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

2,941 subscribers

12,889 次观看 • 10 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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

70,325 次观看 • 1 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

13,854 次观看 • 1 年前

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

48,685 次观看 • 9 天前

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

86,410 次观看 • 1 个月前

You can now run Qwen 3.6 27B on <10GB of memory and retain 90% of the intelligence. Today, PrismML dropped Bonsai 27B - which takes their unique compression approach they have already successfully applied to Qwen3.6 8B and Flux2-Klein and applied it to a properly smart model. Here is it using an entire computer for deep research. Long horizon agentic calls already are strong with Qwen3.6 27B and they still are here - just on 10x less memory.

You can now run Qwen 3.6 27B on <10GB of memory and retain 90% of the intelligence. Today, PrismML dropped Bonsai 27B - which takes their unique compression approach they have already successfully applied to Qwen3.6 8B and Flux2-Klein and applied it to a properly smart model. Here is it using an entire computer for deep research. Long horizon agentic calls already are strong with Qwen3.6 27B and they still are here - just on 10x less memory.

Tim Carambat

61,265 次观看 • 4 天前

A DEVELOPER ASKED LOCAL AI TO SPIN UP 64 AGENTS IN PARALLEL. IT RAN FOR 8 HOURS WITHOUT ASKING PERMISSION AND WITHOUT A SINGLE API CALL. Gemma 4 refused. Qwen 3.6 said nothing and started working. Zero bills. The model didn't negotiate, it just built.

A DEVELOPER ASKED LOCAL AI TO SPIN UP 64 AGENTS IN PARALLEL. IT RAN FOR 8 HOURS WITHOUT ASKING PERMISSION AND WITHOUT A SINGLE API CALL. Gemma 4 refused. Qwen 3.6 said nothing and started working. Zero bills. The model didn't negotiate, it just built.

0xMarioNawfal

61,845 次观看 • 2 个月前

🇺🇸 LAUREN SANCHEZ: I’M TAKING AN ALL-WOMEN CREW OF EXPLORERS TO SPACE "We’re going on a Blue Origin flight with an incredible group of women—all explorers. Jeff once called me an explorer, and it changed how I saw myself. These women, like Magellan or Cousteau, will see space and return to share how it transforms them." Source: USA Today

🇺🇸 LAUREN SANCHEZ: I’M TAKING AN ALL-WOMEN CREW OF EXPLORERS TO SPACE "We’re going on a Blue Origin flight with an incredible group of women—all explorers. Jeff once called me an explorer, and it changed how I saw myself. These women, like Magellan or Cousteau, will see space and return to share how it transforms them." Source: USA Today

Mario Nawfal

279,129 次观看 • 1 年前

Hey girl , space girl Modern alienne you are Tripped on a needle and found you a motor man Hes got a space suit, a rocket to the space coup Drift it in gear and Out through the stratosphere! Hes gonna change you Try to re create you Hes reptilian - I dont think you understandddddddd

Hey girl , space girl Modern alienne you are Tripped on a needle and found you a motor man Hes got a space suit, a rocket to the space coup Drift it in gear and Out through the stratosphere! Hes gonna change you Try to re create you Hes reptilian - I dont think you understandddddddd

AZEALIA BANKS

46,013 次观看 • 2 个月前

THIS ENGINEER RUNS CLAUDE CODE WITHOUT PAYING ANTHROPIC A SINGLE DOLLAR RTX 5090 under the desk, Qwen 3.5 35B, 140 tokens per second Claude Code pointed at localhost instead of Anthropic’s servers override two environment variables and your API bill drops to zero he built a full-stack Next.js app from scratch to prove it works then showed every bug and limitation other YouTubers hide same setup I run with two GPUs and Qwen 3.6 27B full breakdown ↓

THIS ENGINEER RUNS CLAUDE CODE WITHOUT PAYING ANTHROPIC A SINGLE DOLLAR RTX 5090 under the desk, Qwen 3.5 35B, 140 tokens per second Claude Code pointed at localhost instead of Anthropic’s servers override two environment variables and your API bill drops to zero he built a full-stack Next.js app from scratch to prove it works then showed every bug and limitation other YouTubers hide same setup I run with two GPUs and Qwen 3.6 27B full breakdown ↓

leopardracer

29,756 次观看 • 2 个月前

So, Stability AI has this new experimental imageTo3D model, and I just painted a moon buggy in SageBrush, dropped it into their Huggingface space, converted it in Reality Converter, and air dropped it onto the moon – all on #AppleVisionPro 🤯

