Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

🧵 1/7 I gave a Flash model a written spec for a 3D physics game. It broke the task into steps, wrote the code, used the tools, ran the project, and eventually produced a billiards game I could actually play. Ant Ling Ling-3.0-flash has 124B total parameters, but activates...

Lonely__MH's profile picture

Lonely

23,430 subscribers

121,029 görüntüleme • 1 ay önce •via X (Twitter)

Bilim & TeknolojiEğitimOyun
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

one model built ten webpages in 160 seconds. the next one took 623. same prompt to three models at once: ten standalone HTML pages, one per footballer, shared template and CSS, each self-contained. Ling-3.0-flash: 160s Step 3.7 Flash: 319s MiniMax M2.7: 623s first reasoning token came back in 84ms. the other two took 378ms and 8.7s. Ant Ling shipped it at 124B total, 5.1B active per token. one eighth the parameters of their own 1T flagship, and it matches or beats it on most benchmarks they published. the whole race takes 20 seconds to watch.
0:20

one model built ten webpages in 160 seconds. the next one took 623. same prompt to three models at once: ten standalone HTML pages, one per footballer, shared template and CSS, each self-contained. Ling-3.0-flash: 160s Step 3.7 Flash: 319s MiniMax M2.7: 623s first reasoning token came back in 84ms. the other two took 378ms and 8.7s. Ant Ling shipped it at 124B total, 5.1B active per token. one eighth the parameters of their own 1T flagship, and it matches or beats it on most benchmarks they published. the whole race takes 20 seconds to watch.

Hanako

34,332 görüntüleme • 1 ay önce

Most AI research demos show you a polished answer. This one showed me the disagreement that happened before the answer. I gave Ling-3.0-flash Ant Ling a deliberately difficult question: Do four-day workweeks actually increase productivity, or do they simply compress the same workload into fewer days? Instead of asking for a quick summary, I asked it to coordinate five specialist roles: a scientist, a data analyst, a cross-validator, an archivist, and a research writer. Each role had a separate responsibility. The scientist defined the competing hypotheses. The analyst extracted comparable findings. The archivist tracked the sources. The writer could only use approved claims. And the cross-validator had one job: challenge anything that sounded more confident than the evidence allowed. That last role changed the result. The team reviewed 12 sources and challenged six major claims. Three claims were narrowed. One was rejected entirely. Even a widely repeated claim about a 40% productivity increase did not survive the evidence check. That is the part I wanted to see from an AI research workflow. Not just more information, but visible resistance to weak evidence. The final output included: - a direct executive answer - a structured research paper - a source and evidence table - a disagreement log - a six-slide executive deck - a quality-control summary The conclusion was also more useful than a simple yes or no: reduced working hours may maintain productivity and improve wellbeing under certain conditions, while compressing the same workload into fewer days can increase fatigue and intensity. The evidence did not support a universal productivity claim. What impressed me was not that Ling-3.0-flash generated a long response. Plenty of models can do that. It was the way the model maintained multiple roles, evidence standards, objections, citations, and deliverables across one extended workflow, while preserving uncertainty instead of smoothing it away. That makes Ling-3.0-flash especially interesting for work where execution matters as much as reasoning: research, search, coding, document processing, tool use, repeated checks, and other multi-step agent workflows. The strongest AI systems will not use the largest model for every task. They will combine deep planning with fast, cost-efficient execution. Ling-3.0-flash is built for that execution layer. Ling-3.0-flash is now available on OpenRouter and free to use through August 3, 2026. Try it in your coding, search, research, and tool-use workflows. Then show us what you build. Try Ling-3.0-flash: Documentation:
0:33

