Loading video...

Video Failed to Load

Go Home

I wanted to see if Qoder could turn a real World Development Indicators CSV into something verifiable, not just a pretty summary. I opened a new task, selected the QoderCSVReport workspace, left the model on Auto, set permissions, and gave Qoder the CSV. The file had 1,045 rows, 14...

AIStackLabX's profile picture

AI StackLab

71,148 subscribers

139,779 views • 5 days ago •via X (Twitter)

FinanceEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

7 Comments

AI StackLab's profile picture
AI StackLab5 days ago

Try Qoder free with 600 Credits 👇 300 from the Pro trial + 300 with code XK66ZB. 👉

JAYDEN™'s profile picture
JAYDEN™5 days ago

Going from a 1,045-row dataset to a complete interactive dashboard plus verification script in one workflow is seriously impressive.

Aaliyah | AI's profile picture
Aaliyah | AI5 days ago

Handling missing values correctly and validating everything against the original CSV shows how much more reliable these workflows are becoming.

Don Quijote de la IA's profile picture
Don Quijote de la IA5 days ago

New tool for me Friend ✍️

AI with MERLIN's profile picture
AI with MERLIN5 days ago

This goes way beyond a pretty AI summary — structured artifacts, a dashboard, and a verifier make the output genuinely practical.

Miguel Ángel | GptZone's profile picture
Miguel Ángel | GptZone5 days ago

Very interesting, 600 Credits total: 300 from the trial and 300 from code.

Anna K Clinton : AI's profile picture
Anna K Clinton : AI5 days ago

The independent verification step is what really stands out. Turning raw CSV data into something you can actually inspect and trust is incredibly useful.

Related Videos

I wanted to see if an AI agent could take one goal all the way to a finished artifact. I gave Qoder a weekly competitor-tracking task. I started on the task screen, selected my workspace, left the model on Auto, set permissions, and sent the outcome instead of a step-by-step prompt. Qoder read the context and began planning. Rather than one generic research pass, it ran subagents for Cursor, Windsurf and GitHub Copilot in parallel. I watched them check public updates and bring their findings back into the main task. The work was visible: planning, tool calls, terminal commands, file changes and progress updates. It did not feel like another chat answer. It felt like watching a task move through an actual workflow. The final artifact was competitor-weekly-2026-09-22.md It summarized the week's highlights and included sources and caveats, including where public evidence was limited. That made the output reviewable: I could check the sources, question the conclusions, and decide what to do next. That is the part I care about. Qoder is a desktop AI agent you can hand an outcome as a task. It reads context, plans, uses tools, executes and verifies. You can watch, adjust, pause or take over. One goal → planning → parallel research → terminal work → verified Markdown report. In the model picker, Qwen3.8-Flash was showing 0.0x Credits through September 30, so that option was available at zero cost during the offer. If you want to try it, Qoder has a 14-day Pro trial with 300 Credits. Sign up first using this link at before you download. That adds another 300 Credits, for 600 total.
0:36

I wanted to see if an AI agent could take one goal all the way to a finished artifact. I gave Qoder a weekly competitor-tracking task. I started on the task screen, selected my workspace, left the model on Auto, set permissions, and sent the outcome instead of a step-by-step prompt. Qoder read the context and began planning. Rather than one generic research pass, it ran subagents for Cursor, Windsurf and GitHub Copilot in parallel. I watched them check public updates and bring their findings back into the main task. The work was visible: planning, tool calls, terminal commands, file changes and progress updates. It did not feel like another chat answer. It felt like watching a task move through an actual workflow. The final artifact was competitor-weekly-2026-09-22.md It summarized the week's highlights and included sources and caveats, including where public evidence was limited. That made the output reviewable: I could check the sources, question the conclusions, and decide what to do next. That is the part I care about. Qoder is a desktop AI agent you can hand an outcome as a task. It reads context, plans, uses tools, executes and verifies. You can watch, adjust, pause or take over. One goal → planning → parallel research → terminal work → verified Markdown report. In the model picker, Qwen3.8-Flash was showing 0.0x Credits through September 30, so that option was available at zero cost during the offer. If you want to try it, Qoder has a 14-day Pro trial with 300 Credits. Sign up first using this link at before you download. That adds another 300 Credits, for 600 total.

