Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

fixed the reasoning bugs + the thinking loop in glm-5.3 flash. it's a different model now. i gave the same prompt to glm (running on my desk) vs gpt-6.1 sol. they produced a SINGLE HTML file each. very content with GLM's version, i'm genuinely impressed

filicroval's profile picture

filipe

153,583 subscribers

47,597 görüntüleme • 1 gün önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

13 Yorum

dr bosconovitch profil fotoğrafı
dr bosconovitch1 gün önce

how much time did it take?

Sat Grewal profil fotoğrafı
Sat Grewal1 gün önce

Can you share the prompt you used for this animated version?

Rico · DGX Spark Cluster profil fotoğrafı
Rico · DGX Spark Cluster1 gün önce

Running on your desk is the best part. It's my daily coding model on two Sparks too. What caused the thinking loop?

dr bosconovitch profil fotoğrafı
dr bosconovitch1 gün önce

Wow waiting patiently! So that I can leave it running overnight... Please push it's 12am here haha Thanks for your work, man!

Erago 🇦🇹 profil fotoğrafı
Erago 🇦🇹1 gün önce

How do you do that? For me GLM 5.3 Flash (through my Z AI subscription already has issues doing the simplest 3d tasks.

tolgaozisik profil fotoğrafı
tolgaozisik1 gün önce

This is huge if its true

Ican profil fotoğrafı
Ican1 gün önce

What's 16bit or what

Tyler Folkman profil fotoğrafı
Tyler Folkman1 gün önce

Pretty impressive.

accelerate27 profil fotoğrafı
accelerate271 gün önce

how many iterations did it take for glm 5.3 flash to reach this point?

John Davis | Solar Strategies profil fotoğrafı
John Davis | Solar Strategies1 gün önce

Pushed?

Terp profil fotoğrafı
Terp1 gün önce

that's great work

LakyFx profil fotoğrafı
LakyFx1 gün önce

🥳👍

MarioLee profil fotoğrafı
MarioLee1 gün önce

你是通过 zcode 使用 glm 模型的么？

Benzer Videolar

Five frontier models. One simple prompt. No retries. No blender. Just a simple frontend web design. Fable 5.1 vs. GPT-6 Astra vs. DeepSeek v4.1 Flash vs. GLM 5.3 Flash vs. Qwen3.8 Flash Next Which model built the best looking luxury watch landing page? IMO Fable 5.1 and GLM 5.3 Flash look the best. LIVE DEMO:
0:43

Five frontier models. One simple prompt. No retries. No blender. Just a simple frontend web design. Fable 5.1 vs. GPT-6 Astra vs. DeepSeek v4.1 Flash vs. GLM 5.3 Flash vs. Qwen3.8 Flash Next Which model built the best looking luxury watch landing page? IMO Fable 5.1 and GLM 5.3 Flash look the best. LIVE DEMO:

Mia

16,501 görüntüleme • 21 gün önce

GLM-5.3 Flash in already nerfed? I compared Ox Alpha in it's prime vs today just before it got revealed as GLM-5.3 Flash using the same prompt to build 3d raptor engine using three.js OxAlpha on 24th August gave far more accurate output compared to today which looks way worse prompt i used: Create a 3d SpaceX raptor engine using three.js, use white theme background so the main object is clearly visible
0:28

GLM-5.3 Flash in already nerfed? I compared Ox Alpha in it's prime vs today just before it got revealed as GLM-5.3 Flash using the same prompt to build 3d raptor engine using three.js OxAlpha on 24th August gave far more accurate output compared to today which looks way worse prompt i used: Create a 3d SpaceX raptor engine using three.js, use white theme background so the main object is clearly visible

