Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

i keep hearing about how GLM-5.2 not only is great at coding but also that is on Opus 4.8 level when it comes to front end design I wanted to find out so... i put it to the test.. you can be the judge

Hermes Agent Tips

6,582 subscribers

70,284 görüntüleme • 14 gün önce •via X (Twitter)

Eğitim Haberler & Politika Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

we asked GLM 5.2 and Claude Opus 4.8 to find and fix the bugs in two different scripts while Opus 4.8 finished a few seconds faster in both tests, GLM 5.2 burned roughly 17k–38k fewer tokens and absolutely crushed it on cost, coming in 15x to 22x cheaper! Test 1: GLM 5.2 ($0.068) vs. Opus 4.8 ($1.06) Test 2: GLM 5.2 ($0.045) vs. Opus 4.8 ($1.02)

we asked GLM 5.2 and Claude Opus 4.8 to find and fix the bugs in two different scripts while Opus 4.8 finished a few seconds faster in both tests, GLM 5.2 burned roughly 17k–38k fewer tokens and absolutely crushed it on cost, coming in 15x to 22x cheaper! Test 1: GLM 5.2 ($0.068) vs. Opus 4.8 ($1.06) Test 2: GLM 5.2 ($0.045) vs. Opus 4.8 ($1.02)

GMI Cloud

86,026 görüntüleme • 7 gün 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

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

32,805 görüntüleme • 14 gün önce

I was a bit suspicious of the claim, but GLM-5.2 is pretty good at designing stuff. Obviously not at the level of a professional designer, but it has that Opus-level quality. Great at: - games - landing pages - HTML artifacts - 3D worlds Wish I had Fable 5 to compare with.

I was a bit suspicious of the claim, but GLM-5.2 is pretty good at designing stuff. Obviously not at the level of a professional designer, but it has that Opus-level quality. Great at: - games - landing pages - HTML artifacts - 3D worlds Wish I had Fable 5 to compare with.

elvis

16,819 görüntüleme • 15 gün önce

I love using GLM 5.2 for web app iteration. My workflow: generate 6 variations, then pick the best one and continue iterating on it. I built Recast to make this even easier. Give it a prompt, get 6 variations, download the code for your favorite version, then continue iterating in your own coding agent. GLM 5.2 works really well for this use case since it's fast, cheap, and great at design. On average, you can make 3-6 landing pages with GLM 5.2 for every one you can generate with Opus 4.8. And the design variety of the GLM landing pages helps a lot with trying to think through what style you want to go with. Recast is launching soon (as a web app + skill).

I love using GLM 5.2 for web app iteration. My workflow: generate 6 variations, then pick the best one and continue iterating on it. I built Recast to make this even easier. Give it a prompt, get 6 variations, download the code for your favorite version, then continue iterating in your own coding agent. GLM 5.2 works really well for this use case since it's fast, cheap, and great at design. On average, you can make 3-6 landing pages with GLM 5.2 for every one you can generate with Opus 4.8. And the design variety of the GLM landing pages helps a lot with trying to think through what style you want to go with. Recast is launching soon (as a web app + skill).

Hassan

20,164 görüntüleme • 7 gün önce

I haven’t tested it that rigorously but so far glm-5.2 is killing it at breaking out of agent sandboxes. This is so fun I had to make a video.

I haven’t tested it that rigorously but so far glm-5.2 is killing it at breaking out of agent sandboxes. This is so fun I had to make a video.

Zack Korman

20,951 görüntüleme • 16 gün önce

Opus 4.8 vs GLM 5.2 everyone is praising Glm on my timeline, so i had to test it myself > both models were given the same prompt > GLM was super fast and used like 2% of my weekly limit > Opus took over 20 mins and used like 3% of weekly limits which one do you think won?

Opus 4.8 vs GLM 5.2 everyone is praising Glm on my timeline, so i had to test it myself > both models were given the same prompt > GLM was super fast and used like 2% of my weekly limit > Opus took over 20 mins and used like 3% of weekly limits which one do you think won?

