Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Here's a comparison i never thought i would make Qwen-3.8-27b vs Gemini-3.7-flash Yes, you read it right! I don't know what to say, this is soo damn impressive. the difference is hugeee🤯 Take a look at this result 😍 (watch it in highest quality) Same prompt, both one shot... show more

AJ

2,428 subscribers

168,072 просмотров • 3 дней назад •via X (Twitter)

Наука и технологии Юмор Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Kyle Hessling

24,917 просмотров • 3 дней назад

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!

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

10,669 просмотров • 9 дней назад

This happens all the time! This is why I feel like I'm not worth myself! This is why I feel like I cant grow! This is twitch actively nerfing my account every time I go live! The audience didn't leave they were still in the chat! When I asked twitch for help, I got an automated incomplete response that said "everything looks" . I am so tired of fighting this and have pleaded with twitch, Daniel Clancy and have told the VP FACE TO FACE about this issue and still nothing has been done! Why? I'm small potatoes no one cares and no one will even put an iota of time into solving this issue! This has been a constant every day for over 2 years and I cannot express how defeated I absolutely feel every time I press start to immediately have my audience ignored by twitch. I know some of you are going to say its not all about the numbers and if you enjoy it, it shouldn't matter. Unfortunately the ultimate truth is we are heavily judged on our CPM by everyone, potential partners, sponsors, collaborative opportunities and even by twitch themselves. So yes, it does matter. It matters a lot and worst part is no one, will take this issue seriously! I have literally 120 days of information from twitches 9th longest subathon (unrecognized of course as again small potatoes) that would absolutely show this being a consistent issue. I don't know what to do, I am at wits end here and I every time I see this happen to me I just want to curl up into a ball and let the world wash over me. I need help, i need someone to look at this, because I have dedicated my life to entertaining individuals and I do this full time, I dedicate 8 hours a day every day for the past 2 years to this company and the only thing I get is ignored. I know this is a lot and it looks like just some random person complaining, but I need some way to get this in the right hands and not the automated jarble that I've been getting. Its even been acknowledged in the past by a tech for twitch that something might be up. Again, I know I'm not big but were all working under the same logo and should all be taken care of equally! Twitch

Frosted Fricks 💣🐦‍⬛

21,589 просмотров • 1 год назад

Seedance 2.0 vs Gemini Omni, tested under the same conditions 👀 I was working on a new storyboard. After generating it with Seedance 2.0, I gave the exact same prompt + storyboard reference + character reference to Gemini Omni as well. Result: Gemini Omni surprised me with style quality and got closer than I expected in prompt adherence. But Seedance still feels ahead for storyboard execution, motion energy, camera language and environmental interaction. Gemini looks good. Seedance feels directed. You can see them in the video and the storyboard sheet is shown at the end. Which one do you think is more useful for this kind of work?

Seedance 2.0 vs Gemini Omni, tested under the same conditions 👀 I was working on a new storyboard. After generating it with Seedance 2.0, I gave the exact same prompt + storyboard reference + character reference to Gemini Omni as well. Result: Gemini Omni surprised me with style quality and got closer than I expected in prompt adherence. But Seedance still feels ahead for storyboard execution, motion energy, camera language and environmental interaction. Gemini looks good. Seedance feels directed. You can see them in the video and the storyboard sheet is shown at the end. Which one do you think is more useful for this kind of work?

Kōda

35,800 просмотров • 3 месяцев назад

hey here is the final result of octopus invaders on nvidia's flagship at full precision. nemotron super 120B on 2x H200 NVL. BF16 unquantized. 287GB of VRAM. hermes agent as the harness. 60 tok/s. first try it autonomously coded for 6 minutes straight. created 11 files. correct project structure. correct load order. started the server. i opened the browser and the result was a blank screen. i did not give up. second try i gave it a precise list of bugs and things to fix. it went back in for another 3 minutes. patched the code. served it again. still blank. so i did what any sane person would do. third try i just said the screen is blank, test it and fix it yourself. and this is where nemotron showed what it actually is. it became a debugger. you can see it in the video. realtime CSS test squares, red screen flashes, hermes agent browser tools, inspecting its own output. it built the parallax background with planets and comets. it rendered a rocket ship that tracks your mouse with fire and bullet physics. the aesthetic is real. but no enemies spawn. no collision. not playable. what surprised me is qwen 27B one shotted this exact game on a single RTX 3090 at Q4 quant. and here is nvidia's flagship at full precision on enterprise hardware needing 3 tries and still not getting there. that makes my hope high for the undisputed qwen 122B which is about to face the same test next. same hardware. same prompt and same harness. lets see if it one shots or not. full session in the video. no cuts. 5x speed.

