Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

I gave Space Bunny an ASCII wireframe and told it to compile it into a working dashboard. the ascii map was the entire spec. exact 250px sidebar, responsive grid, live charts on a 2-second mock telemetry loop. It reproduced the layout pixel-for-pixel and wired up all the state: sidebar...

iamfakhrealam's profile picture

Fakhr

36,321 subscribers

51,702 görüntüleme • 3 gün önce •via X (Twitter)

SanatEğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

17 Yorum

Kalsoom (ghotai ) profil fotoğrafı
Kalsoom (ghotai )3 gün önce

That 250px sidebar + live 2-second loop actually working on shot one is the part that sold me.

Parul Gautam profil fotoğrafı
Parul Gautam3 gün önce

The video of that telemetry dashboard looks insane — first-try pixel-perfect from ASCII is actually wild.

Z-Coder profil fotoğrafı
Z-Coder3 gün önce

That telemetry dashboard is seriously impressive getting a pixel-perfect result from ASCII on the first attempt is kind of crazy.

Farhan Azad Shuvra profil fotoğrafı
Farhan Azad Shuvra3 gün önce

Sounds Good!

Patrick's AIBuzzNews profil fotoğrafı
Patrick's AIBuzzNews3 gün önce

Been testing it since yesterday and the speed is the part nobody’s talking about enough.

Arfa Farheen profil fotoğrafı
Arfa Farheen3 gün önce

Dashboard looks production-ready, not “AI slop with extra steps.”

Mushfiq Sajib profil fotoğrafı
Mushfiq Sajib3 gün önce

This is the kind of demo that makes you open OpenCode immediately.

Amira Zairi profil fotoğrafı
Amira Zairi3 gün önce

Anonymous model + 1M context + this kind of frontend output is a dangerous combo

Javeriya Ahsan profil fotoğrafı
Javeriya Ahsan3 gün önce

The ASCII-as-blueprint part is wild. If it really holds pixel-level layout + state wiring from a simple spec, that’s a pretty different way of building UIs.

Nargis Mita profil fotoğrafı
Nargis Mita3 gün önce

Turning ASCII into pixel-perfect UI is impressive.

RAVI KUMAR SAHU profil fotoğrafı
RAVI KUMAR SAHU3 gün önce

Treating ASCII as a precise UI blueprint is seriously impressive.

Dhaval Makwana profil fotoğrafı
Dhaval Makwana3 gün önce

The fact that it wired up nav, dropdown, and filters without extra prompting is what most agents still fail at.

Aaliya profil fotoğrafı
Aaliya3 gün önce

This one actually makes me want to build something tonight instead of just watching the video.

Utkarsh Sharma profil fotoğrafı
Utkarsh Sharma3 gün önce

Who’s actually behind Space Bunny at this point? MiniMax rumors keep getting louder.

Samuel Hu profil fotoğrafı
Samuel Hu3 gün önce

pixel-perfect layout is a good demo. i'd mutate the ascii spec after the first pass and see if the agent updates state without clobbering the live chart. the 2-second loop is where race bugs show up. did you run a second edit?

Muhammad Ayan profil fotoğrafı
Muhammad Ayan3 gün önce

Nobody had ASCII sketches on their 2026 bingo card, But if it's pixel-exact, wireframing just got way cheaper :)

Muhammad Ali profil fotoğrafı
Muhammad Ali3 gün önce

Most models still guess the layout even when you describe it twice. This one treating the wireframe like a blueprint is the difference.