Tim Jayas

82,975 görüntüleme • 1 ay önce

glm 5.3 flash is 7.5x cheaper, but 3.4x slower than gemini 3.7 flash Z.ai glm 5.3 flash – shipped aug 26, $0.07/$0.25 per 1m Google DeepMind gemini 3.7 flash – shipped aug 13, $0.38/$1.88 per 1m we put the two models on one job: write one html file that draws an animated 3d scene in the browser. no images, no downloads, and it has to look the same on every load. the setup: three scenes – a glass aquarium in a lit room, the solar system, a night city under a thunderstorm. identical brief word for word, reasoning effort high, 64k output cap. the numbers below are not the whole run. they cover the three scenes we kept – the best one per task from each model, the ones in the video. - total generation time for the three scenes #1 gemini 3.7 flash – 10m 36s #2 glm 5.3 flash – 36m 30s - tokens spent on those three scenes #1 glm 5.3 flash – 110k #2 gemini 3.7 flash – 111k - cost of those three scenes #1 glm 5.3 flash – $0.027 #2 gemini 3.7 flash – $0.202 observations: • glm's first 10 attempts: 7 blank pages. it kept inventing short random helpers and forgetting to define one of them. the fix was one line in the brief: use exactly one random helper, named rand(), and don't invent shorthands next to it. next 12 attempts: 11 alive, 0 crashes. • glm spends 66% of its output on reasoning, gemini 57%. that is the whole speed gap. • gemini's storm came back as a black rectangle in 4 of 6 runs. glm's best storm has a branching bolt, lit rain and wet asphalt – for $0.01. conclusion: same three scenes, same token spend – glm 5.3 flash billed $0.027 and took 36m 30s, gemini 3.7 flash billed $0.202 and took 10m 36s. glm wins gemini on price and made the best storm of the whole run follow thehype. for 24/7 ai news, analysis and breakdowns
0:30

glm 5.3 flash is 7.5x cheaper, but 3.4x slower than gemini 3.7 flash Z.ai glm 5.3 flash – shipped aug 26, $0.07/$0.25 per 1m Google DeepMind gemini 3.7 flash – shipped aug 13, $0.38/$1.88 per 1m we put the two models on one job: write one html file that draws an animated 3d scene in the browser. no images, no downloads, and it has to look the same on every load. the setup: three scenes – a glass aquarium in a lit room, the solar system, a night city under a thunderstorm. identical brief word for word, reasoning effort high, 64k output cap. the numbers below are not the whole run. they cover the three scenes we kept – the best one per task from each model, the ones in the video. - total generation time for the three scenes #1 gemini 3.7 flash – 10m 36s #2 glm 5.3 flash – 36m 30s - tokens spent on those three scenes #1 glm 5.3 flash – 110k #2 gemini 3.7 flash – 111k - cost of those three scenes #1 glm 5.3 flash – $0.027 #2 gemini 3.7 flash – $0.202 observations: • glm's first 10 attempts: 7 blank pages. it kept inventing short random helpers and forgetting to define one of them. the fix was one line in the brief: use exactly one random helper, named rand(), and don't invent shorthands next to it. next 12 attempts: 11 alive, 0 crashes. • glm spends 66% of its output on reasoning, gemini 57%. that is the whole speed gap. • gemini's storm came back as a black rectangle in 4 of 6 runs. glm's best storm has a branching bolt, lit rain and wet asphalt – for $0.01. conclusion: same three scenes, same token spend – glm 5.3 flash billed $0.027 and took 36m 30s, gemini 3.7 flash billed $0.202 and took 10m 36s. glm wins gemini on price and made the best storm of the whole run follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

16,041 görüntüleme • 1 ay önce

I'm becoming a real Droid fan now! Here we have Calude Code vs Droid in Lego San Andreas glm-5-turbo edition! - 0-shot - same prompt, same model, same reasoning - stealing vehicle doesn't work in cc version - time of the day simulated in Droid version! Look at the image! 🤯
1:00

I'm becoming a real Droid fan now! Here we have Calude Code vs Droid in Lego San Andreas glm-5-turbo edition! - 0-shot - same prompt, same model, same reasoning - stealing vehicle doesn't work in cc version - time of the day simulated in Droid version! Look at the image! 🤯

