正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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

WeZZard

5,427 subscribers

38,567 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

6 条评论

WeZZard 的头像

WeZZard3 个月前

The explorer:

WeZZard 的头像

WeZZard3 个月前

Repo:

AlphaBuilder 的头像

AlphaBuilder3 个月前

强悍

Alejandro Rivero 的头像

Alejandro Rivero3 个月前

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.

克拉泽利克的头像

克拉泽利克3 个月前

请问这项目的意义与i前景

WeZZard 的头像

WeZZard3 个月前

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。

相关视频

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.🧵

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 次观看 • 3 个月前

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.

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 次观看 • 5 个月前

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.

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 次观看 • 3 个月前

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.

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 次观看 • 4 个月前

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 🤪.

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 次观看 • 2 个月前

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.

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 次观看 • 2 年前

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

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 次观看 • 5 个月前

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!

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 次观看 • 3 个月前

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

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 次观看 • 4 个月前

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:

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 次观看 • 3 个月前

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!)

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 次观看 • 4 个月前

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

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

Loktar 🇺🇸

36,732 次观看 • 2 个月前

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

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

Rapid Response 47

261,164 次观看 • 1 年前

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 👇

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 次观看 • 1 年前

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

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 次观看 • 5 个月前

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

26,243 次观看 • 2 个月前

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

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

Dagnum²

16,020 次观看 • 1 年前

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

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

Robert F. Kennedy Jr

8,546,236 次观看 • 2 年前

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

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 次观看 • 4 个月前

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

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 次观看 • 5 个月前