Video yükleniyor...

Video Yüklenemedi

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

Ana Sayfaya Dön

This is actually cool - I tried the same prompt for the new Interactive Playwright skill in Codex & GPT-5.4 xHigh - the one above is with the skill and the one below is without. What the skill does is uses the computer use capability of GPT-5.4 to look... show more

Peter Gostev

13,024 subscribers

257,111 görüntüleme • 3 ay önce •via X (Twitter)

Sanat Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Had early access to GPT-5.4 and Pro. They are very good. One fun illustration of progress, this is the same prompt I used in GPT-4 below (making a 3D space inspired by Piranesi) now in GPT-5.4 Pro. There were no errors, made in a single prompt plus one to "make it better."

Had early access to GPT-5.4 and Pro. They are very good. One fun illustration of progress, this is the same prompt I used in GPT-4 below (making a 3D space inspired by Piranesi) now in GPT-5.4 Pro. There were no errors, made in a single prompt plus one to "make it better."

Ethan Mollick

188,306 görüntüleme • 3 ay önce

Built a tactical turn-based RPG with Codex + GPT-5.4, using Playwright for testing and image-gen for the visuals. I grew up loving turn-based RPGs, so this was a fun one to build. Sharing a 45s demo below — it’s also featured in the OpenAI GPT-5.4 blog post for anyone who wants more context.

Built a tactical turn-based RPG with Codex + GPT-5.4, using Playwright for testing and image-gen for the visuals. I grew up loving turn-based RPGs, so this was a fun one to build. Sharing a 45s demo below — it’s also featured in the OpenAI GPT-5.4 blog post for anyone who wants more context.

corey.ching

233,239 görüntüleme • 3 ay önce

One shot in codex with gpt-taste skill! GPT 5.4 medium works best :) skill:

One shot in codex with gpt-taste skill! GPT 5.4 medium works best :) skill:

Leon Lin

158,387 görüntüleme • 2 ay önce

PSA: your really MUST use the Front End skill for GPT-5.4 - if you want to see the comparison quickly: c. 1:30 for 'without skill' c. 2:00 for 'with skill'

PSA: your really MUST use the Front End skill for GPT-5.4 - if you want to see the comparison quickly: c. 1:30 for 'without skill' c. 2:00 for 'with skill'

Peter Gostev

32,122 görüntüleme • 3 ay önce

HOLLLLY SHIIIIIT 😳 GPT 5.5 xhigh in codex made this paper physics website with wind effect one shot check the physics , ui and interaction Sam Altman you guys cooked and this is my first time i can suggest chatgpt is go to ai solution for everything

HOLLLLY SHIIIIIT 😳 GPT 5.5 xhigh in codex made this paper physics website with wind effect one shot check the physics , ui and interaction Sam Altman you guys cooked and this is my first time i can suggest chatgpt is go to ai solution for everything

Chetaslua

1,620,017 görüntüleme • 2 ay önce

When using GPT-5.5, it is instantly noticeable how much more powerful it is. In Codex, I gave it a very complex prompt to create London Toy Railway with landmarks and seasons - it did an excellent job in one shot. In the second half of the video you see GPT-5.4 - it was also not bad, but very clearly worse. GPT-5.5's generation is far more ambitious, coherent and with fewer errors. This is obviously a toy example, but I've used it on much more complex real tasks, including a complex app migration and a new hard workflow - it has been working away for many hours without getting stumped. I'm getting more and more addicted to this stuff with every model release.

When using GPT-5.5, it is instantly noticeable how much more powerful it is. In Codex, I gave it a very complex prompt to create London Toy Railway with landmarks and seasons - it did an excellent job in one shot. In the second half of the video you see GPT-5.4 - it was also not bad, but very clearly worse. GPT-5.5's generation is far more ambitious, coherent and with fewer errors. This is obviously a toy example, but I've used it on much more complex real tasks, including a complex app migration and a new hard workflow - it has been working away for many hours without getting stumped. I'm getting more and more addicted to this stuff with every model release.

Peter Gostev

262,507 görüntüleme • 2 ay önce

GPT-5.4 is now the default model in Augment, and it’s free for a limited time.