Ivan Fioravanti ᯅ

17,953 görüntüleme • 6 ay önce

DeepSeek v4.1 Flash vs GLM 5.3 Flash I asked both models to recreate the Psychonauts 2 and Metroid Prime game menus as closely as possible to the originals. Attached are full-sized videos from both models for both games. All were done in a single shot, both at Max thinking, same harness. Tokens used: DeepSeek v4.1 Flash - Psychonauts 2: 412k - Metroid Prime: 466k GLM 5.3 Flash - Psychonauts 2: 134k - Metroid Prime: 111k That's between 3-4x MORE used by DS4.1F. Who do you think won? IMO GLM 5.3 Flash won by FAR on both.
0:20

DeepSeek v4.1 Flash vs GLM 5.3 Flash I asked both models to recreate the Psychonauts 2 and Metroid Prime game menus as closely as possible to the originals. Attached are full-sized videos from both models for both games. All were done in a single shot, both at Max thinking, same harness. Tokens used: DeepSeek v4.1 Flash - Psychonauts 2: 412k - Metroid Prime: 466k GLM 5.3 Flash - Psychonauts 2: 134k - Metroid Prime: 111k That's between 3-4x MORE used by DS4.1F. Who do you think won? IMO GLM 5.3 Flash won by FAR on both.

Mia

23,835 görüntüleme • 20 gün önce

GLM 5.3 Flash vs Hybrid (GLM 5.3 Flash + Jev) on a turn-based strategy game (Halite 2) The hybrid approach is 13x faster, 56% of the pure GLM 5.3 Flash API cost, and gains a slight edge in performance. In the hybrid approach: -GLM 5.3 Flash handles strategic judgment of which planets matter, who expands, who fights, when to re-plan. -Jev handles the ship-by-ship execution. GLM 5.3 Flash alone defeats Jev alone 82% of the time. This is obviously just a single example and some of the first things I've tried to make use of Jev as an augmentation to an LLM. Could potentially make even more gains in cost, speed, and performance, but using what I've figured out here, I am compelled to try some ideas with robotics next.
0:24

GLM 5.3 Flash vs Hybrid (GLM 5.3 Flash + Jev) on a turn-based strategy game (Halite 2) The hybrid approach is 13x faster, 56% of the pure GLM 5.3 Flash API cost, and gains a slight edge in performance. In the hybrid approach: -GLM 5.3 Flash handles strategic judgment of which planets matter, who expands, who fights, when to re-plan. -Jev handles the ship-by-ship execution. GLM 5.3 Flash alone defeats Jev alone 82% of the time. This is obviously just a single example and some of the first things I've tried to make use of Jev as an augmentation to an LLM. Could potentially make even more gains in cost, speed, and performance, but using what I've figured out here, I am compelled to try some ideas with robotics next.

Harrison Kinsley

53,159 görüntüleme • 16 gün önce

I gave 4 frontier models the same prompt to create an Ecco the Dolphin style video game 100% procedural 🐬 Same task, official chat UIs, max thinking. Watch 👇 Claude Fable 5 Z.ai GLM 5.2 ChatGPT GPT 5.5 Pro Google Gemini Flash 3.5 Note: Fable 5 version was created before the model was restricted.
0:53

I gave 4 frontier models the same prompt to create an Ecco the Dolphin style video game 100% procedural 🐬 Same task, official chat UIs, max thinking. Watch 👇 Claude Fable 5 Z.ai GLM 5.2 ChatGPT GPT 5.5 Pro Google Gemini Flash 3.5 Note: Fable 5 version was created before the model was restricted.