J A Z I I

47,962 görüntüleme • 13 gün önce

I wanted to ask Coach Prime about how Travis Hunter is doing. “Everything is great, he has the Heisman Trophy at the crib… I don’t know where the bulljunk comes in at… It’s so easy to see the negative when the positive is right in front of you.”

I wanted to ask Coach Prime about how Travis Hunter is doing. “Everything is great, he has the Heisman Trophy at the crib… I don’t know where the bulljunk comes in at… It’s so easy to see the negative when the positive is right in front of you.”

RK

871,573 görüntüleme • 1 yıl önce

OpenAI are testing a new model on the Web Dev Arena Arena under the name 'Anonymous Chatbot 0717'. I can't believe I'm gonna say this, but it is genuinely at a completely different level of front end coding - far better than Sonnet, o3, Gemini 2.5 Pro, or Grok 4. To test it, I ran a great prompt borrowed from the amazing The Feature Crew YouTube channel, asking models to create a procedurally generated planet with Three.js. Take a look yourselves, but I'm pretty astonished by how big the jump is. I have featured the new model twice just because its implementations have been so interesting. Of course, this is only one test, but OpenAI models have always been a bit 'meh' at front-end work, and they seem to have finally overtaken everyone else on that front. We'll see when it comes out. Credit to Chetaslua for discovering the model

OpenAI are testing a new model on the Web Dev Arena Arena under the name 'Anonymous Chatbot 0717'. I can't believe I'm gonna say this, but it is genuinely at a completely different level of front end coding - far better than Sonnet, o3, Gemini 2.5 Pro, or Grok 4. To test it, I ran a great prompt borrowed from the amazing The Feature Crew YouTube channel, asking models to create a procedurally generated planet with Three.js. Take a look yourselves, but I'm pretty astonished by how big the jump is. I have featured the new model twice just because its implementations have been so interesting. Of course, this is only one test, but OpenAI models have always been a bit 'meh' at front-end work, and they seem to have finally overtaken everyone else on that front. We'll see when it comes out. Credit to Chetaslua for discovering the model

Peter Gostev

495,815 görüntüleme • 11 ay önce

I just tested GLM 5.2, Claude opus 4.8, and GPT 5.5 to see which one could rebuild my personal site in that whimsical ascii style GLM 5.2 held its own and went toe to toe with the other 2 top tier models lowkey impressed, look at the hero section it built here

I just tested GLM 5.2, Claude opus 4.8, and GPT 5.5 to see which one could rebuild my personal site in that whimsical ascii style GLM 5.2 held its own and went toe to toe with the other 2 top tier models lowkey impressed, look at the hero section it built here

Ann Nguyen

33,577 görüntüleme • 15 gün önce

This is how I created this video. Prompts + bloopers below ♥ I used a previs storyboard style this time just to test it, it worked well except when it would keep the directional arrows. I need to adjust the prompt so that does not happen. The little videos and buttons at the end is pure capcut masking.

This is how I created this video. Prompts + bloopers below ♥ I used a previs storyboard style this time just to test it, it worked well except when it would keep the directional arrows. I need to adjust the prompt so that does not happen. The little videos and buttons at the end is pure capcut masking.

Glitter Gal

89,152 görüntüleme • 1 ay önce

At this point, you can technically be done. But when it comes to frosted glass, I like to add some noise. You can technically add the noise to just the logo, but I want it over the whole photo. Watch how I do it:

Brett

15,343 görüntüleme • 1 yıl önce

I made a new video to show not only how powerful the AirFanta 3Pro is, but also how compact and portable it is. It is the only air purifier on the market that have more than 400CFM CADR and be so portable at the same time!

I made a new video to show not only how powerful the AirFanta 3Pro is, but also how compact and portable it is. It is the only air purifier on the market that have more than 400CFM CADR and be so portable at the same time!

Adam Wong

20,334 görüntüleme • 1 yıl önce

Everyone is talking about Claude Design… but I keep going back to Gemini. Gemini 3.1 Pro is seriously impressive when it comes to motion design. I actually want to try Claude Design, but after only two prompts, I was already running out of credits. If you care about anti AI slop, Gemini is still winning. With a single prompt, it can transform a static HTML layout into dynamic, polished motion graphics.