Nelly;

159,743 views • 5 days ago

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

143,163 views • 2 days ago

Competitor tracking is one of those tasks that's easy to skip because it's slow. I tested automating it with Qoder. The goal was simple: every week, research what changed across competitors and produce a report I could actually review. Qoder planned the research, checked public updates, ran tasks in parallel, and compiled everything into a structured Markdown report with sources and caveats where evidence was limited. The workflow went from manual to: schedule → research → verify → analyze → report. I also ran Qwen3.8-Flash on it, which is showing 0.0x Credits through September 30. Qoder has a 14-day Pro trial with 300 Credits. Sign up before downloading through this link and you get another 300 — 600 Credits total: The interesting part isn't just the research. It's having an AI agent turn a recurring task into a finished artifact automatically.
0:30

Competitor tracking is one of those tasks that's easy to skip because it's slow. I tested automating it with Qoder. The goal was simple: every week, research what changed across competitors and produce a report I could actually review. Qoder planned the research, checked public updates, ran tasks in parallel, and compiled everything into a structured Markdown report with sources and caveats where evidence was limited. The workflow went from manual to: schedule → research → verify → analyze → report. I also ran Qwen3.8-Flash on it, which is showing 0.0x Credits through September 30. Qoder has a 14-day Pro trial with 300 Credits. Sign up before downloading through this link and you get another 300 — 600 Credits total: The interesting part isn't just the research. It's having an AI agent turn a recurring task into a finished artifact automatically.

Shruti

141,916 views • 4 days ago

Created a new task with Qoder: gave it one of my own talk recordings and its transcript, and asked it to find the five most clippable moments, caption them, and cut them with ffmpeg. This is the whole run (check the video 😏) • Qoder is a desktop app where you hand work over as a task rather than chatting about it. • You describe the outcome, pick a model, set permissions, and then watch it plan, run commands, and touch files. You can pause it or take over at any point. • The model picker is worth a look on its own. You choose per task or leave it on Auto, and Qwen3.8-Flash is running at 0.0x through September 30, so you can work through real tasks at zero Credits right now. 🪙 14-day Pro trial gets you 300 Credits. My code gets you another 300. 🔗 Enter AD23XU at first, then download and sign in. [1/2] ↓ #ad
1:29

Created a new task with Qoder: gave it one of my own talk recordings and its transcript, and asked it to find the five most clippable moments, caption them, and cut them with ffmpeg. This is the whole run (check the video 😏) • Qoder is a desktop app where you hand work over as a task rather than chatting about it. • You describe the outcome, pick a model, set permissions, and then watch it plan, run commands, and touch files. You can pause it or take over at any point. • The model picker is worth a look on its own. You choose per task or leave it on Auto, and Qwen3.8-Flash is running at 0.0x through September 30, so you can work through real tasks at zero Credits right now. 🪙 14-day Pro trial gets you 300 Credits. My code gets you another 300. 🔗 Enter AD23XU at first, then download and sign in. [1/2] ↓ #ad

Eleftheria Batsou

148,092 views • 2 days ago

“Atria Dawn Preview” just caught my attention after I tested it on a real frontend task. I tested Atria ASI with Claude Code on a real frontend task: build a modern, responsive landing page using HTML, CSS, and JavaScript. It created the files, validated the code, and opened the final result for review. What stood out was the workflow. It went from understanding the task to writing code, checking the result, and delivering something I could actually run and verify. That makes “Atria Dawn Preview” interesting to me for research, development, and other professional workflows where the goal isn’t just an answer, but a usable and verifiable result. Definitely an agent I’ll be keeping an eye on. Official links:👇 API: Website: Looking forward to seeing where Atria Dawn Preview goes next.
0:40

“Atria Dawn Preview” just caught my attention after I tested it on a real frontend task. I tested Atria ASI with Claude Code on a real frontend task: build a modern, responsive landing page using HTML, CSS, and JavaScript. It created the files, validated the code, and opened the final result for review. What stood out was the workflow. It went from understanding the task to writing code, checking the result, and delivering something I could actually run and verify. That makes “Atria Dawn Preview” interesting to me for research, development, and other professional workflows where the goal isn’t just an answer, but a usable and verifiable result. Definitely an agent I’ll be keeping an eye on. Official links:👇 API: Website: Looking forward to seeing where Atria Dawn Preview goes next.

