Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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...

148,092 Aufrufe • vor 2 Tagen •via X (Twitter)

45 Kommentare

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

Use the code: AD23XU 1️⃣Enter it here first → 2️⃣Then download → 300 Credits from the trial, 300 from the code. [2/2]

Profilbild von Alex Bitoshi
Alex Bitoshivor 2 Tagen

@qoder_ai_ide This is a great example of an agent taking a task all the way to an actual deliverable.

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide Yes, and the great part is that you can customize it a lot.

Profilbild von Ryan Carter
Ryan Cartervor 2 Tagen

@qoder_ai_ide How did it handle the caption styling and word-level timing? Did it generate the subtitles via the transcript or use a separate tool for the burn-in?

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide It's generated using the transcript, but you can use an API as well, from Gemini (Free) or from wherever you want, to make everything even smoother.

Profilbild von Victor
Victorvor 2 Tagen

@qoder_ai_ide Do I get it right that you give it a video with transcription and it returns a set of nice clips out of it?

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide Yes, that's the project that I built. In general, with Qoder, you can do whatever you want.

Profilbild von Mary Queen 🫅
Mary Queen 🫅vor 2 Tagen

@qoder_ai_ide Video editing and clip generation via terminal commands is such a great test case for this. What model did you end up selecting on Auto for this run?

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide It's Qwen, which is currently completely free at Qoder.

Profilbild von Blake Thompson
Blake Thompsonvor 2 Tagen

@qoder_ai_ide Five clips, captions, and actual video edits from one task is a solid example of agentic automation.

Profilbild von Ana de Armas
Ana de Armasvor 2 Tagen

One task covering discovery, captions, cutting, and exporting is a surprisingly clean workflow.

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

Exactly. Thank you, Ana, for checking.

Profilbild von Rose Carter
Rose Cartervor 2 Tagen

@qoder_ai_ide This is a good demonstration of what happens when an AI agent gets access to tools, files, and a clear outcome.

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide Exactly, that's right. And I've started thinking about my next few projects as well. It has a generous free plan.

Profilbild von AHSAN BILAL
AHSAN BILALvor 2 Tagen

@qoder_ai_ide 0.0x on Qwen3.8-Flash through September is a steal. Testing this out with some talk transcripts today!

Profilbild von The Token Xpress 🚀
The Token Xpress 🚀vor 2 Tagen

@qoder_ai_ide Your project shows promise! Let’s discuss potential collaborations. ➡️💬

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

Of course, feel free to send me a DM.

Profilbild von Queen Isabell
Queen Isabellvor 2 Tagen

@qoder_ai_ide This is a killer demo for local AI task handoff. Definitely trying code AD23XU to test it out on my next talk recording!

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide Thank you! Free Qwen3.8-Flash runs through September plus double credits with the code!!

Profilbild von Eliana Skye 📊🚀
Eliana Skye 📊🚀vor 2 Tagen

@qoder_ai_ide Having the transcript alongside the video makes this kind of automated editing workflow really practical

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide Exactly, and that's what I wanted to do.

Profilbild von CLAIRE IVORY
CLAIRE IVORYvor 2 Tagen

@qoder_ai_ide The part I like most is that you give it the outcome instead of micromanaging every action.

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide Yes, and I've tested it with other projects as well, and I always get the result that I want.

Profilbild von SOPHIA VALE
SOPHIA VALEvor 2 Tagen

@qoder_ai_ide I like that the whole process stays visible instead of everything happening behind the scenes.

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide Yes, that was very useful, especially when I was checking the stage of every task.

Profilbild von ETHERSON
ETHERSONvor 2 Tagen

@qoder_ai_ide Free Qwen3.8-Flash runs through September plus double credits with the code is an insane deal. Appreciate you sharing the workflow setup!

Profilbild von Eleftheria Batsou
Eleftheria Batsouvor 2 Tagen

@qoder_ai_ide Thank you so much. It was my pleasure.

Profilbild von Melisa AI
Melisa AIvor 2 Tagen

@qoder_ai_ide Going from a raw talk recording to five ready-to-use clips in one workflow is pretty impressive.

Profilbild von Doremon AI
Doremon AIvor 2 Tagen

@qoder_ai_ide Heavy AI workloads running on autopilot and costing 0.0x? Qwen3.8-Flash is insane value. Lightning fast + free till end of September is a no-brainer.

Profilbild von Harrison AI
Harrison AIvor 2 Tagen

@qoder_ai_ide This is the kind of workflow where the final output matters more than the conversation.

Profilbild von Quantum Mind AI
Quantum Mind AIvor 2 Tagen

@qoder_ai_ide Running heavy AI tasks for 0.0x cost? Qwen3.8-Flash is literally free speed till September end. Must try!

Profilbild von BRAND
BRANDvor 2 Tagen

@qoder_ai_ide From transcript to finished clips without constant prompting—that’s the interesting part.

Profilbild von Cyber Sentinel AI
Cyber Sentinel AIvor 2 Tagen

@qoder_ai_ide Real control + AI automation = Perfect combo. Need this for my workflow

Profilbild von hidecoingloabal
hidecoingloabalvor 2 Tagen

@_tiv2 @qoder_ai_ide Automated competitive tracking is great

Profilbild von BLOCKCHAIN ⛓️
BLOCKCHAIN ⛓️vor 2 Tagen

@_tiv2 @qoder_ai_ide Free runs on Qwen3.8-Flash until the end of September? Count me in!