Benzer Videolar

I gave Space Bunny a napkin sketch of a flight tracker inside OpenCode. After testing, seems like it's at flash level. it built this: → a 3D globe with glowing continent outlines → flight arcs with planes moving along them → click a route, the globe turns to it → all in one HTML file the part that got me: it printed an ASCII map of the world in the terminal to check its own continents before shipping, while doing all really quick. first full version in 3.5 minutes. done with fixes in about 6. a simpler dashboard screenshot to working page took 45 seconds. on OpenRouter it runs at ~90 tokens/sec with about 1.3s to first token. 1M context. text, image and video in. free in OpenCode this week. what would you sketch for it?
0:36

I gave Space Bunny a napkin sketch of a flight tracker inside OpenCode. After testing, seems like it's at flash level. it built this: → a 3D globe with glowing continent outlines → flight arcs with planes moving along them → click a route, the globe turns to it → all in one HTML file the part that got me: it printed an ASCII map of the world in the terminal to check its own continents before shipping, while doing all really quick. first full version in 3.5 minutes. done with fixes in about 6. a simpler dashboard screenshot to working page took 45 seconds. on OpenRouter it runs at ~90 tokens/sec with about 1.3s to first token. 1M context. text, image and video in. free in OpenCode this week. what would you sketch for it?

Muhammad Ayan

61,959 görüntüleme • 3 gün önce

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription
0:22

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

savip.

68,984 görüntüleme • 2 ay önce

WTF.. 65 of the 96 core team members behind this AI agent are university students. It’s called Atria Dawn Preview. Atria ASI I saw that and was like… okay, I need to try this. So I plugged it into Codex and asked it to build me an interactive creator dashboard from scratch. It made the files, wrote the code, ran the checks, fixed what broke and actually got the dashboard working. And it got there without me babysitting every step. Not bad at all for a first run.
0:56

WTF.. 65 of the 96 core team members behind this AI agent are university students. It’s called Atria Dawn Preview. Atria ASI I saw that and was like… okay, I need to try this. So I plugged it into Codex and asked it to build me an interactive creator dashboard from scratch. It made the files, wrote the code, ran the checks, fixed what broke and actually got the dashboard working. And it got there without me babysitting every step. Not bad at all for a first run.

EyeingAI

26,248 görüntüleme • 15 gün önce

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 görüntüleme • 3 ay önce

This looks like a toy. It's actually the meanest little vision eval I've built. The task: look at an emoji image, then repaint it on a 16×16 grid, one pixel at a time. Just the model, a tiny canvas, and up to 2000 brushstrokes. What I didn't expect was the personalities. > some models REGRET a stroke and go back to repaint it > some get stuck looping the same little patch over and over, like they're trying to animate it > some are calm little surgeons and just nail it first try And the task is genuinely mean: it has to see the image, crush it down to 256 cells, then decide what's actually load-bearing: > the tears on 😂 but still keep the smile > the horn on 🦄 > the antenna on 🤖 and keep the soul of it with almost no resolution to spare. 5 models. 7 emojis. Best of 5 runs each. Side by side. Who's your winner?
0:46

This looks like a toy. It's actually the meanest little vision eval I've built. The task: look at an emoji image, then repaint it on a 16×16 grid, one pixel at a time. Just the model, a tiny canvas, and up to 2000 brushstrokes. What I didn't expect was the personalities. > some models REGRET a stroke and go back to repaint it > some get stuck looping the same little patch over and over, like they're trying to animate it > some are calm little surgeons and just nail it first try And the task is genuinely mean: it has to see the image, crush it down to 256 cells, then decide what's actually load-bearing: > the tears on 😂 but still keep the smile > the horn on 🦄 > the antenna on 🤖 and keep the soul of it with almost no resolution to spare. 5 models. 7 emojis. Best of 5 runs each. Side by side. Who's your winner?

stevibe

284,432 görüntüleme • 3 ay önce

been playing with whop's new blueprints feature and a part of it changes the whole math on starting a business.. a blueprint is a full business ready to run. not a template you fill in. the actual site, the checkout, tracking, the whop pixel, analytics, all of it live from the first second. you pick a bluepint, name it and deploy, that's it. you're on a .whop.app url taking real payments with nothing left to wire up. i deployed one in the time it takes to read this and these aren't thin little landing pages. multi-page sites, customer accounts, carts, booking, subscriptions, reviews, checkout. full commercial sites out of the box, hosted on Whop for free. the analytics sit in the same dashboard. traffic, conversions, revenue, MRR, churn, ad spend, all in one place,you deploy and you can already see everything. but here's the part that actually that got me invested into it. instead of just building and deploying blueprints, it has other features in-built which can make the whole process easier and every business that gets onboarded through a blueprint you built earns you 10% of whop's gross profit from that business. recurring, per business, for as long as they run. so building a blueprint is its own business. you build one for a niche, put it out there, and every business that runs on it keeps paying you while you do nothing. i spent years thinking distribution was the hard part. build a good blueprint and the distribution is the business.
0:42