Everyone is talking about Claude Design… but I keep going back to Gemini. Gemini 3.1 Pro is seriously impressive when it comes to motion design. I actually want to try Claude Design, but after only two prompts, I was already running out of credits. If you care about anti AI slop, Gemini is still winning. With a single prompt, it can transform a static HTML layout into dynamic, polished motion graphics.

FHILY👑

25,019 görüntüleme • 11 gün önce

Truly unbelievable GLM 5.2 just released and it's an open weights model you can run locally The insane part is, it's just as good as Opus 4.8 Unlimited, free super intelligence running on your desk In this video I cover how it works, and how to set up your first local model:

Truly unbelievable GLM 5.2 just released and it's an open weights model you can run locally The insane part is, it's just as good as Opus 4.8 Unlimited, free super intelligence running on your desk In this video I cover how it works, and how to set up your first local model:

Alex Finn

122,085 görüntüleme • 12 gün önce

I know that more is not always better when it comes to visual or gameplay design, but when it comes to testing the capabilities of PS5 in our Astrobot #MadeInDreams , I am a simple man.

I know that more is not always better when it comes to visual or gameplay design, but when it comes to testing the capabilities of PS5 in our Astrobot #MadeInDreams , I am a simple man.

BadRobo82

16,522 görüntüleme • 1 yıl önce

🍀 "how do you overcome times when your willpower drops?" 🐻 "when willpower drops, just live with it dropped. just let it flow. and then, at some point, someday you'll have the strength to do it again. but i think the most important thing at that time is to completely empty your mind of any desire to do something. like, 'i don't want to do it right now. i'm not going to do it.' if you can cleanly say that, that's great. but if there's even a little bit of, 'i should be doing it, so why am i not doing it?' in your mind, then it's better to just go ahead and do it. but in the end, when your willpower is down, you can't do it anyway. so in the end, i think it's good to take care of your own feelings. that's how i overcame it."

🍀 "how do you overcome times when your willpower drops?" 🐻 "when willpower drops, just live with it dropped. just let it flow. and then, at some point, someday you'll have the strength to do it again. but i think the most important thing at that time is to completely empty your mind of any desire to do something. like, 'i don't want to do it right now. i'm not going to do it.' if you can cleanly say that, that's great. but if there's even a little bit of, 'i should be doing it, so why am i not doing it?' in your mind, then it's better to just go ahead and do it. but in the end, when your willpower is down, you can't do it anyway. so in the end, i think it's good to take care of your own feelings. that's how i overcame it."

dea❀ꕤ

15,922 görüntüleme • 1 yıl önce

250724 #ATEEZ #Hongjoong about Seonghwa’s hand after the incident, TOKTOQ pop (voice) live (rough translation): I saw in the comments that many of you are curious about Seonghwa’s hand, and actually, I noticed it yesterday too - in the messages on Fromm. To be honest, I wasn’t sure how Seonghwa himself wanted to talk about it, and he knows better than I do about the extent of his injury, so I didn’t want to speak on his behalf, which is why I deliberately didn’t mention it earlier. But I saw today that Seonghwa talked about it yesterday, so I think I can say a little now. Actually, it happened right before my solo stage, so during the performance I wasn’t fully aware of what had happened, and I found out only later. When members get injured on stage, it’s always tough. Of course, we feel it physically ourselves, but it’s also hard to know how it comes across to those watching, and that’s why it’s not easy to talk about these things publicly. Still, I talked to Seonghwa after the performance and saw how he was doing. While there’s nothing fortunate about getting injured - and it was one of those unpredictable situations where no one was at fault - it seems like the emergency response was handled well. And Seonghwa was even smiling when talking about it, so it doesn’t seem to be anything extremely serious. But I think what worries ATINY - and me too - is not just the pain, but the fact that burns or sparks like that can leave scars easily. We really don’t want any lasting marks on Seonghwa’s hands, or anywhere on his body. Thankfully, our care team is doing a great job making sure he’s being looked after properly. Of course, there’s not much I can personally do, but we’ll keep communicating well with the members, the stage production team, and the on-site staff so that accidents like this don’t happen again. Since this isn’t directly about me, it feels a bit awkward to talk about it at length, but I know a lot of you are concerned and curious, so I wanted to share. video cr. m0men1_s2