Most AI research demos show you a polished answer. This one showed me the disagreement that happened before the answer. I gave Ling-3.0-flash Ant Ling a deliberately difficult question: Do four-day workweeks actually increase productivity, or do they simply compress the same workload into fewer days? Instead of asking for a quick summary, I asked it to coordinate five specialist roles: a scientist, a data analyst, a cross-validator, an archivist, and a research writer. Each role had a separate responsibility. The scientist defined the competing hypotheses. The analyst extracted comparable findings. The archivist tracked the sources. The writer could only use approved claims. And the cross-validator had one job: challenge anything that sounded more confident than the evidence allowed. That last role changed the result. The team reviewed 12 sources and challenged six major claims. Three claims were narrowed. One was rejected entirely. Even a widely repeated claim about a 40% productivity increase did not survive the evidence check. That is the part I wanted to see from an AI research workflow. Not just more information, but visible resistance to weak evidence. The final output included: - a direct executive answer - a structured research paper - a source and evidence table - a disagreement log - a six-slide executive deck - a quality-control summary The conclusion was also more useful than a simple yes or no: reduced working hours may maintain productivity and improve wellbeing under certain conditions, while compressing the same workload into fewer days can increase fatigue and intensity. The evidence did not support a universal productivity claim. What impressed me was not that Ling-3.0-flash generated a long response. Plenty of models can do that. It was the way the model maintained multiple roles, evidence standards, objections, citations, and deliverables across one extended workflow, while preserving uncertainty instead of smoothing it away. That makes Ling-3.0-flash especially interesting for work where execution matters as much as reasoning: research, search, coding, document processing, tool use, repeated checks, and other multi-step agent workflows. The strongest AI systems will not use the largest model for every task. They will combine deep planning with fast, cost-efficient execution. Ling-3.0-flash is built for that execution layer. Ling-3.0-flash is now available on OpenRouter and free to use through August 3, 2026. Try it in your coding, search, research, and tool-use workflows. Then show us what you build. Try Ling-3.0-flash: Documentation:

Rachel🥥

73,264 görüntüleme • 1 ay önce

watch this anon. i gave NVIDIA's biggest model ever a single task. 100 minutes and 440,000 tokens later, it had rendered nothing. not one important thing on the screen. this is Nemotron 3 Ultra. 550 billion parameters, a hybrid Mamba Transformer MoE, the largest model NVIDIA has ever shipped, and they built it specifically for long-running agentic coding. so i handed it exactly that: build a 3D scene from a spec, multiple files, iterate until the tests pass. the same task a frontier model one shotted in minutes. i genuinely wanted to be impressed. it ran for an hour and forty. burned through 440,000 tokens. wrote every file, passed its own tests, and proudly printed "task complete."the browser was blank. the 3D scene never rendered. not once. and the long horizon agentic behavior was genuinely good. it stayed on task the whole hour and forty, wrote real multi-file code, drove its own tools without derailing. it just couldn't turn any of that into something that actually runs. here's the part that gets me. it's a text model, it cannot see its own output. so it sat there looping on a broken vision tool, trying to "look" at the page, hitting error after error, never once reasoning its way out. it declared victory on an empty screen because it had no way to know the screen was empty. to be fair, i genuinely don't know what quant the NIM was serving, so maybe some of that's on the serving, not the model. but the biggest model NVIDIA has ever made, on the exact task it was designed for, couldn't tell it had built nothing in 100 minutes. same task on a local model, below thread👇.
4:07

watch this anon. i gave NVIDIA's biggest model ever a single task. 100 minutes and 440,000 tokens later, it had rendered nothing. not one important thing on the screen. this is Nemotron 3 Ultra. 550 billion parameters, a hybrid Mamba Transformer MoE, the largest model NVIDIA has ever shipped, and they built it specifically for long-running agentic coding. so i handed it exactly that: build a 3D scene from a spec, multiple files, iterate until the tests pass. the same task a frontier model one shotted in minutes. i genuinely wanted to be impressed. it ran for an hour and forty. burned through 440,000 tokens. wrote every file, passed its own tests, and proudly printed "task complete."the browser was blank. the 3D scene never rendered. not once. and the long horizon agentic behavior was genuinely good. it stayed on task the whole hour and forty, wrote real multi-file code, drove its own tools without derailing. it just couldn't turn any of that into something that actually runs. here's the part that gets me. it's a text model, it cannot see its own output. so it sat there looping on a broken vision tool, trying to "look" at the page, hitting error after error, never once reasoning its way out. it declared victory on an empty screen because it had no way to know the screen was empty. to be fair, i genuinely don't know what quant the NIM was serving, so maybe some of that's on the serving, not the model. but the biggest model NVIDIA has ever made, on the exact task it was designed for, couldn't tell it had built nothing in 100 minutes. same task on a local model, below thread👇.