been playing with whop's new blueprints feature and a part of it changes the whole math on starting a business.. a blueprint is a full business ready to run. not a template you fill in. the actual site, the checkout, tracking, the whop pixel, analytics, all of it live from the first second. you pick a bluepint, name it and deploy, that's it. you're on a .whop.app url taking real payments with nothing left to wire up. i deployed one in the time it takes to read this and these aren't thin little landing pages. multi-page sites, customer accounts, carts, booking, subscriptions, reviews, checkout. full commercial sites out of the box, hosted on Whop for free. the analytics sit in the same dashboard. traffic, conversions, revenue, MRR, churn, ad spend, all in one place,you deploy and you can already see everything. but here's the part that actually that got me invested into it. instead of just building and deploying blueprints, it has other features in-built which can make the whole process easier and every business that gets onboarded through a blueprint you built earns you 10% of whop's gross profit from that business. recurring, per business, for as long as they run. so building a blueprint is its own business. you build one for a niche, put it out there, and every business that runs on it keeps paying you while you do nothing. i spent years thinking distribution was the hard part. build a good blueprint and the distribution is the business.

Sulfur

42,267 görüntüleme • 1 ay önce

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.
7:18

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.

Mckay Wrigley

85,751 görüntüleme • 2 yıl önce

Damian Lillard says he bought a $100,000 Porsche 911 after getting an advance from the Blazers before playing his first NBA game “I bought a Porsche off the rip. I bought it so fast. I bought it so fast that I was still living in Oakland when I bought it. The first check I got from the Blazers, I hadn't even played a game yet. It was like an advance. I came to Portland in the summer and they handed me the check” “I was with my brother and my older cousin. And we looking at it like, ‘Damn.’ We couldn't believe it. I was ready to go spend it all right there. I came back home, got back to Oakland, went to that Porsche dealership. It was charcoal gray. I still got it. It was $100,000”
1:06

Damian Lillard says he bought a $100,000 Porsche 911 after getting an advance from the Blazers before playing his first NBA game “I bought a Porsche off the rip. I bought it so fast. I bought it so fast that I was still living in Oakland when I bought it. The first check I got from the Blazers, I hadn't even played a game yet. It was like an advance. I came to Portland in the summer and they handed me the check” “I was with my brother and my older cousin. And we looking at it like, ‘Damn.’ We couldn't believe it. I was ready to go spend it all right there. I came back home, got back to Oakland, went to that Porsche dealership. It was charcoal gray. I still got it. It was $100,000”

dank

420,774 görüntüleme • 2 ay önce

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 görüntüleme • 15 gün önce

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 görüntüleme • 1 ay önce

Fable 5 (max) “build a clash of clans clone” Fable absolutely destroys Sonnet 5, and I’ll show that in an upcoming comparison video. I did give it one follow-up while it was working, basically telling it I only needed a demo and didn’t need it to overthink the whole thing, so it ended up being only around 2,500 lines. The funny part is it still grabbed the Clash of Clans assets with no trouble, which genuinely surprised me. I missed this model so much.
1:07

Fable 5 (max) “build a clash of clans clone” Fable absolutely destroys Sonnet 5, and I’ll show that in an upcoming comparison video. I did give it one follow-up while it was working, basically telling it I only needed a demo and didn’t need it to overthink the whole thing, so it ended up being only around 2,500 lines. The funny part is it still grabbed the Clash of Clans assets with no trouble, which genuinely surprised me. I missed this model so much.