Aryan Rakib

35,129 views • 12 days ago

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 views • 3 months ago

I got a smart meter recently and saw you can download a HDF file with the data so I had the idea of writing a script that could parse that and show the data in a useful manner. However I discovered that someone has already done this and done a really good job on it. The video explains how it works. In simple terms it uses the ESB smart meter data and shows a breakdown of how much data you are using and when and also recommends plans and estimates what each one would cost based on the data. The tool is available at easier to read on Laptop or Tablet or then your phone to Landscape.
1:26

I got a smart meter recently and saw you can download a HDF file with the data so I had the idea of writing a script that could parse that and show the data in a useful manner. However I discovered that someone has already done this and done a really good job on it. The video explains how it works. In simple terms it uses the ESB smart meter data and shows a breakdown of how much data you are using and when and also recommends plans and estimates what each one would cost based on the data. The tool is available at easier to read on Laptop or Tablet or then your phone to Landscape.

Carlow Weather

298,565 views • 2 years ago

what the hell did this free stealth model just build 💀 I asked Space Bunny, a Flash-level model, to make Minecraft in one HTML file and left it running it came back with a playable survival game inside my browser I could explore the generated world, break and place blocks, and switch items through the hotbar easily the best result I have got from a coding model on this test Space Bunny is free on OpenCode for the next week prompt below:
2:19

what the hell did this free stealth model just build 💀 I asked Space Bunny, a Flash-level model, to make Minecraft in one HTML file and left it running it came back with a playable survival game inside my browser I could explore the generated world, break and place blocks, and switch items through the hotbar easily the best result I have got from a coding model on this test Space Bunny is free on OpenCode for the next week prompt below:

Israfil

41,131 views • 3 days ago

Johnny Manziel says the adrenaline he felt walking into SEC stadiums never showed up once in the NFL, and he lost love for the game entirely “It comes from like, damn, I didn’t even make it through a four-year contract, two terrible years in Cleveland. At times, I showed potential of what I could have been, and then I just stopped giving a sh*t about the game, and I lost love for it.” “And it was so fun walking into SEC stadiums. The energy, and I remember walking into an NFL field for the first time and being like, ‘This isn’t that.’” “It’s just lit, but it was like it was such a hype and adrenaline run and like I didn’t really get that in the NFL. And I was in a situation that, half of the people in the organization probably wanted to be me to be there and half of them didn’t.” “Like half of them didn’t see who I was or the potential. And when you don’t put in the time in and do the right things, you just kind of fall out of it.”
0:48

Johnny Manziel says the adrenaline he felt walking into SEC stadiums never showed up once in the NFL, and he lost love for the game entirely “It comes from like, damn, I didn’t even make it through a four-year contract, two terrible years in Cleveland. At times, I showed potential of what I could have been, and then I just stopped giving a sh*t about the game, and I lost love for it.” “And it was so fun walking into SEC stadiums. The energy, and I remember walking into an NFL field for the first time and being like, ‘This isn’t that.’” “It’s just lit, but it was like it was such a hype and adrenaline run and like I didn’t really get that in the NFL. And I was in a situation that, half of the people in the organization probably wanted to be me to be there and half of them didn’t.” “Like half of them didn’t see who I was or the potential. And when you don’t put in the time in and do the right things, you just kind of fall out of it.”

katsu

85,095 views • 1 month ago

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 views • 2 months ago

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 views • 3 months ago

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 views • 12 days ago

🚨TRUMP: "I would like my legacy to be that I came into a country that was great but is in trouble, and I made America great again and I got it out of trouble, and people respect America now, and we are a country of peace, and we've brought peace to the rest of the world."
0:37

🚨TRUMP: "I would like my legacy to be that I came into a country that was great but is in trouble, and I made America great again and I got it out of trouble, and people respect America now, and we are a country of peace, and we've brought peace to the rest of the world."