Sudo su

32,589 görüntüleme • 2 ay önce

Every big MoE model I test on my 3090 is basically to see how good it is compared to Qwen3.6-27B. "How good is it compared to Qwen3.6-27B?" is the question I get asked the most, and that shows how much people love and, more importantly, trust the 27B 27B is battle tested. It has proven its worth and has nothing left to prove. Now it just needs to make way for the next 27B. Here’s an example video: a Three.js task, same prompt, not oneshot but two shots for all models. All ran on my 3090 + 64GB VRAM Qwen-3.6-27b fully on vram while others have experts offloaded to system ram. Pinned on the left: Qwen3.6-27B-Q5 On the right, i'm switching between Inkling-Small-Q4_K_M DSV4-Flash-0731-UD-IQ1 Ling-3.0-Flash-Q4_K_M Qwen3.6-27B nailed it. The effects and visuals are just spot on.The other models got some things right, but not everything. Second place would have to go to Inkling-Small while DSV4-Flash-0731 and Ling-3.0-Flash failed to capture the full requirements. This is also why we’re all excited for Qwen Qwen3.8-27B!
2:20

Every big MoE model I test on my 3090 is basically to see how good it is compared to Qwen3.6-27B. "How good is it compared to Qwen3.6-27B?" is the question I get asked the most, and that shows how much people love and, more importantly, trust the 27B 27B is battle tested. It has proven its worth and has nothing left to prove. Now it just needs to make way for the next 27B. Here’s an example video: a Three.js task, same prompt, not oneshot but two shots for all models. All ran on my 3090 + 64GB VRAM Qwen-3.6-27b fully on vram while others have experts offloaded to system ram. Pinned on the left: Qwen3.6-27B-Q5 On the right, i'm switching between Inkling-Small-Q4_K_M DSV4-Flash-0731-UD-IQ1 Ling-3.0-Flash-Q4_K_M Qwen3.6-27B nailed it. The effects and visuals are just spot on.The other models got some things right, but not everything. Second place would have to go to Inkling-Small while DSV4-Flash-0731 and Ling-3.0-Flash failed to capture the full requirements. This is also why we’re all excited for Qwen Qwen3.8-27B!

AJ

11,670 görüntüleme • 24 gün önce

99% of iPhone users don’t know this: Their phone already has a free music production powerhouse hidden inside. It’s one of the treasures left behind from the Steve Jobs era. Millions of people own an iPhone, iPad, or MacBook — but have never truly opened it. I asked an AI Agent to create a completely new piece of music from scratch. The result surprised me. It wasn’t just generating audio. It could be edited. Sounds, channels, tracks — everything was adjustable. But I didn’t ask AI to generate an MP3. Instead, I asked it to create a: structured, editable, and extendable music project. The model had to understand: 🎹 Main melody 🎻 Harmony relationships 🥁 Rhythm design 🎸 Instrument arrangement 🎼 Multi-track structure The final output was MIDI, which was imported directly into GarageBand. And this reveals a key difference: Traditional AI music tools like SUNO often generate the final audio directly. You get an MP3. It sounds good, but it’s difficult to modify. MIDI is like the Python of the music world. And this is exactly where Ling-3.0-flash Ant Ling shines. It works like a high-speed execution engine in an AI workflow: ⚡ Low latency 💰 Cost-efficient 🔧 Stable tool calling It can transform complex plans into real outputs quickly. In this music creation workflow, it can independently handle: •Which instruments should play •Which notes should be combined •How rhythms should evolve •How different tracks should interact After importing into GarageBand, you can: ✅ Edit the melody ✅ Replace instruments ✅ Adjust tempo ✅ Re-arrange the composition ✅ Add your own creativity I was genuinely impressed by the result. Try it.
0:21