So, Stability AI has this new experimental imageTo3D model, and I just painted a moon buggy in SageBrush, dropped it into their Huggingface space, converted it in Reality Converter, and air dropped it onto the moon – all on #AppleVisionPro 🤯

Gregory Wieber

63,837 次观看 • 2 年前

Yesterday we found out Qwen3.5-27B (dense) beats both the 35B and 122B MoE variants at UI replication from screenshots. Today's question: what about Jackrong's Qwen3.5-27B-Claude-Opus-4.6-Reasoning-Distilled? A distilled 27B with Claude Opus 4.6 reasoning baked in. So I put all 3 in the ring: - Qwen3.5-27B - Qwen3.5-27B-Claude-Opus-Distilled - Claude Opus 4.6 Since the distilled model isn't multimodal, I gave all three the same detailed text prompts describing the UI components from yesterday's test.

Yesterday we found out Qwen3.5-27B (dense) beats both the 35B and 122B MoE variants at UI replication from screenshots. Today's question: what about Jackrong's Qwen3.5-27B-Claude-Opus-4.6-Reasoning-Distilled? A distilled 27B with Claude Opus 4.6 reasoning baked in. So I put all 3 in the ring: - Qwen3.5-27B - Qwen3.5-27B-Claude-Opus-Distilled - Claude Opus 4.6 Since the distilled model isn't multimodal, I gave all three the same detailed text prompts describing the UI components from yesterday's test.

stevibe

125,913 次观看 • 3 个月前

Axiom-4 Mission Pilot & Gaganyatri Shubhanshu Shukla talking about what items he will be carrying to space to represent India! 🇮🇳 ISRO had consulted a university and asked its students from various different regions of India to come up with ideas for items representing all the regions and communities in India, which will be carried to space by him! 🚀

Axiom-4 Mission Pilot & Gaganyatri Shubhanshu Shukla talking about what items he will be carrying to space to represent India! 🇮🇳 ISRO had consulted a university and asked its students from various different regions of India to come up with ideas for items representing all the regions and communities in India, which will be carried to space by him! 🚀

Debapratim

22,099 次观看 • 1 年前

$watch a new 27 billion dense parameter model autonomously fail then fix itself on a single rtx 3090. 28 minutes of building, testing, debugging, and serving compressed to under three minutes. qwen 3.6 27b dense, q4_k_m quant, hermes agent as driving harness. one prompt in. mandelbrot fractal explorer with zoom, pan, three palettes, smooth coloring, responsive layout out the other side. 10 verifiable tests, all 10 landed green on its own. what you watch in the video. the model writes mandelbrot.html. writes tests.js. starts the http server. opens the page in its own browser. runs the tests. finds the failures. traces the math. patches the code. reloads. re-runs. iterates again. and again. until every test passes. no human in the loop. local prototyping looks like this in 2026. one consumer card. one open source model. one harness.$

watch a new 27 billion dense parameter model autonomously fail then fix itself on a single rtx 3090. 28 minutes of building, testing, debugging, and serving compressed to under three minutes. qwen 3.6 27b dense, q4_k_m quant, hermes agent as driving harness. one prompt in. mandelbrot fractal explorer with zoom, pan, three palettes, smooth coloring, responsive layout out the other side. 10 verifiable tests, all 10 landed green on its own. what you watch in the video. the model writes mandelbrot.html. writes tests.js. starts the http server. opens the page in its own browser. runs the tests. finds the failures. traces the math. patches the code. reloads. re-runs. iterates again. and again. until every test passes. no human in the loop. local prototyping looks like this in 2026. one consumer card. one open source model. one harness.