Chris

264,339 görüntüleme • 2 ay önce

We just launched Quant IQ 🧠 an AI assistant built directly into Quant Data. It sees what you see 👀. Ask "What does the 0DTE GEX look like for SPY?" and it answers using the live data on your screen. You can describe what you want in plain English, and it does it: "Add a SPX GEX Heat Map to my page." Done. "Filter the order flow table for Mag 7 tickers and OTM contracts expiring within 90 days." Done. Quant IQ is included with every dashboard subscription. This is the first version. It only gets smarter from here.
0:40

We just launched Quant IQ 🧠 an AI assistant built directly into Quant Data. It sees what you see 👀. Ask "What does the 0DTE GEX look like for SPY?" and it answers using the live data on your screen. You can describe what you want in plain English, and it does it: "Add a SPX GEX Heat Map to my page." Done. "Filter the order flow table for Mag 7 tickers and OTM contracts expiring within 90 days." Done. Quant IQ is included with every dashboard subscription. This is the first version. It only gets smarter from here.

Andrew Hiesinger

21,009 görüntüleme • 2 ay önce

My top 3 in voting was 1. cs_alpine 2. de_golden 3. de_warden This is Golden; a very interesting layout that takes a little getting used to, hence me dying a lot at the start of this playtest but it gets better. This is the map I want to play the most due to the layout. This contest had a number of daring and unique layouts (contact is also worth a look); for me this one was the most intriguing and perhaps offers something new to CS2 . Perhaps Overpass stans will get the mental juices flowing on this map. Maps like these offer something new and challenging to CS, beyond the tried and tested layout formula that we are all familiar with. When CS2 add new community maps in updates, I think a video should accompany the changes with fly-throughs and some words on the type of map it is to encourage people to test the waters of these new maps and potentially shape the future of the active duty map pool.
31:45

My top 3 in voting was 1. cs_alpine 2. de_golden 3. de_warden This is Golden; a very interesting layout that takes a little getting used to, hence me dying a lot at the start of this playtest but it gets better. This is the map I want to play the most due to the layout. This contest had a number of daring and unique layouts (contact is also worth a look); for me this one was the most intriguing and perhaps offers something new to CS2 . Perhaps Overpass stans will get the mental juices flowing on this map. Maps like these offer something new and challenging to CS, beyond the tried and tested layout formula that we are all familiar with. When CS2 add new community maps in updates, I think a video should accompany the changes with fly-throughs and some words on the type of map it is to encourage people to test the waters of these new maps and potentially shape the future of the active duty map pool.

James Bardolph

18,204 görüntüleme • 1 yıl önce

📼 | A little misunderstanding about Juan's death #Nexe: The first time someone told me that Juan died, it was Graf, for a second, I thought he died irl because I was on vacation and I didn't follow the lore #Roier: Oh, what the fuck, no, stupid! #Nexe: I was so scared for a second and then someone told me it was only in game and it was like Phew!
0:26

📼 | A little misunderstanding about Juan's death #Nexe: The first time someone told me that Juan died, it was Graf, for a second, I thought he died irl because I was on vacation and I didn't follow the lore #Roier: Oh, what the fuck, no, stupid! #Nexe: I was so scared for a second and then someone told me it was only in game and it was like Phew!

Roier English Updates

23,498 görüntüleme • 2 ay önce

Karpathy said something you'll regret ignoring: "We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues." He said it at YC talk last year, when the worry was reliability. The models hallucinated and made mistakes no human would, so the leash implied keeping yourself in the loop and checking the output before trusting it. The models are far better now, and the line still holds, for a reason he was not focused on back then. Even a model that writes flawless code today still has no idea who is allowed to run it. Correctness and authorization are different problems, and only correctness improves as the model improves. A perfect agent still hands a tool where anyone can do anything, because permission was never part of the task. I actually tested this in practice with Claude Code. I asked it to build a small internal tool with a button that issues account credits. It worked first try, and running it locally, the credit applied the instant I clicked. Nothing decided who was allowed to click it. The agent wrote the right logic and displayed a success notification. It never checked whether the caller had the right, whether it should pause for a human, or whether anything was logged. And this is not a bug a smarter model can outgrow because the leash was never in the code. Identity, permissions, and audit live in the system that runs the app, not in what the agent generates. To solve this, I took the exact same bundle and hosted it on Retool. The credit write that fired silently on my laptop now stopped at an approval gate, resolved to a real identity through SSO, and landed in an audit log. I wrote none of it. The app inherited the entire boundary the moment it was deployed, and the video shows the before and after. You can try it yourself here: I also wrote a detailed breakdown of the whole thing in my recent article, and I worked with the team to put this together. It walks through the build, the exact moment the credit write went through on my laptop with nobody checking, and then what changed when the same app ran on Retool. It also covers why this is a property of the runtime and not something a better model fixes, which is why devs typically miss this. The article is quoted below.
0:38