99% of iPhone users don’t know this: Their phone already has a free music production powerhouse hidden inside. It’s one of the treasures left behind from the Steve Jobs era. Millions of people own an iPhone, iPad, or MacBook — but have never truly opened it. I asked an AI Agent to create a completely new piece of music from scratch. The result surprised me. It wasn’t just generating audio. It could be edited. Sounds, channels, tracks — everything was adjustable. But I didn’t ask AI to generate an MP3. Instead, I asked it to create a: structured, editable, and extendable music project. The model had to understand: 🎹 Main melody 🎻 Harmony relationships 🥁 Rhythm design 🎸 Instrument arrangement 🎼 Multi-track structure The final output was MIDI, which was imported directly into GarageBand. And this reveals a key difference: Traditional AI music tools like SUNO often generate the final audio directly. You get an MP3. It sounds good, but it’s difficult to modify. MIDI is like the Python of the music world. And this is exactly where Ling-3.0-flash Ant Ling shines. It works like a high-speed execution engine in an AI workflow: ⚡ Low latency 💰 Cost-efficient 🔧 Stable tool calling It can transform complex plans into real outputs quickly. In this music creation workflow, it can independently handle: •Which instruments should play •Which notes should be combined •How rhythms should evolve •How different tracks should interact After importing into GarageBand, you can: ✅ Edit the melody ✅ Replace instruments ✅ Adjust tempo ✅ Re-arrange the composition ✅ Add your own creativity I was genuinely impressed by the result. Try it.

实践哥MinLi

139,763 görüntüleme • 1 ay önce

Stop waiting for a smarter model. The agent era starts the day execution costs hit the floor. Ling-3.0-flash quietly showed up on OpenRouter. 124B total params, 5.1B active. No launch event, no marketing push, it just appeared. Output quality matches some flagship models, roughly half the token cost of Claude, and a full commented code block lands the second you hit enter. Spent three days throwing every task I didn't want to do at it: ▫️ 30-page product doc into a structured table. Fewer field errors than when I do it by hand. ▫️ Bug fix spanning 5 files. It wrote the test cases too. ▫️ A 963-line single-file SaaS landing page in one shot. Glassmorphism, particle field, interactive workflow, all of it. I read that landing page line by line. Here's the honest part. Every constraint I wrote into the prompt, it shipped. Particle counts, devicePixelRatio cap, reduced-motion fallback. Not one missed. Anything that needed someone to actually look at the render, it had no idea. The five workflow nodes sit 70px apart, center to center. The circles are 72px wide. The last three pairs overlap. I moved them by hand. This isn't a model you hand strategy to. It's a tireless workhorse. The sharper your instructions, and the more of them a machine can check, the better it holds. Agents have been hyped for two years without landing. The blocker was never intelligence. One run just cost more than paying a person. My setup now: flagship plans, this one executes, and I keep a verification step in between. Tiering your models is the real edge in 2026. Still free right now. 256K context, tool calling on. Take the repetitive, structured, verifiable work off your plate and move it over for two days. Save the budget and your attention for what actually needs thinking. Stop using a sledgehammer to crack a nut. #AI #Agents #LLM
0:53