Profilbild von Neural Pulse AI
Neural Pulse AIvor 2 Tagen

@qoder_ai_ide This is huge! Zero cost for heavy AI tasks is exactly what developers needed. Trying Qwen3.8-Flash right now

Profilbild von Fudmottin
Fudmottinvor 2 Tagen

@qoder_ai_ide Do you prefer cloud based models over the ones you can run locally? I can see the performance appeal. I'm finding the privacy advantage of local models quite compelling. Also no direct fees per token, only time cost. And power if you can measure that.

Profilbild von Diamond Hands ₿ 💎🤲
Diamond Hands ₿ 💎🤲vor 2 Tagen

@_tiv2 @qoder_ai_ide If the speed holds up, free access like this could be seriously useful 🔥

Profilbild von Digital Horizon AI
Digital Horizon AIvor 2 Tagen

@qoder_ai_ide Qwen3.8-Flash is insanely fast 🔥

Profilbild von CallMeNeena_
CallMeNeena_vor 2 Tagen

@_tiv2 @qoder_ai_ide loop fresh without burning afternoon hours.

Profilbild von RealGoldfi
RealGoldfivor 2 Tagen

@_tiv2 @qoder_ai_ide human context is still needed to decide what to act on.

Profilbild von Chloe || $
Chloe || $vor 2 Tagen

@qoder_ai_ide The model picker is an interesting part too. Being able to choose per task or let Auto decide adds useful flexibility.

Profilbild von Sienna Valen
Sienna Valenvor 2 Tagen

@qoder_ai_ide Being able to pause the agent or take control midway is a nice touch for real-world tasks.

Profilbild von PhysicalFi
PhysicalFivor 2 Tagen

@qoder_ai_ide The demo itself is super cool to watch 😍

Profilbild von SULTAN KINGBTC💸
SULTAN KINGBTC💸vor 2 Tagen

@_tiv2 @qoder_ai_ide Heavy tasks on autopilot + Qwen3.8-Flash at 0.0x till Sep 30 = basically free AI work. Gotta try Qoder

Ähnliche 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.

Nelly;

159,743 Aufrufe • vor 5 Tagen

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!

GREG ISENBERG

30,787 Aufrufe • vor 12 Tagen

GPT 5.6 SOL IS HERE! How to run your personal + business life with GPT 5.6 Sol + Codex (full 49 min masterclass) We tested it for 30 days and the video it's the CLEAREST look at the FUTURE of work: Here's what's possible once you set it up: 1. Your inbox becomes cards every morning, each with a summary and a reply drafted in your own voice. Y 2. Your Slack, meeting notes, and company updates can turn into one daily feed with a clear next action. It learns what you care about over time and rewrites its own prompts to get sharper. 3. You can give your agent its own email address, so your other tools and even your team's Slack bot email it directly and it just handles things. 4. You can have it watch you do a task once and turn it into a skill it repeats forever. 5. You can set a long goal and walk away. You can have it run for 20 hours straight, and fine-tune your own models, something that was out of reach for non-engineers 12 months ago. How to start: Open Codex, give it access to your computer, and ask it to suggest things it could do for you based on how you already work. Full episode on The Startup Ideas Podcast (SIP) 🧃 (thanks Dan Shipper for sharing your entire workflow and review of GPT 5.6) Start with one boring task, get it working, and build from there. You'll learn exactly how to make something similar. GPT 5.6 Sol is impressive. Sol (according to openAI benchmarks) is the best coding model out right now. It set a new state of the art on Terminal-Bench 2.1 at 88.8%, and its "ultra mode" hits 91.9%, beating Claude Opus 4.8, Fable 5, and even Mythos 5 this masterclass is 100% free, like always. For more The Startup Ideas Podcast (SIP) 🧃 Watch

GREG ISENBERG

156,617 Aufrufe • vor 2 Monaten

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

Hermes just made its in-app browser a whole lot more useful. You can now keep multiple browser tabs open inside Hermes Desktop instead of every new page replacing the one you were already using. And that matters more than it sounds. Because this is not just about “having tabs.” It means Hermes can work across multiple pages without forcing you to keep losing your place every time you open the next thing. Research one source, keep it open, open another tab, compare them side by side, and keep moving. Check a few products before buying something. Look at multiple hotel or travel options at once. Keep a YouTube tutorial open in one tab while Hermes looks through docs or another page in the next. And because this lives inside Hermes Desktop, you are not limited to one basic browser view either. You can keep multiple tabs open. You can view two pages side by side. You can stack them top and bottom. You can even run a four-panel view when you want several pages open at once. So the browser inside Hermes is starting to feel a lot more like a real workspace instead of one page you keep replacing. There is also some nice polish that comes with it. Browser tabs now label themselves based on the page, and the address bar behaves more cleanly while pages are loading. And remember, this is the same in-app browser Hermes can already read, click through, type in, scroll, and annotate. So this is not just a prettier browser. It is a more capable workspace for the browser Hermes is actually using. If Hermes is going to do more of your work on the web, this is exactly the kind of browser upgrade it needed.

Hermes Release Watch

52,493 Aufrufe • vor 1 Monat