hey here is the final result of octopus invaders on nvidia's flagship at full precision. nemotron super 120B on 2x H200 NVL. BF16 unquantized. 287GB of VRAM. hermes agent as the harness. 60 tok/s. first try it autonomously coded for 6 minutes straight. created 11 files. correct project structure. correct load order. started the server. i opened the browser and the result was a blank screen. i did not give up. second try i gave it a precise list of bugs and things to fix. it went back in for another 3 minutes. patched the code. served it again. still blank. so i did what any sane person would do. third try i just said the screen is blank, test it and fix it yourself. and this is where nemotron showed what it actually is. it became a debugger. you can see it in the video. realtime CSS test squares, red screen flashes, hermes agent browser tools, inspecting its own output. it built the parallax background with planets and comets. it rendered a rocket ship that tracks your mouse with fire and bullet physics. the aesthetic is real. but no enemies spawn. no collision. not playable. what surprised me is qwen 27B one shotted this exact game on a single RTX 3090 at Q4 quant. and here is nvidia's flagship at full precision on enterprise hardware needing 3 tries and still not getting there. that makes my hope high for the undisputed qwen 122B which is about to face the same test next. same hardware. same prompt and same harness. lets see if it one shots or not. full session in the video. no cuts. 5x speed.

Sudo su

11,011 просмотров • 4 месяцев назад

🚨Gemini 3.0 Pro - One shotted i asked it for retro nintendo sims with games and no external assets used , it takes 1 min to output no other model have this level of consistency Prompt and Proof of one shot in Thread and this is not the best shot , there is one more cooking with slightly different prompt

🚨Gemini 3.0 Pro - One shotted i asked it for retro nintendo sims with games and no external assets used , it takes 1 min to output no other model have this level of consistency Prompt and Proof of one shot in Thread and this is not the best shot , there is one more cooking with slightly different prompt

Chetaslua

184,281 просмотров • 10 месяцев назад

DeepSeek v4 Flash (0731) vs Kimi K3 (10x more weights) i gave both the exact same prompt, in the exact same harness: one-shot a luxury product landing page ($10,000 "ARC-01" concept object). results in the video. my take: Kimi K3: wins on polish. Better typography hierarchy, more confident use of negative space, and the hero product shot integration is genuinely beautiful DeepSeek v4 Flash: very close. The structure is right, the copy is right, the layout logic is right. It loses on finish, not on fundamentals. a 10x smaller model getting ~90% of the way there. a year ago this gap would have been embarrassing. mind you it cost less than $0.10 for 6 build iterations and 8 QA passes. small models aren't "good for their size" anymore. they're just good.

DeepSeek v4 Flash (0731) vs Kimi K3 (10x more weights) i gave both the exact same prompt, in the exact same harness: one-shot a luxury product landing page ($10,000 "ARC-01" concept object). results in the video. my take: Kimi K3: wins on polish. Better typography hierarchy, more confident use of negative space, and the hero product shot integration is genuinely beautiful DeepSeek v4 Flash: very close. The structure is right, the copy is right, the layout logic is right. It loses on finish, not on fundamentals. a 10x smaller model getting ~90% of the way there. a year ago this gap would have been embarrassing. mind you it cost less than $0.10 for 6 build iterations and 8 QA passes. small models aren't "good for their size" anymore. they're just good.

