Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

I built a J-Space explorer with several curated sessions. It shows all three regions described in Anthropic's paper on J-Space: sensory, workspace and motor. Model: Qwen 3.6 27B 4-bit

realWeZZard's profile picture

WeZZard

5,427 subscribers

38,567 görüntüleme • 3 ay önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

6 Yorum

WeZZard profil fotoğrafı
WeZZard3 ay önce

The explorer:

WeZZard profil fotoğrafı
WeZZard3 ay önce

Repo:

AlphaBuilder profil fotoğrafı
AlphaBuilder3 ay önce

强悍

Alejandro Rivero profil fotoğrafı
Alejandro Rivero3 ay önce

The funny thing with Qwen models is that some are pinned (embedder = unembedder), some fully unpinned, and some unpinned for fine tuning. That should have different properties in the lens.

克拉泽利克 profil fotoğrafı
克拉泽利克3 ay önce

请问这项目的意义与i前景

WeZZard profil fotoğrafı
WeZZard3 ay önce

提供一种可以大家可以亲身参与的 J-Space 体验方案 我觉得这样比单纯的文字理解、图片理解，又或者阅读新闻报道会好很多。

Benzer Videolar

Anthropic's new J-Space paper is fascinating. It describes an internal workspace where Claude keeps concepts in mind before they appear in its response. Inspired by the paper, I built a skill that lets Claude (and others) reveal their J-Space. Here's what it looks like.🧵
0:26

Anthropic's new J-Space paper is fascinating. It describes an internal workspace where Claude keeps concepts in mind before they appear in its response. Inspired by the paper, I built a skill that lets Claude (and others) reveal their J-Space. Here's what it looks like.🧵

Pietro Schirano

75,989 görüntüleme • 3 ay önce

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.
1:36

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.

BridgeMind

70,626 görüntüleme • 5 ay önce

Today we’re announcing our “ThinkingCap” efficient model series with a 2× thinking token reduction on average in Qwen 3.6 27B, with up to 10x faster generation on individual examples.
1:14

Today we’re announcing our “ThinkingCap” efficient model series with a 2× thinking token reduction on average in Qwen 3.6 27B, with up to 10x faster generation on individual examples.

Jaroslav Beck

51,640 görüntüleme • 3 ay önce

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.
0:46

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.

Mia

11,183 görüntüleme • 4 ay önce

I put Qwen 3.6 27B on a B200 for the fun of it. I told Fable to apply my past optimisation principles. Result? 1000 TPS Qwen 3.6 27B NVFP4 (550 TPS average long decode) I used the same principles that got me 250 TPS on 2x 3090s. Now I need to buy a DGX Station 🤪.
0:37

I put Qwen 3.6 27B on a B200 for the fun of it. I told Fable to apply my past optimisation principles. Result? 1000 TPS Qwen 3.6 27B NVFP4 (550 TPS average long decode) I used the same principles that got me 250 TPS on 2x 3090s. Now I need to buy a DGX Station 🤪.

Youssof Al Toukhi

46,527 görüntüleme • 2 ay önce

Cuebus and Unabandonware preserved a dialer app, featuring Ulala from Space Channel 5! It was preloaded on J-SH07, an early J-SKY keitai from 2001. This was likely intended to show off Mascot Capsule 3D graphics. The right video shows Ulala's model in the PVMicro model viewer.
0:30

Cuebus and Unabandonware preserved a dialer app, featuring Ulala from Space Channel 5! It was preloaded on J-SH07, an early J-SKY keitai from 2001. This was likely intended to show off Mascot Capsule 3D graphics. The right video shows Ulala's model in the PVMicro model viewer.

RockmanCosmo

13,902 görüntüleme • 2 yıl önce

Managed to get QWEN 3.6 27B running in Cursor with localhost (no Ngrok) at 120 - 140 TPS on 2x 3090s.
1:02

Managed to get QWEN 3.6 27B running in Cursor with localhost (no Ngrok) at 120 - 140 TPS on 2x 3090s.

Youssof Al Toukhi

21,221 görüntüleme • 5 ay önce

Grok 4.5 is INSANE for web dev. I built this scrolling space explorer in just a couple hours with Grok Build. Link below, try it out!
0:25

Grok 4.5 is INSANE for web dev. I built this scrolling space explorer in just a couple hours with Grok Build. Link below, try it out!