Stop waiting for a smarter model. The agent era starts the day execution costs hit the floor. Ling-3.0-flash quietly showed up on OpenRouter. 124B total params, 5.1B active. No launch event, no marketing push, it just appeared. Output quality matches some flagship models, roughly half the token cost of Claude, and a full commented code block lands the second you hit enter. Spent three days throwing every task I didn't want to do at it: ▫️ 30-page product doc into a structured table. Fewer field errors than when I do it by hand. ▫️ Bug fix spanning 5 files. It wrote the test cases too. ▫️ A 963-line single-file SaaS landing page in one shot. Glassmorphism, particle field, interactive workflow, all of it. I read that landing page line by line. Here's the honest part. Every constraint I wrote into the prompt, it shipped. Particle counts, devicePixelRatio cap, reduced-motion fallback. Not one missed. Anything that needed someone to actually look at the render, it had no idea. The five workflow nodes sit 70px apart, center to center. The circles are 72px wide. The last three pairs overlap. I moved them by hand. This isn't a model you hand strategy to. It's a tireless workhorse. The sharper your instructions, and the more of them a machine can check, the better it holds. Agents have been hyped for two years without landing. The blocker was never intelligence. One run just cost more than paying a person. My setup now: flagship plans, this one executes, and I keep a verification step in between. Tiering your models is the real edge in 2026. Still free right now. 256K context, tool calling on. Take the repetitive, structured, verifiable work off your plate and move it over for two days. Save the budget and your attention for what actually needs thinking. Stop using a sledgehammer to crack a nut. #AI #Agents #LLM

AYi

66,501 görüntüleme • 1 ay önce

New body-physics test for the best AI video tools: The newly released Grok Imagine 1.5, the king Seedance 2.0, Google’s “revolutionary super-duper” Gemini Omni Flash, and the old-timer Kling 3.0 Pro. This time I tested how each model handles realistic running motion, body movement, fabric physics, and natural secondary motion. And the result was much less obvious than I expected. Believe it or not, I can’t call Seedance the clear winner this time. Each model got several attempts. - Grok Imagine 1.5: The new version is finally available on the official Grok website, so I could properly test it. Honestly, I didn’t notice a massive improvement over the previous version. Still, the result was acceptable. It produced the most cartoonish image, and the woman runs as if she’s wearing heels, but the body physics were decent enough. It also understood the instructions quickly and followed them correctly. - Kling 3.0 Pro: The old man decided to test my patience. It repeatedly blocked a simple running scene as adult content, then misunderstood the instructions several times. The successful result has the most realistic lighting and frame rate, but the actual body physics look strange. It almost feels like loose foam padding is bouncing inside the leggings. There are also several visible artifacts and unnatural movements. - Gemini Omni Flash: As usual, it gave me that strange slow-motion, low-FPS look that Google models seem to love. But it didn’t censor anything, understood the instructions immediately, and produced a beautiful, realistic result. Surprisingly, this is the output I liked the most in this test. - Seedance 2.0: Seedance also blocked a couple of generations, just like Kling, but eventually produced a strong result. It delivered the most beautiful and visually appealing footage, but I honestly expected better physics. The video looks great, yet I can’t confidently call it the most physically accurate result. - My ranking: 1. Gemini Omni Flash — not perfect, but the best overall result for me 2. Seedance 2.0 — visually stunning, but I preferred Omni’s physics 3. Grok Imagine 1.5 — cartoonish look and strange running, but still acceptable 4. Kling 3.0 Pro — the longest wait, the strangest physics, and the most inconsistent result Do you agree with my ranking? #AIVideo
0:41