Majid Manzarpour

42,774 görüntüleme • 3 ay önce

okay so this one of many vibetest comparisons between glm-5 and opus-4.6 (below) on design + visualization. prompt: a window in a paris apartment. you sit and watch the hours pass - dawn, morning rain, golden afternoon, violet dusk, city lights at night. click anywhere to move time forward. each hour sounds different. each hour feels different. single html file. glm-5👇
0:54

okay so this one of many vibetest comparisons between glm-5 and opus-4.6 (below) on design + visualization. prompt: a window in a paris apartment. you sit and watch the hours pass - dawn, morning rain, golden afternoon, violet dusk, city lights at night. click anywhere to move time forward. each hour sounds different. each hour feels different. single html file. glm-5👇

himanshu

12,552 görüntüleme • 7 ay önce

Qwen3.8-Flash-Next (176B, NVFP4, 2× DGX Spark): 40,265 thinking tokens, 21,091 answer. Qwen3.8-27B on the same prompt: 42,988 thinking, 6,040 answer. Same question, same deliberation, 3.5× the output. 55 min vs 37 min. The 176B shipped a genuine leapfrog wave equation on a 512² lattice with reflections and interference. The 27B shipped a solid ripple tank. Both run 60fps in a single HTML file Generated on DGX Sparks on my desk.
0:45

Qwen3.8-Flash-Next (176B, NVFP4, 2× DGX Spark): 40,265 thinking tokens, 21,091 answer. Qwen3.8-27B on the same prompt: 42,988 thinking, 6,040 answer. Same question, same deliberation, 3.5× the output. 55 min vs 37 min. The 176B shipped a genuine leapfrog wave equation on a 512² lattice with reflections and interference. The 27B shipped a solid ripple tank. Both run 60fps in a single HTML file Generated on DGX Sparks on my desk.

Wësche

23,168 görüntüleme • 1 ay önce

Fable 5.1 xHigh vs GLM 5.3 Flash Max With Zai’s current promo, GLM 5.3 Flash is around 58x cheaper than Fable 5.1… and just look at the quality It finished the same task in about half the time, while still delivering a genuinely impressive result 58x cheaper. 2x faster. And the quality is this close That’s honestly crazy, Huge credit to Zhipu for bringing us models this efficient
1:38

Fable 5.1 xHigh vs GLM 5.3 Flash Max With Zai’s current promo, GLM 5.3 Flash is around 58x cheaper than Fable 5.1… and just look at the quality It finished the same task in about half the time, while still delivering a genuinely impressive result 58x cheaper. 2x faster. And the quality is this close That’s honestly crazy, Huge credit to Zhipu for bringing us models this efficient

Iam_

110,563 görüntüleme • 1 ay önce

I was skeptical about giving GLM-5.2 the task to build a super mario snes style game in a single HTML file so i ran the test on Opus and also on GLM-5.2 Opus didnt even try to make a game or made something but it wasn't a game GLM-5.2 one shotted a pretty functional game.. WILD
0:45

I was skeptical about giving GLM-5.2 the task to build a super mario snes style game in a single HTML file so i ran the test on Opus and also on GLM-5.2 Opus didnt even try to make a game or made something but it wasn't a game GLM-5.2 one shotted a pretty functional game.. WILD

Hermes Agent Tips

32,883 görüntüleme • 3 ay önce

1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5 We gave 3 models the same prompt and compared one-shot outputs. The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s. Which output do you like best? GGUF:
0:21

1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5 We gave 3 models the same prompt and compared one-shot outputs. The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s. Which output do you like best? GGUF:

Unsloth AI

1,544,807 görüntüleme • 3 ay önce

Qwen3.8-Flash-Next is shockingly good against GLM-3.5 Flash i used the same prompt to build fully controllable hummingbird using three.js and here's the side by side comparison between both it's insane how both are open models that can one shot entire game with a single prompt
0:42

Qwen3.8-Flash-Next is shockingly good against GLM-3.5 Flash i used the same prompt to build fully controllable hummingbird using three.js and here's the side by side comparison between both it's insane how both are open models that can one shot entire game with a single prompt

Tim Jayas

20,467 görüntüleme • 1 ay önce

GLM 5.3 Flash running locally makes a Minecraft black hole mod We ran GLM 5.3 Flash Q4 locally on a rented 4x RTX PRO 6000 box and asked it to make a lightning gun mod for the real game using the Fabric API Output: -7.6M tokens -Time: ~9 hours -Decode: ~96 tok/s The mod adds a black hole rifle, when shot it spawns a black hole that pulls in blocks, with light rings that shrink all the way into the singularity, then collapses into an explosion crater that wipes out several chunks Run GLM 5.3 Flash locally in
0:22

