generator and more like an AI-powered game-building workspace. If you’ve ever had a game idea but never opened a game engine, this is worth trying: Gear Zero

Md Riyazuddin

43,480 Aufrufe • vor 1 Monat

Proudest accomplishment of 2023, I’ll go first. In the world of ultra running- this is not all that special. But in my world it was the full circle of the journey from boy to man. It’s the kind of thing that even as you commit to doing it, even as I laced up my shoes I didn’t know if I was ready. It just seemed so massive and daunting. When I first took up running I was a skinny kid with stick legs that couldn’t run for more than half a mile before I had to stop and walk. But I was so damn inspired to change my life. You can do pretty much anything if you’re too stubborn to stop. 2023 was the biggest year of my life so far in a lot of ways. But these 33 hours will be some of the best of my life til the day I die. No test. No testimony baby. Bring on 2024 🎉🎉🎉
3:57

Proudest accomplishment of 2023, I’ll go first. In the world of ultra running- this is not all that special. But in my world it was the full circle of the journey from boy to man. It’s the kind of thing that even as you commit to doing it, even as I laced up my shoes I didn’t know if I was ready. It just seemed so massive and daunting. When I first took up running I was a skinny kid with stick legs that couldn’t run for more than half a mile before I had to stop and walk. But I was so damn inspired to change my life. You can do pretty much anything if you’re too stubborn to stop. 2023 was the biggest year of my life so far in a lot of ways. But these 33 hours will be some of the best of my life til the day I die. No test. No testimony baby. Bring on 2024 🎉🎉🎉

Ian Carroll

76,033 Aufrufe • vor 2 Jahren

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.
0:52

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.

Yam Peleg

420,390 Aufrufe • vor 9 Monaten

In AI-generated art, the idea is still where creativity begins. The idea behind this animation is mine. AI is simply the medium I chose to bring it to life. And when it can turn an idea into something this beautiful, why wouldn’t I use it? Don’t let other people decide which tools you’re allowed to create with. AI can be an incredible playground for creativity. If you’re already creative, it gives you new ways to explore that creativity. And if you’ve never thought of yourself as creative, you might discover a talent you didn’t even know you had. I just want people to enjoy art. And if AI inspires someone to start creating for the first time, they’re more than welcome to join the fun.
0:30

In AI-generated art, the idea is still where creativity begins. The idea behind this animation is mine. AI is simply the medium I chose to bring it to life. And when it can turn an idea into something this beautiful, why wouldn’t I use it? Don’t let other people decide which tools you’re allowed to create with. AI can be an incredible playground for creativity. If you’re already creative, it gives you new ways to explore that creativity. And if you’ve never thought of yourself as creative, you might discover a talent you didn’t even know you had. I just want people to enjoy art. And if AI inspires someone to start creating for the first time, they’re more than welcome to join the fun.

OscarAI

12,714 Aufrufe • vor 2 Tagen

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.
4:15

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

Sudo su

39,764 Aufrufe • vor 3 Monaten