filipe

26,175 просмотров • 17 дней назад

Caitlin Clark on how she gets covered by the media: "I think there's just like a false characterization of who I am sometimes. And I get it like as a reporter or as a blogger, like you can write an opinion piece and that's your job and whatever. But at the same time, like you don't know me. Like we've never had a conversation. I get people have a job to do. But at the same time, like don't make accusations about my character and who I am when you don't know me. I understand this is your job and this is your profession, and this is what you get to do. And basketball is my profession, what I get to do. And the reason I play it is when I step in between the lines, I love it. And that's what's so fun about it for me is like, I get to compete. This was always my dream. And nobody should ever try to take that away from me"

Caitlin Clark on how she gets covered by the media: "I think there's just like a false characterization of who I am sometimes. And I get it like as a reporter or as a blogger, like you can write an opinion piece and that's your job and whatever. But at the same time, like you don't know me. Like we've never had a conversation. I get people have a job to do. But at the same time, like don't make accusations about my character and who I am when you don't know me. I understand this is your job and this is your profession, and this is what you get to do. And basketball is my profession, what I get to do. And the reason I play it is when I step in between the lines, I love it. And that's what's so fun about it for me is like, I get to compete. This was always my dream. And nobody should ever try to take that away from me"

Oh No He Didn't

260,949 просмотров • 24 дней назад

Let's talk Chiefs run game and RPOs, volume up on this. There's a lot I don't discuss TBF, but this is about what the lack of a consistent run game allows a defense to do and what it takes away from the players. This is objectively a great play/result! But is it best for this O?

Let's talk Chiefs run game and RPOs, volume up on this. There's a lot I don't discuss TBF, but this is about what the lack of a consistent run game allows a defense to do and what it takes away from the players. This is objectively a great play/result! But is it best for this O?

Mitchell Schwartz

51,594 просмотров • 9 месяцев назад

0xSero helped me setup local models properly and I uh, had no idea these things had gotten this good Are they frontier level? No, but considering this is running on just my 5090 it's remarkably capable First tests on a couple of programming tasks and the qwen 3.6-27b model with no reasoning feels about on par with something like sonnet 4-ish, probably better it's really impressive But also setting up local models isn't easy, I don't know nearly enough to talk much about it yet other than you need to know what you're doing to have a good experience. The out of the box stuff is not nearly as good as setting it up correctly

0xSero helped me setup local models properly and I uh, had no idea these things had gotten this good Are they frontier level? No, but considering this is running on just my 5090 it's remarkably capable First tests on a couple of programming tasks and the qwen 3.6-27b model with no reasoning feels about on par with something like sonnet 4-ish, probably better it's really impressive But also setting up local models isn't easy, I don't know nearly enough to talk much about it yet other than you need to know what you're doing to have a good experience. The out of the box stuff is not nearly as good as setting it up correctly

Ben Davis

14,490 просмотров • 3 месяцев назад

Does anyone know what this is? I came across it and couldn’t figure it out, it looks unusual and kind of interesting at the same time. Have you ever seen something like this before, or do you have any idea what it could be?

Does anyone know what this is? I came across it and couldn’t figure it out, it looks unusual and kind of interesting at the same time. Have you ever seen something like this before, or do you have any idea what it could be?

Dr. CZ

1,869,333 просмотров • 5 месяцев назад

Gemini 3.5 Pro vs Grok 4.6 Please read entire post before coming to conclusion :) Both are present in arena first of all let me clear i really want that google cook great comeback but this model is disaster it make stuff that you didnot asked for , have crappy ui guys at this point we have grok with better ui compared to gemini > gemini was good in webdev now its bad > gemini 2.5 DT was good in 3d now its bad > gemini was less restrictive and prompt following in 2.5 pro was so good , now its corporate slop with template , at this time you will feel that there is template for coding , writing and researching all sucks I will write a long review if you guys want that , this is first time i am writing long tweet , i will now follow this for every big release

Gemini 3.5 Pro vs Grok 4.6 Please read entire post before coming to conclusion :) Both are present in arena first of all let me clear i really want that google cook great comeback but this model is disaster it make stuff that you didnot asked for , have crappy ui guys at this point we have grok with better ui compared to gemini > gemini was good in webdev now its bad > gemini 2.5 DT was good in 3d now its bad > gemini was less restrictive and prompt following in 2.5 pro was so good , now its corporate slop with template , at this time you will feel that there is template for coding , writing and researching all sucks I will write a long review if you guys want that , this is first time i am writing long tweet , i will now follow this for every big release