Sudo su

46,638 次观看 • 2 个月前

.Ann He and I won the AGI House ai x commerce hackathon on saturday! we built taste space: a 3d representation of 1500 clothing items that, through rating, you can place yourself in. built with CLIP, UMAP, synthetic labeling, react three fiber, and more. thread 👇

.Ann He and I won the AGI House ai x commerce hackathon on saturday! we built taste space: a 3d representation of 1500 clothing items that, through rating, you can place yourself in. built with CLIP, UMAP, synthetic labeling, react three fiber, and more. thread 👇

Michelle Lu

87,190 次观看 • 1 年前

3 ways to destroy a piece of paper. Qwen 3.5 35B A3B vs. Ornith 1.0 35B, side-by-side canvas test. (Why 3.5 not 3.6? Ornith is post-trained on Qwen 3.5 and Gemma 4, so this shows what the post-training adds.) Same 3 challenges: 🔪 Slice: three blade swipes, fruit-game style 📄 Shredder: desktop strip-cut 🗑️ Crumple: balled up and tossed Winner: not close. Ornith, decisively. The post-training quality is REAL.

3 ways to destroy a piece of paper. Qwen 3.5 35B A3B vs. Ornith 1.0 35B, side-by-side canvas test. (Why 3.5 not 3.6? Ornith is post-trained on Qwen 3.5 and Gemma 4, so this shows what the post-training adds.) Same 3 challenges: 🔪 Slice: three blade swipes, fruit-game style 📄 Shredder: desktop strip-cut 🗑️ Crumple: balled up and tossed Winner: not close. Ornith, decisively. The post-training quality is REAL.

stevibe

47,262 次观看 • 22 天前

We asked kache about his bespoke IDE setup: “I’ve built a custom framework in Neovim. It’s a server that creates a facade over all the LLMs: Claude, Gemini, OpenAI. They go down all the time, so I always have a model available. If everything breaks, I can still hit DeepSeek.” “Space+I is Gemini 2.5 Pro. Space+K is Gemini Flash. It all renders in a single markdown file. I’ve written commands, three backticks and a command like edit_file, and it just goes.” “It's not open source. People would start posting issues and I’m not interested in fixing them. I’m pulling up the ladder behind me.”

We asked kache about his bespoke IDE setup: “I’ve built a custom framework in Neovim. It’s a server that creates a facade over all the LLMs: Claude, Gemini, OpenAI. They go down all the time, so I always have a model available. If everything breaks, I can still hit DeepSeek.” “Space+I is Gemini 2.5 Pro. Space+K is Gemini Flash. It all renders in a single markdown file. I’ve written commands, three backticks and a command like edit_file, and it just goes.” “It's not open source. People would start posting issues and I’m not interested in fixing them. I’m pulling up the ladder behind me.”

TBPN

361,346 次观看 • 1 年前

NASA Trains in Deserts And Arctic Islands… Then Shows You “Mars.” 👁️✨ They Call Them Analog Sites. I Call It A Question Worth Asking. How Much of “Space” Was Built... Through A Screen? 🤡🌏

NASA Trains in Deserts And Arctic Islands… Then Shows You “Mars.” 👁️✨ They Call Them Analog Sites. I Call It A Question Worth Asking. How Much of “Space” Was Built... Through A Screen? 🤡🌏

vegastar

11,911 次观看 • 2 个月前

Most tools help you write, edit, or design in separate places. Felo takes a different approach with an intelligent canvas workspace where documents, slides, and collaboration all stay in the same space. It is positioned as an agent workspace for documents rather than a collection of isolated AI tricks. 🔗 | Felo AI (EN)

Most tools help you write, edit, or design in separate places. Felo takes a different approach with an intelligent canvas workspace where documents, slides, and collaboration all stay in the same space. It is positioned as an agent workspace for documents rather than a collection of isolated AI tricks. 🔗 | Felo AI (EN)

GitHub Projects Community

60,187 次观看 • 7 个月前

“All you little dorks go rewatch it. Round one, three, and five. I WON that fight!” Sean O’Malley just went off on a Twitter Space after rewatching the Merab fight 😅

“All you little dorks go rewatch it. Round one, three, and five. I WON that fight!” Sean O’Malley just went off on a Twitter Space after rewatching the Merab fight 😅

Happy Punch

1,113,033 次观看 • 1 年前

Pokini Games First I polished the base of the tail (with aim space), then animated the rest of the tail simply, switched it all to aim space, and offset. With aim space it's easy to make simple overlapping Here's a quick video showing the process. The tools I used are available on my Gumroad

Pokini Games First I polished the base of the tail (with aim space), then animated the rest of the tail simply, switched it all to aim space, and offset. With aim space it's easy to make simple overlapping Here's a quick video showing the process. The tools I used are available on my Gumroad

Martin

12,203 次观看 • 1 年前