250724 #ATEEZ #Hongjoong about Seonghwa’s hand after the incident, TOKTOQ pop (voice) live (rough translation): I saw in the comments that many of you are curious about Seonghwa’s hand, and actually, I noticed it yesterday too - in the messages on Fromm. To be honest, I wasn’t sure how Seonghwa himself wanted to talk about it, and he knows better than I do about the extent of his injury, so I didn’t want to speak on his behalf, which is why I deliberately didn’t mention it earlier. But I saw today that Seonghwa talked about it yesterday, so I think I can say a little now. Actually, it happened right before my solo stage, so during the performance I wasn’t fully aware of what had happened, and I found out only later. When members get injured on stage, it’s always tough. Of course, we feel it physically ourselves, but it’s also hard to know how it comes across to those watching, and that’s why it’s not easy to talk about these things publicly. Still, I talked to Seonghwa after the performance and saw how he was doing. While there’s nothing fortunate about getting injured - and it was one of those unpredictable situations where no one was at fault - it seems like the emergency response was handled well. And Seonghwa was even smiling when talking about it, so it doesn’t seem to be anything extremely serious. But I think what worries ATINY - and me too - is not just the pain, but the fact that burns or sparks like that can leave scars easily. We really don’t want any lasting marks on Seonghwa’s hands, or anywhere on his body. Thankfully, our care team is doing a great job making sure he’s being looked after properly. Of course, there’s not much I can personally do, but we’ll keep communicating well with the members, the stage production team, and the on-site staff so that accidents like this don’t happen again. Since this isn’t directly about me, it feels a bit awkward to talk about it at length, but I know a lot of you are concerned and curious, so I wanted to share. video cr. m0men1_s2

Irene | AhgaTiny

50,330 görüntüleme • 11 ay önce

ADÉLA talks about the Dream Academy Documentary and how she and her friends get torn to shreds on social media. “I was like, it is not the time to be depressed about this, it is time to put out music about this. ‘Cause people are talking about it so they want to hear what I have to say”

ADÉLA talks about the Dream Academy Documentary and how she and her friends get torn to shreds on social media. “I was like, it is not the time to be depressed about this, it is time to put out music about this. ‘Cause people are talking about it so they want to hear what I have to say”

ADÉLA Access

611,615 görüntüleme • 2 ay önce

I tested GLM 5.2 on three real builds. A horror house game. A 3D stealth game. A Remotion marketing video. The results are exactly what I expect from Chinese open source coding models right now. The horror house has broken game logic. Collect all three keys, complete the objective, and the front door still won't open. The stealth game shipped with lighting so dark you can't see your own character. The Remotion video is rough. GLM 5.2 is faster than 5.1 and 10x cheaper than the frontier. But Opus 4.8 and GPT 5.5 are still in a different league for serious coding work. Chinese models keep missing the attention to detail that matters. I MISS FABLE 5 ALREADY. Full review live now.

I tested GLM 5.2 on three real builds. A horror house game. A 3D stealth game. A Remotion marketing video. The results are exactly what I expect from Chinese open source coding models right now. The horror house has broken game logic. Collect all three keys, complete the objective, and the front door still won't open. The stealth game shipped with lighting so dark you can't see your own character. The Remotion video is rough. GLM 5.2 is faster than 5.1 and 10x cheaper than the frontier. But Opus 4.8 and GPT 5.5 are still in a different league for serious coding work. Chinese models keep missing the attention to detail that matters. I MISS FABLE 5 ALREADY. Full review live now.

BridgeMind

24,527 görüntüleme • 19 gün önce