New body-physics test for the best AI video tools: The newly released Grok Imagine 1.5, the king Seedance 2.0, Google’s “revolutionary super-duper” Gemini Omni Flash, and the old-timer Kling 3.0 Pro. This time I tested how each model handles realistic running motion, body movement, fabric physics, and natural secondary motion. And the result was much less obvious than I expected. Believe it or not, I can’t call Seedance the clear winner this time. Each model got several attempts. - Grok Imagine 1.5: The new version is finally available on the official Grok website, so I could properly test it. Honestly, I didn’t notice a massive improvement over the previous version. Still, the result was acceptable. It produced the most cartoonish image, and the woman runs as if she’s wearing heels, but the body physics were decent enough. It also understood the instructions quickly and followed them correctly. - Kling 3.0 Pro: The old man decided to test my patience. It repeatedly blocked a simple running scene as adult content, then misunderstood the instructions several times. The successful result has the most realistic lighting and frame rate, but the actual body physics look strange. It almost feels like loose foam padding is bouncing inside the leggings. There are also several visible artifacts and unnatural movements. - Gemini Omni Flash: As usual, it gave me that strange slow-motion, low-FPS look that Google models seem to love. But it didn’t censor anything, understood the instructions immediately, and produced a beautiful, realistic result. Surprisingly, this is the output I liked the most in this test. - Seedance 2.0: Seedance also blocked a couple of generations, just like Kling, but eventually produced a strong result. It delivered the most beautiful and visually appealing footage, but I honestly expected better physics. The video looks great, yet I can’t confidently call it the most physically accurate result. - My ranking: 1. Gemini Omni Flash — not perfect, but the best overall result for me 2. Seedance 2.0 — visually stunning, but I preferred Omni’s physics 3. Grok Imagine 1.5 — cartoonish look and strange running, but still acceptable 4. Kling 3.0 Pro — the longest wait, the strangest physics, and the most inconsistent result Do you agree with my ranking? #AIVideo

Alpha Mom

155,583 görüntüleme • 2 ay önce

Only if education could be this interactive ❤️‍🔥 I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it. A 3D human anatomy application built with Three.js using GPT 5.6 Sol. It all started with a single design image that I created using GPT Image 2.0. I then used it to generate every 3D organ image, one by one. Next, I converted each of those images into 3D models using Tripo (and no, they didn't sponsor this 😄). After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models. Codex built the first version beautifully, but there was one big problem. Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps. After a few iterations, Codex optimized each model down to roughly 2–5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand. Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that. The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step. It genuinely felt like building something that could make learning anatomy much more engaging. The inspiration came from Dilum Sanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day." And I did it :D Live: Code:
0:43

Only if education could be this interactive ❤️‍🔥 I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it. A 3D human anatomy application built with Three.js using GPT 5.6 Sol. It all started with a single design image that I created using GPT Image 2.0. I then used it to generate every 3D organ image, one by one. Next, I converted each of those images into 3D models using Tripo (and no, they didn't sponsor this 😄). After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models. Codex built the first version beautifully, but there was one big problem. Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps. After a few iterations, Codex optimized each model down to roughly 2–5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand. Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that. The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step. It genuinely felt like building something that could make learning anatomy much more engaging. The inspiration came from Dilum Sanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day." And I did it :D Live: Code:

The Bugged Dev

2,083,607 görüntüleme • 1 ay önce

I plugged MiniMax (official) M3 into Claude Code in under 5 minutes and gave it a real task. most models need hand-holding every few steps. M3 ran 147 iterations on its own. what it actually did: → took a broken CUDA kernel → ran it for 24 hours, autonomously → pushed hardware efficiency from 7.6% to 71.3% → shipped a 9.4x speedup I didn't touch it once across that whole window. the rest of the spec sheet: → 1M token context window → native multimodal from day one → fully open weights pricing: → $20/month for 1.7B tokens → $50/month for 5.1B tokens → text, image, speech, and music all share one pool usually with this kind of capability the bill catches up fast. M3 keeps both lines low at the same time. that's the part that surprised me. and if this is what M3 does at launch, the full rollout is going to be one to watch. what would you build with 1M context? #MiniMax #MiniMaxM3 #ClaudeCode #LLM
0:25