Chetaslua

38,866 просмотров • 11 дней назад

One UI 8's latest version, ZYES, is the smoothest version I've ever experienced, smoother than all previous versions of One UI 7 and One UI 8. I can confirm that it has optimized the App startup animation again, making it more natural, smoother, and non-linear. Please watch the video I recorded. And the most important thing is that ZYES responds too fast. Watch my video, when I click the icons of One UI 8 and One UI 7 at the same time, you can see that the response speed of ZYES on the left is much faster. You know, One UI 7 already performed very well, and One UI 8 is obviously better. This shocked me, and I hope Samsung will continue to maintain it. Of course, some people will have some problems with this version. I think this may be because the cumulative number of installations is too many. I suggest that friends who have problems go back to the ZYDA version of One UI 7, and then directly install YDA→YEQ, and then install YEQ→YER and YER→YES in sequence. This is what I did, and I haven't found any bugs so far. You can also try this.

One UI 8's latest version, ZYES, is the smoothest version I've ever experienced, smoother than all previous versions of One UI 7 and One UI 8. I can confirm that it has optimized the App startup animation again, making it more natural, smoother, and non-linear. Please watch the video I recorded. And the most important thing is that ZYES responds too fast. Watch my video, when I click the icons of One UI 8 and One UI 7 at the same time, you can see that the response speed of ZYES on the left is much faster. You know, One UI 7 already performed very well, and One UI 8 is obviously better. This shocked me, and I hope Samsung will continue to maintain it. Of course, some people will have some problems with this version. I think this may be because the cumulative number of installations is too many. I suggest that friends who have problems go back to the ZYDA version of One UI 7, and then directly install YDA→YEQ, and then install YEQ→YER and YER→YES in sequence. This is what I did, and I haven't found any bugs so far. You can also try this.

PhoneArt

151,005 просмотров • 1 год назад

hey if you're thinking about running qwopus (the claude opus distilled qwen 3.5 27B) as a coding agent, this might save you a few hours. i tested both the base and the distilled version on the same hardware. single RTX 3090. same prompt. same context. same everything. the only variable was the model weights. base qwen 3.5 27B built octopus invaders in 13 minutes. 1,827 lines across 11 files. zero steering. one scope bug that took 2 lines to fix. game ran. qwopus couldn't finish the same task. enemies overlapping on screen. bullets not firing. controls worked but the game was broken. i had to steer it multiple times and it still didn't produce a playable result. both run at 35 tok/s. both use thinking mode. the distilled version actually has better jinja compatibility and doesn't stall midtask like base does on claude code. for conversation and reasoning it feels sharper. but for multifile autonomous coding where the model needs to coordinate 10+ files without losing track, base wins and it's not close. distillation compresses reasoning patterns but seems to lose precision on complex coordination. the model "thinks" well but can't hold the full picture across files the way base can. tested on opencode (base) and claude code (both). next up is hermes agent framework on base. same hardware. same prompt. comparing agents now, not just models. video below. first half is the distilled model's broken game. second half is what base built on the same 3090. judge for yourself.

hey if you're thinking about running qwopus (the claude opus distilled qwen 3.5 27B) as a coding agent, this might save you a few hours. i tested both the base and the distilled version on the same hardware. single RTX 3090. same prompt. same context. same everything. the only variable was the model weights. base qwen 3.5 27B built octopus invaders in 13 minutes. 1,827 lines across 11 files. zero steering. one scope bug that took 2 lines to fix. game ran. qwopus couldn't finish the same task. enemies overlapping on screen. bullets not firing. controls worked but the game was broken. i had to steer it multiple times and it still didn't produce a playable result. both run at 35 tok/s. both use thinking mode. the distilled version actually has better jinja compatibility and doesn't stall midtask like base does on claude code. for conversation and reasoning it feels sharper. but for multifile autonomous coding where the model needs to coordinate 10+ files without losing track, base wins and it's not close. distillation compresses reasoning patterns but seems to lose precision on complex coordination. the model "thinks" well but can't hold the full picture across files the way base can. tested on opencode (base) and claude code (both). next up is hermes agent framework on base. same hardware. same prompt. comparing agents now, not just models. video below. first half is the distilled model's broken game. second half is what base built on the same 3090. judge for yourself.