Autism Capital 🧩

130,522 views • 1 year ago

I got this custom scorpion rigged, animated and running in my game in one full day with AI. GPT-6 built the entire rig. My part was preparing the model and motion references, then giving feedback. After trying a few approaches, I found a workflow that worked: 1. Give it a model that makes sense. I generated the model with Tripo P2.0, then cleaned it up myself. Low-poly, optimized, split into logical parts. I think that preparation mattered a lot. GPT-6 works on the mesh through code. A manageable vertex count and sensible parts give it a clearer starting point for bone placement and skinning. 2. Show it the movement you want. I took a reference image of the character and used Seedance to generate side-view animation videos. I decided which animations the game needed and selected the takes with the movements I liked. Then I gave GPT-6 the model, the videos and that animation list. There was no existing rig to start from. 3. Compare the animation frame by frame. This was the idea I wanted to test: ask GPT-6 to compare its Blender animation against the reference video frame by frame, from the same view. That gave it concrete poses and timing to work toward. I could point to where the feet should be planted or when the tail should strike. 4. Expect to give feedback. A generated run can look like hopping. An attack can start with a jump you never wanted. Choosing the references matters, and a side view still leaves depth and hidden legs to figure out. It took several iterations. I explained what looked wrong and how I wanted it to move, and GPT-6 kept refining the animation. Once the walk worked, I also had it create left and right strafe animations procedurally from that walk. Those didn't need their own reference videos. By the end of the day, the creature was in Unity. I've recorded the full workflow, including the Blender setup and feedback process:
0:59

I got this custom scorpion rigged, animated and running in my game in one full day with AI. GPT-6 built the entire rig. My part was preparing the model and motion references, then giving feedback. After trying a few approaches, I found a workflow that worked: 1. Give it a model that makes sense. I generated the model with Tripo P2.0, then cleaned it up myself. Low-poly, optimized, split into logical parts. I think that preparation mattered a lot. GPT-6 works on the mesh through code. A manageable vertex count and sensible parts give it a clearer starting point for bone placement and skinning. 2. Show it the movement you want. I took a reference image of the character and used Seedance to generate side-view animation videos. I decided which animations the game needed and selected the takes with the movements I liked. Then I gave GPT-6 the model, the videos and that animation list. There was no existing rig to start from. 3. Compare the animation frame by frame. This was the idea I wanted to test: ask GPT-6 to compare its Blender animation against the reference video frame by frame, from the same view. That gave it concrete poses and timing to work toward. I could point to where the feet should be planted or when the tail should strike. 4. Expect to give feedback. A generated run can look like hopping. An attack can start with a jump you never wanted. Choosing the references matters, and a side view still leaves depth and hidden legs to figure out. It took several iterations. I explained what looked wrong and how I wanted it to move, and GPT-6 kept refining the animation. Once the walk worked, I also had it create left and right strafe animations procedurally from that walk. Those didn't need their own reference videos. By the end of the day, the creature was in Unity. I've recorded the full workflow, including the Blender setup and feedback process:

Stefan 3D AI

12,563 views • 13 days ago

Kit Harington talked about joining HBO's HARRY POTTER and the Chamber of Secrets on Today: "When I knew this was happening as a series, I thought it was the best idea. I love the films, but with this, they can really explore the books at their fullest, and for a book nerd like me, that was a really great idea. So it was one that I had eyes on, I really wanted to be in it, and the part I’m playing is just the best."
5:14

Kit Harington talked about joining HBO's HARRY POTTER and the Chamber of Secrets on Today: "When I knew this was happening as a series, I thought it was the best idea. I love the films, but with this, they can really explore the books at their fullest, and for a book nerd like me, that was a really great idea. So it was one that I had eyes on, I really wanted to be in it, and the part I’m playing is just the best."

Wizarding World Direct

193,147 views • 10 days ago