Karpathy said something you'll regret ignoring: "We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues." He said it at YC talk last year, when the worry was reliability. The models hallucinated and made mistakes no human would, so the leash implied keeping yourself in the loop and checking the output before trusting it. The models are far better now, and the line still holds, for a reason he was not focused on back then. Even a model that writes flawless code today still has no idea who is allowed to run it. Correctness and authorization are different problems, and only correctness improves as the model improves. A perfect agent still hands a tool where anyone can do anything, because permission was never part of the task. I actually tested this in practice with Claude Code. I asked it to build a small internal tool with a button that issues account credits. It worked first try, and running it locally, the credit applied the instant I clicked. Nothing decided who was allowed to click it. The agent wrote the right logic and displayed a success notification. It never checked whether the caller had the right, whether it should pause for a human, or whether anything was logged. And this is not a bug a smarter model can outgrow because the leash was never in the code. Identity, permissions, and audit live in the system that runs the app, not in what the agent generates. To solve this, I took the exact same bundle and hosted it on Retool. The credit write that fired silently on my laptop now stopped at an approval gate, resolved to a real identity through SSO, and landed in an audit log. I wrote none of it. The app inherited the entire boundary the moment it was deployed, and the video shows the before and after. You can try it yourself here: I also wrote a detailed breakdown of the whole thing in my recent article, and I worked with the team to put this together. It walks through the build, the exact moment the credit write went through on my laptop with nobody checking, and then what changed when the same app ran on Retool. It also covers why this is a property of the runtime and not something a better model fixes, which is why devs typically miss this. The article is quoted below.

Akshay 🚀

42,911 görüntüleme • 3 ay önce

I just designed a full food recipe app with dishes from all over the world… in under 10 minutes using Grok Build with the new Composer 2.5 model And the entire process was basically just 3 simple steps: → Gave the idea I had in my mind and asked it to plan everything → Told it to execute the plan → Made a few layout adjustments …and done This honestly feels like a cheat code for app development.... It even perfectly added the ingredient quantity adjustments and allergen ingredients to avoid check list The speed at which “Grok Build” can go from idea → design → launch now is absolutely insane
1:30

I just designed a full food recipe app with dishes from all over the world… in under 10 minutes using Grok Build with the new Composer 2.5 model And the entire process was basically just 3 simple steps: → Gave the idea I had in my mind and asked it to plan everything → Told it to execute the plan → Made a few layout adjustments …and done This honestly feels like a cheat code for app development.... It even perfectly added the ingredient quantity adjustments and allergen ingredients to avoid check list The speed at which “Grok Build” can go from idea → design → launch now is absolutely insane

X Freeze

13,066 görüntüleme • 4 ay önce

"Everyone's talking about continual learning. That's entirely where this space is going to go." The Applied Compute platform is architected around that premise: build memory and intuition from fragmented data across your entire org, train reasoning models directly on top of it, and close the loop. A model is just one piece. An agent is where it runs, what tools it has, how permissions and auth are handled, how humans guide and instruct it, and the observability around it all. Every interaction should be treated as a training signal so the system can compound over time. Thanks for having us TBPN
1:46

"Everyone's talking about continual learning. That's entirely where this space is going to go." The Applied Compute platform is architected around that premise: build memory and intuition from fragmented data across your entire org, train reasoning models directly on top of it, and close the loop. A model is just one piece. An agent is where it runs, what tools it has, how permissions and auth are handled, how humans guide and instruct it, and the observability around it all. Every interaction should be treated as a training signal so the system can compound over time. Thanks for having us TBPN