Sudo su

45,052 просмотров • 5 месяцев назад

We've tested the Qwen 3.8 Max preview and it absolutely rocks! Each scene is built in one shot, a single Three.js file with nothing else added: • Odysseus' war galley riding the waves • Trojan horse • Greek war helmet Qwen managed to execute the task faster than the other models, while output quality is relatively the same across all of them. If the pricing stays close to Alibaba's previous flagships, we'll get one of the best speed/quality ratios on the market — perfect for running agents at scale. Soon live on AI/ML API.

We've tested the Qwen 3.8 Max preview and it absolutely rocks! Each scene is built in one shot, a single Three.js file with nothing else added: • Odysseus' war galley riding the waves • Trojan horse • Greek war helmet Qwen managed to execute the task faster than the other models, while output quality is relatively the same across all of them. If the pricing stays close to Alibaba's previous flagships, we'll get one of the best speed/quality ratios on the market — perfect for running agents at scale. Soon live on AI/ML API.

AI/ML API

132,425 просмотров • 25 дней назад

🥊 Time for a new fight Qwen3.5 397B A17B vs Qwen3.6 27B 🌸 "Cherry Blossom" (↓ prompt below) Using OpenRouter for 397B Running 27B locally on a single RTX 5080 Wow! 🤯 I'm sure this one is going to divide opinions. 397B feels cinematic with the flare and shadows it added, while 27B is just beautiful; it has a completely different color palette and the leaves are falling from the branches as asked. It's really tough to decide which model is the best. I was about to call it a tie, but then I remembered that 397B needs 180GB VRAM to run locally 😅 Don't get me wrong the model is amazing, but right now the VRAM it requires doesn't feel justified. It's simply not 10× better than 27B. We'll have to dig deeper with more prompts to be sure, let's see what each one has in store for us. What do you think?

🥊 Time for a new fight Qwen3.5 397B A17B vs Qwen3.6 27B 🌸 "Cherry Blossom" (↓ prompt below) Using OpenRouter for 397B Running 27B locally on a single RTX 5080 Wow! 🤯 I'm sure this one is going to divide opinions. 397B feels cinematic with the flare and shadows it added, while 27B is just beautiful; it has a completely different color palette and the leaves are falling from the branches as asked. It's really tough to decide which model is the best. I was about to call it a tie, but then I remembered that 397B needs 180GB VRAM to run locally 😅 Don't get me wrong the model is amazing, but right now the VRAM it requires doesn't feel justified. It's simply not 10× better than 27B. We'll have to dig deeper with more prompts to be sure, let's see what each one has in store for us. What do you think?

left curve dev

21,224 просмотров • 3 месяцев назад

🎥| "I want to take this opportunity to, yes, thank you all, for the fifteenth time, and this won't be the last time tonight. But listen, I feel so lucky and grateful to be able to do what I do, but obviously, I couldn't do it without the trust you give me. I'm out of breath and I haven't even started singing yet. Just give me a second. I know you're going to react to this, but listen, I don't consider myself the best singer in the world, I don't consider myself the best artist in the world. I don't judge myself as the best performer in the world. Just don't. Just don't. But I think what all this shows is that I'm from a small town in Doncaster, right? Where we don't usually get opportunities like this. And when I have all of you, I feel like I can do anything, absolutely anything. And on nights like this, when you look around and see what we've created together, it's incredible. I see you trying to gain. It's above the waist. It doesn't count. [interacting with a fan] Yes, I just want to say that this is one of those really, really special moments. I feel so proud of what we've created together. And you should feel proud of yourselves too!" Louis Tomlinson on stage at #HDWGHWTBologna