I plugged MiniMax (official) M3 into Claude Code in under 5 minutes and gave it a real task. most models need hand-holding every few steps. M3 ran 147 iterations on its own. what it actually did: → took a broken CUDA kernel → ran it for 24 hours, autonomously → pushed hardware efficiency from 7.6% to 71.3% → shipped a 9.4x speedup I didn't touch it once across that whole window. the rest of the spec sheet: → 1M token context window → native multimodal from day one → fully open weights pricing: → $20/month for 1.7B tokens → $50/month for 5.1B tokens → text, image, speech, and music all share one pool usually with this kind of capability the bill catches up fast. M3 keeps both lines low at the same time. that's the part that surprised me. and if this is what M3 does at launch, the full rollout is going to be one to watch. what would you build with 1M context? #MiniMax #MiniMaxM3 #ClaudeCode #LLM

Nelly;

17,576 görüntüleme • 3 ay önce

I’ve never shared this before. But I wanted to share a small story about the biggest project I had taken once. The project was one of the largest we’ve ever worked on. A product built from scratch, valued close to a billion dollars. The whole team didn’t just work on it; we lived it. The energy, the pressure, the excitement… it was unlike anything we had experienced before. We were fully booked for the next 6 months on this one project. Enjoyed every moment of it though, through and through.
1:23

I’ve never shared this before. But I wanted to share a small story about the biggest project I had taken once. The project was one of the largest we’ve ever worked on. A product built from scratch, valued close to a billion dollars. The whole team didn’t just work on it; we lived it. The energy, the pressure, the excitement… it was unlike anything we had experienced before. We were fully booked for the next 6 months on this one project. Enjoyed every moment of it though, through and through.

Arafat

47,009 görüntüleme • 8 ay önce

After ClawdBot, the next big thing could be Qoder Quest. Most of the coding tools today need multiple iterations of testing, debugging, and prompts. An autonomous coding tool would be game changer. Qoder Quest is exactly this. It’s designed to take ownership of your projects. For sure, it is not a replacement for your mental model. Instead of line-by-line hand-holding, the workflow looks like this: – Describe a goal: tell it what you want to build – Approve the Spec: approve the technical spec first to align Quest with your mental model – Walk away: let the Quest run autonomously Attached is a video of me playing around with Quest for the first time. Get started with it: New users could have a 2-week pro trial with some credits to execute 5 Quest tasks. Appreciate the Qoder team for collaborating with me on this deep dive.
5:58

After ClawdBot, the next big thing could be Qoder Quest. Most of the coding tools today need multiple iterations of testing, debugging, and prompts. An autonomous coding tool would be game changer. Qoder Quest is exactly this. It’s designed to take ownership of your projects. For sure, it is not a replacement for your mental model. Instead of line-by-line hand-holding, the workflow looks like this: – Describe a goal: tell it what you want to build – Approve the Spec: approve the technical spec first to align Quest with your mental model – Walk away: let the Quest run autonomously Attached is a video of me playing around with Quest for the first time. Get started with it: New users could have a 2-week pro trial with some credits to execute 5 Quest tasks. Appreciate the Qoder team for collaborating with me on this deep dive.

Pratham

104,021 görüntüleme • 7 ay 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

39,719 görüntüleme • 2 ay önce

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.
0:22

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

122,548 görüntüleme • 2 ay önce

🧵1/3 I partnered with Kling to make a promo for their new 3.0 model. I came up with the concept, created it and delivered it all on my own in 3 days of early access, I wanted to make something that showed how Kling could be used to tell a diverse range of stories in a diverse range of styles. I've honestly been blown away be how incredible the model is and I haven't even scratched the surface of features like the new 3.0 OMNI model. For me Kling 2.6 was already best in class for most things but 3.0 sees massive improvements to video quality and detail (no need to add grain to mask imperfections) and prompt adherence. Also you can time your generations to be as long as 15 seconds and as short as 3, this is fantastic for pacing your scenes. Read on to find out more about the new Performance and Multi shot features!👇
1:26