Applied Compute

64,309 görüntüleme • 7 ay önce

CLAUDE BUILT A TRADING SYSTEM ON MY MAC I gave Claude full control over my Mac and just left it running overnight No prompts, no detailed instructions – I just told it to figure out how to make money on Polymarket Then I closed the laptop and went to sleep In the morning, I opened my Mac and saw the terminal still running with logs constantly updating At first it looked like random activity, but once I scrolled through it, I realized it had actually built a structured system overnight It was already tracking wallets Ranking them by performance Filtering out the ones with random entries And focusing only on the ones with consistent behavior What surprised me the most is that it didn’t stop at analysis It organized everything into a working dashboard inside the terminal Capital, PnL, winrate – all updating in real time It even ranked wallets based on performance metrics like ROI, consistency, and execution timing This is the part I would normally spend hours building manually At that point, it was ready to trade, but not actually executing anything yet So I connected it to a Telegram copytrading bot to actually execute the trades, and just let it run Bot: Polymarket: After that, it started opening positions on its own A few hours later I checked the dashboard again Capital: $12,380 P&L: +$23,128 Winrate: 100% 48 trades executed Now I’m not even trading myself I just check the dashboard and see what it’s doing And the strange part is – it keeps getting better the longer it runs
0:24

CLAUDE BUILT A TRADING SYSTEM ON MY MAC I gave Claude full control over my Mac and just left it running overnight No prompts, no detailed instructions – I just told it to figure out how to make money on Polymarket Then I closed the laptop and went to sleep In the morning, I opened my Mac and saw the terminal still running with logs constantly updating At first it looked like random activity, but once I scrolled through it, I realized it had actually built a structured system overnight It was already tracking wallets Ranking them by performance Filtering out the ones with random entries And focusing only on the ones with consistent behavior What surprised me the most is that it didn’t stop at analysis It organized everything into a working dashboard inside the terminal Capital, PnL, winrate – all updating in real time It even ranked wallets based on performance metrics like ROI, consistency, and execution timing This is the part I would normally spend hours building manually At that point, it was ready to trade, but not actually executing anything yet So I connected it to a Telegram copytrading bot to actually execute the trades, and just let it run Bot: Polymarket: After that, it started opening positions on its own A few hours later I checked the dashboard again Capital: $12,380 P&L: +$23,128 Winrate: 100% 48 trades executed Now I’m not even trading myself I just check the dashboard and see what it’s doing And the strange part is – it keeps getting better the longer it runs

𝗖𝗛𝗔𝗜𝗡 𝗠𝗜𝗡𝗗 ⛓🧠

83,254 görüntüleme • 6 ay önce

the agent failed while I was asleep and somehow the work still got finished that was the test I actually wanted i gave GPT-6 Astra a workflow that normally needed me between every step inbound came in messy one agent had to sort it, another find the missing context, another build the deliverable, and the last one check everything before it reached me somewhere in the middle, agent 2 got stuck the source it needed wasn’t there normally that kills the entire chain instead, it wrote the missing piece into a blocker file and passed everything else forward the other agents kept working when I came back, most of the pack was finished and the one thing they couldn’t solve was sitting separately waiting for me that felt more important than a perfect demo because an agent completing 10/10 tasks is impressive an agent failing without taking the other 9 down with it is infrastructure
0:30

the agent failed while I was asleep and somehow the work still got finished that was the test I actually wanted i gave GPT-6 Astra a workflow that normally needed me between every step inbound came in messy one agent had to sort it, another find the missing context, another build the deliverable, and the last one check everything before it reached me somewhere in the middle, agent 2 got stuck the source it needed wasn’t there normally that kills the entire chain instead, it wrote the missing piece into a blocker file and passed everything else forward the other agents kept working when I came back, most of the pack was finished and the one thing they couldn’t solve was sitting separately waiting for me that felt more important than a perfect demo because an agent completing 10/10 tasks is impressive an agent failing without taking the other 9 down with it is infrastructure

Lummox

19,046 görüntüleme • 9 gün önce