Anshu

49,806 görüntüleme • 3 ay önce

Orinth-1.0-35b vs Qwen-3.6-27b I've asked both to build a single html file of Tetris game. First here's the Orinth 35b I think it did a fine job. Every control works, the game looks fine visually. How did Qwen 3.6 27b did? See post #2
0:40

Orinth-1.0-35b vs Qwen-3.6-27b I've asked both to build a single html file of Tetris game. First here's the Orinth 35b I think it did a fine job. Every control works, the game looks fine visually. How did Qwen 3.6 27b did? See post #2

Mia

62,696 görüntüleme • 4 ay önce

Anthropic discovered J-space and it's a big deal. 🔸Where models do deep (invisible) thinking 🔸No lying in the J-space (alignment solution) 🔸We can modify the J-space to change AI's thoughts Full breakdown:
23:39

Anthropic discovered J-space and it's a big deal. 🔸Where models do deep (invisible) thinking 🔸No lying in the J-space (alignment solution) 🔸We can modify the J-space to change AI's thoughts Full breakdown:

Matthew Berman

48,862 görüntüleme • 3 ay önce

Vibe coding at 40,000 feet in the air at 75TPS+ on my MacBook with no WiFi. Qwen 3.6 27B on MTPLX V2 (coming soon!)
1:38

Vibe coding at 40,000 feet in the air at 75TPS+ on my MacBook with no WiFi. Qwen 3.6 27B on MTPLX V2 (coming soon!)

Youssof Al Toukhi

61,734 görüntüleme • 4 ay önce

Qwen 3.8 27b Pagoda test compared to 3.8 max and 3.6. BF16 results! Looks great!
0:22

Qwen 3.8 27b Pagoda test compared to 3.8 max and 3.6. BF16 results! Looks great!

Loktar 🇺🇸

36,732 görüntüleme • 2 ay önce

.President Donald J. Trump receives a briefing on the UAE's space program and its partnership with NASA
0:55

.President Donald J. Trump receives a briefing on the UAE's space program and its partnership with NASA

Rapid Response 47

261,164 görüntüleme • 1 yıl önce

QwQ-32B model from Qwen in VSCode... Got 20GB of free space? 😅 This is the latest reasoning model developed by Qwen In this video, I walk you through how to download and install it in VSCode using ollama, completely free and private 👇
0:29

QwQ-32B model from Qwen in VSCode... Got 20GB of free space? 😅 This is the latest reasoning model developed by Qwen In this video, I walk you through how to download and install it in VSCode using ollama, completely free and private 👇

Daniel San

29,169 görüntüleme • 1 yıl önce

the different flavors of specdec, and why I'm trying produce a Qwen-3.6-27b EAGLE-3 drafter for ya'll
0:39

the different flavors of specdec, and why I'm trying produce a Qwen-3.6-27b EAGLE-3 drafter for ya'll

Eric

18,198 görüntüleme • 5 ay önce

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!
4:28

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

26,243 görüntüleme • 2 ay önce

Donald J. Trump NASA and Space Force are part of National DigiFoundry which is built on Constellation² $DAG America's Blockchain 🇺🇸
1:08

Donald J. Trump NASA and Space Force are part of National DigiFoundry which is built on Constellation² $DAG America's Blockchain 🇺🇸

Dagnum²

16,020 görüntüleme • 1 yıl önce

This earns Donald J. Trump a space on Mount Rushmore.
6:36

This earns Donald J. Trump a space on Mount Rushmore.

Robert F. Kennedy Jr

8,546,151 görüntüleme • 2 yıl önce

NVIDIA CEO JENSEN HUANG UNVEILED THE RTX 3090 AND THE USED VERSION ON EBAY NOW KILLS A $400/MONTH CLAUDE CODE AND OPENAI BILL the rtx 3090 has 24gb of vram, the same as a new rtx 4090 that costs $2,000. for local ai inference vram matters more than anything else and the 3090 sells for $650-800 used it runs qwen 3.6 27b comfortably, deepseek r1 14b at 60+ tokens per second and mistral 7b for fast automation. 16gb of qwen 3.6 fits with 8gb of headroom for long context alibaba's qwen 3.6 27b beats claude 4.5 opus on realworldqa vision 84.1 vs 77.0 and on ifbench instructions 76.5 vs 58.0. a free open weight model out-benchmarks anthropic's flagship a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and a used 3090 pays itself off in 3.5 months install ollama, pull qwen 3.6 27b, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below
0:33

NVIDIA CEO JENSEN HUANG UNVEILED THE RTX 3090 AND THE USED VERSION ON EBAY NOW KILLS A $400/MONTH CLAUDE CODE AND OPENAI BILL the rtx 3090 has 24gb of vram, the same as a new rtx 4090 that costs $2,000. for local ai inference vram matters more than anything else and the 3090 sells for $650-800 used it runs qwen 3.6 27b comfortably, deepseek r1 14b at 60+ tokens per second and mistral 7b for fast automation. 16gb of qwen 3.6 fits with 8gb of headroom for long context alibaba's qwen 3.6 27b beats claude 4.5 opus on realworldqa vision 84.1 vs 77.0 and on ifbench instructions 76.5 vs 58.0. a free open weight model out-benchmarks anthropic's flagship a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and a used 3090 pays itself off in 3.5 months install ollama, pull qwen 3.6 27b, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

starmex

86,831 görüntüleme • 4 ay önce

100 TPS on 16 concurrent processes running a modified version of Cursor using QWEN 3.6 27B to build a 3D Bowmasters game.
0:58

100 TPS on 16 concurrent processes running a modified version of Cursor using QWEN 3.6 27B to build a 3D Bowmasters game.

Youssof Altoukhi

11,243 görüntüleme • 5 ay önce