🧵1/3 I partnered with Kling to make a promo for their new 3.0 model. I came up with the concept, created it and delivered it all on my own in 3 days of early access, I wanted to make something that showed how Kling could be used to tell a diverse range of stories in a diverse range of styles. I've honestly been blown away be how incredible the model is and I haven't even scratched the surface of features like the new 3.0 OMNI model. For me Kling 2.6 was already best in class for most things but 3.0 sees massive improvements to video quality and detail (no need to add grain to mask imperfections) and prompt adherence. Also you can time your generations to be as long as 15 seconds and as short as 3, this is fantastic for pacing your scenes. Read on to find out more about the new Performance and Multi shot features!👇

Uncanny Harry AI

29,194 görüntüleme • 6 ay önce

AN OPENCLAW AI AGENT JUST DESIGNED A 3D CHARACTER IN BLENDER AND SENT IT TO A 3D PRINTER. SHE DIDN'T TOUCH A SINGLE BUTTON. This is what running an OpenClaw AI agent on a Mac Mini actually looks like. She described what she wanted. The agent did everything else. Blender opened automatically. Character designed. Put in space. Animated with blinking eyes and stomping feet. Landing page built and live. Model sliced. File sent to 3D printer. Printer started moving. All from conversation. Zero code. Zero design skills. Zero manual work. Here's why this matters beyond the demo: Custom 3D printed figures sell for $30-$200 each on Etsy and at conventions. The people making serious money aren't artists. They're the ones who can produce custom designs fast. An AI agent that goes from description to printed figure autonomously is a business model not a toy. "I was just talking to the guy and he made it happen." Bookmark this. Full demo in the video below.
1:29

AN OPENCLAW AI AGENT JUST DESIGNED A 3D CHARACTER IN BLENDER AND SENT IT TO A 3D PRINTER. SHE DIDN'T TOUCH A SINGLE BUTTON. This is what running an OpenClaw AI agent on a Mac Mini actually looks like. She described what she wanted. The agent did everything else. Blender opened automatically. Character designed. Put in space. Animated with blinking eyes and stomping feet. Landing page built and live. Model sliced. File sent to 3D printer. Printer started moving. All from conversation. Zero code. Zero design skills. Zero manual work. Here's why this matters beyond the demo: Custom 3D printed figures sell for $30-$200 each on Etsy and at conventions. The people making serious money aren't artists. They're the ones who can produce custom designs fast. An AI agent that goes from description to printed figure autonomously is a business model not a toy. "I was just talking to the guy and he made it happen." Bookmark this. Full demo in the video below.

SCOTTY BEAM

17,209 görüntüleme • 2 ay önce

Claude Opus 5 just one-shotted this FPS. Less than 1 hour from prompt to playable demo. Every weapon, enemy, mechanic and environment was generated from scratch. Prompt below 👇 There is no prompt below, because the first section is exactly the kind of post I’m tired of seeing every time a new model drops. A flashy demo, “one-shot” in the caption, “built in under an hour”… anything to farm impressions while conveniently hiding the actual process. If it was really made from a single prompt, show the prompt. That’s what I do on this account. When I claim something is a one-prompt prototype built with GPT-5.6 Sol Ultra and Codex, I share the prompt publicly so anyone can verify it. AI is already making game prototyping incredible. We don’t need fake “one-shot” stories to prove it. Original footage:
0:36

Claude Opus 5 just one-shotted this FPS. Less than 1 hour from prompt to playable demo. Every weapon, enemy, mechanic and environment was generated from scratch. Prompt below 👇 There is no prompt below, because the first section is exactly the kind of post I’m tired of seeing every time a new model drops. A flashy demo, “one-shot” in the caption, “built in under an hour”… anything to farm impressions while conveniently hiding the actual process. If it was really made from a single prompt, show the prompt. That’s what I do on this account. When I claim something is a one-prompt prototype built with GPT-5.6 Sol Ultra and Codex, I share the prompt publicly so anyone can verify it. AI is already making game prototyping incredible. We don’t need fake “one-shot” stories to prove it. Original footage:

Givros

14,794 görüntüleme • 1 ay önce