🎥| "I want to take this opportunity to, yes, thank you all, for the fifteenth time, and this won't be the last time tonight. But listen, I feel so lucky and grateful to be able to do what I do, but obviously, I couldn't do it without the trust you give me. I'm out of breath and I haven't even started singing yet. Just give me a second. I know you're going to react to this, but listen, I don't consider myself the best singer in the world, I don't consider myself the best artist in the world. I don't judge myself as the best performer in the world. Just don't. Just don't. But I think what all this shows is that I'm from a small town in Doncaster, right? Where we don't usually get opportunities like this. And when I have all of you, I feel like I can do anything, absolutely anything. And on nights like this, when you look around and see what we've created together, it's incredible. I see you trying to gain. It's above the waist. It doesn't count. [interacting with a fan] Yes, I just want to say that this is one of those really, really special moments. I feel so proud of what we've created together. And you should feel proud of yourselves too!" Louis Tomlinson on stage at #HDWGHWTBologna

World Tomlinson

25,447 просмотров • 4 месяцев назад

been playing with hermes agent paired with qwen 3.5 dense 27B on my single 3090 since last night. there is something about this harness that caught me and i think i know what it is. i've now run five qwen configs on consumer hardware: 35B MoE (3B active) -- 112 tok/s flat across 262K context, 1x 3090 27B dense -- 35 tok/s, zero degradation across the same range, 1x 3090 qwopus 27B (opus distilled) -- 35.7 tok/s, same architecture, different brain 80B coder -- 46 tok/s on 2x 3090s, oneshotted a 564 line particle sim 80B coder -- 1.3 tok/s on 1x 3090, bleeding through RAM because it didn't fit but it still ran with same benchmarks. same prompts. same quant where possible. every config is documented. i know these models. and hermes agent is the first harness that feels like it respects that work. tool calls show inline with execution time. nvidia-smi 0.2s. write_file 0.7s. you see exactly what the agent is doing and how long each step takes. no mystery. no black box. no tool call failures so far and i've been pushing it. most agent frameworks feel like you're watching a spinner and hoping. hermes shows the work. that transparency changes how you trust the output. once you use it you see the UX decisions are not accidental. Teknium 🪽 and the nous team built this like engineers who actually use their own tools. 80 skills. 29 tools. persistent memory. context compression. runs clean on a single consumer GPU.

been playing with hermes agent paired with qwen 3.5 dense 27B on my single 3090 since last night. there is something about this harness that caught me and i think i know what it is. i've now run five qwen configs on consumer hardware: 35B MoE (3B active) -- 112 tok/s flat across 262K context, 1x 3090 27B dense -- 35 tok/s, zero degradation across the same range, 1x 3090 qwopus 27B (opus distilled) -- 35.7 tok/s, same architecture, different brain 80B coder -- 46 tok/s on 2x 3090s, oneshotted a 564 line particle sim 80B coder -- 1.3 tok/s on 1x 3090, bleeding through RAM because it didn't fit but it still ran with same benchmarks. same prompts. same quant where possible. every config is documented. i know these models. and hermes agent is the first harness that feels like it respects that work. tool calls show inline with execution time. nvidia-smi 0.2s. write_file 0.7s. you see exactly what the agent is doing and how long each step takes. no mystery. no black box. no tool call failures so far and i've been pushing it. most agent frameworks feel like you're watching a spinner and hoping. hermes shows the work. that transparency changes how you trust the output. once you use it you see the UX decisions are not accidental. Teknium 🪽 and the nous team built this like engineers who actually use their own tools. 80 skills. 29 tools. persistent memory. context compression. runs clean on a single consumer GPU.

Sudo su

100,259 просмотров • 5 месяцев назад

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.

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

39,574 просмотров • 2 месяцев назад

I miss mad tv. It was on at the same time Saturday Night Live was. I remember not finding SNL funny at all so I turned this on and it outperformed it every week. This is just one example of the hilarity. 🤣🤣🤣

I miss mad tv. It was on at the same time Saturday Night Live was. I remember not finding SNL funny at all so I turned this on and it outperformed it every week. This is just one example of the hilarity. 🤣🤣🤣

Johnny B. Good

27,534 просмотров • 3 месяцев назад