GLM 5.3 Flash running locally makes a Minecraft black hole mod We ran GLM 5.3 Flash Q4 locally on a rented 4x RTX PRO 6000 box and asked it to make a lightning gun mod for the real game using the Fabric API Output: -7.6M tokens -Time: ~9 hours -Decode: ~96 tok/s The mod adds a black hole rifle, when shot it spawns a black hole that pulls in blocks, with light rings that shrink all the way into the singularity, then collapses into an explosion crater that wipes out several chunks Run GLM 5.3 Flash locally in

atomic.chat

32,515 görüntüleme • 1 ay önce

My vid on Opus 5.5 and GPT 6.1 Sol: - Sol 6.1 is miles better than 6.0, it's worth trying out & the price is nuts - Opus 5.5 is the best Claude model in a very long time
22:06

My vid on Opus 5.5 and GPT 6.1 Sol: - Sol 6.1 is miles better than 6.0, it's worth trying out & the price is nuts - Opus 5.5 is the best Claude model in a very long time

Ben Davis

18,809 görüntüleme • 4 gün önce

Something is wrong at OpenAI. Tibo and Sam said GPT-6.1 Sol would be faster today. Instead it appears to be running slower. Sonnet 5.5 and Opus 5.5 are much faster than Sol 6.1 and Grok 4.7 Check out the below comparison, same prompt on high reasoning with a 20 minute deadline.
2:42

Something is wrong at OpenAI. Tibo and Sam said GPT-6.1 Sol would be faster today. Instead it appears to be running slower. Sonnet 5.5 and Opus 5.5 are much faster than Sol 6.1 and Grok 4.7 Check out the below comparison, same prompt on high reasoning with a 20 minute deadline.

Eco

17,812 görüntüleme • 5 gün önce

We tested GLM 5.3 Flash and Qwen 3.8 Flash in Pi. Same task for both: use ego lite to build an interactive 3D solar system. Qwen cost 3.6x more and ran 1.7x longer, but the output tells a different story. Comment "prompt" below and we'll drop it.
0:25

We tested GLM 5.3 Flash and Qwen 3.8 Flash in Pi. Same task for both: use ego lite to build an interactive 3D solar system. Qwen cost 3.6x more and ran 1.7x longer, but the output tells a different story. Comment "prompt" below and we'll drop it.

ego

24,535 görüntüleme • 1 ay önce

Neel built Builddy to go from a text prompt to a deployed web app in one go using GLM-5.1. The system coordinates 6 different agents to handle everything from system design to final deployment, all running on GLM-5.1's coding logic.
2:46

Neel built Builddy to go from a text prompt to a deployed web app in one go using GLM-5.1. The system coordinates 6 different agents to handle everything from system design to final deployment, all running on GLM-5.1's coding logic.

Z.ai

40,572 görüntüleme • 5 ay önce

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.
0:25

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.

Tony

112,633 görüntüleme • 12 gün önce

This is what the future of coding looks like. Multiple AI models working in the same Codex session, with Jev routing them to tackle different parts of the task. Here, I had it build a full-stack demo app: > Opus 5.5 planned it. > GPT-6 Astra built the backend. > Kimi K3 built the frontend. > DeepSeek handled testing. > GLM 5.3 Flash wrote the docs. Jev handles the switching. I never touched the model picker. 40% cheaper, 15% faster for the same build.
0:29

This is what the future of coding looks like. Multiple AI models working in the same Codex session, with Jev routing them to tackle different parts of the task. Here, I had it build a full-stack demo app: > Opus 5.5 planned it. > GPT-6 Astra built the backend. > Kimi K3 built the frontend. > DeepSeek handled testing. > GLM 5.3 Flash wrote the docs. Jev handles the switching. I never touched the model picker. 40% cheaper, 15% faster for the same build.

elvis

16,347 görüntüleme • 8 gün önce