GPT-5.4 is now the default model in Augment, and it’s free for a limited time.

Augment Code

16,308 görüntüleme • 3 ay önce

gpt-5.4 is an incredible model. It is the only model I use for 90% of the stuff I do.

gpt-5.4 is an incredible model. It is the only model I use for 90% of the stuff I do.

Theo - t3.gg

151,682 görüntüleme • 3 ay önce

So this game is real now, fully built with GPT-5.5. I told Codex to use the imagegen skill to generate a reference UI and sprites, and used the Build macOS Apps plugin to build the app for a native retro fantasy labyrinth game! Adjusted the UI in a few prompts and here we are!

So this game is real now, fully built with GPT-5.5. I told Codex to use the imagegen skill to generate a reference UI and sprites, and used the Build macOS Apps plugin to build the app for a native retro fantasy labyrinth game! Adjusted the UI in a few prompts and here we are!

Thomas Ricouard

144,154 görüntüleme • 2 ay önce

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this

Min Zhou

341,265 görüntüleme • 2 ay önce

WOW! I'm so excited about this. OpenAI Developers said Codex was good at Computer Use, but I wasn't prepared for this. For the last two weeks I've been working on a Computer Use skill to work with Linux. And while I had some success, it was a pretty frustrating experience. That is...until the breakthrough. Using accessibility tools, Codex can now control my entire computer, not just the browser. There are limits to this, of course, but what a time to be alive. This Computer Use skill will unlock and entirely new set of automations, all powered by Codex. Demonstration below 👇

WOW! I'm so excited about this. OpenAI Developers said Codex was good at Computer Use, but I wasn't prepared for this. For the last two weeks I've been working on a Computer Use skill to work with Linux. And while I had some success, it was a pretty frustrating experience. That is...until the breakthrough. Using accessibility tools, Codex can now control my entire computer, not just the browser. There are limits to this, of course, but what a time to be alive. This Computer Use skill will unlock and entirely new set of automations, all powered by Codex. Demonstration below 👇

am.will

79,622 görüntüleme • 3 ay önce

GPT 5.4 is live on Blink! We built a Spotify-style global radio station with an equalizer for our evals and GPT 5.4 one-shotted it. We're giving away 20 Pro Plans ($50 - 200 creds). Reply GPT and we'll send you a code to try the new model today!

GPT 5.4 is live on Blink! We built a Spotify-style global radio station with an equalizer for our evals and GPT 5.4 one-shotted it. We're giving away 20 Pro Plans ($50 - 200 creds). Reply GPT and we'll send you a code to try the new model today!

Blink.new

22,375 görüntüleme • 3 ay önce

GPT-5.4 is my new default model for OpenClaw. For the last 2 months, Opus was the only model I felt could really unlock OpenClaw for serious agent tasks. GPT-5.4 is the first one that got close enough in quality to change that. In practice, it feels ~60% faster (73 tok/s vs 46), costs about half as much, and gives ~5x longer context. That combination makes OpenClaw much more snappy as a default. I tested it side by side against Opus 4.6 on deep research + slide generation, and the outputs are inspectable too. Full video below:

GPT-5.4 is my new default model for OpenClaw. For the last 2 months, Opus was the only model I felt could really unlock OpenClaw for serious agent tasks. GPT-5.4 is the first one that got close enough in quality to change that. In practice, it feels ~60% faster (73 tok/s vs 46), costs about half as much, and gives ~5x longer context. That combination makes OpenClaw much more snappy as a default. I tested it side by side against Opus 4.6 on deep research + slide generation, and the outputs are inspectable too. Full video below:

Quinn Leng

131,551 görüntüleme • 3 ay önce

Nobody seems to know how insane GPT-5.4 is with computer use. I asked GPT-5.4 to draw the OpenAI logo in Microsoft Paint. No computer use API. Just a screenshot and basic tool calls (click, drag, press_key) all coordinate-based. The first drawing was awful. And GPT knew it. It looked at its own result and essentially went "yeah, no." What happened next is what broke my brain: It opened a browser. Went to Bing Images. Searched for the OpenAI logo. Found one. Then (and I cannot stress this enough) it used the Windows area screenshot shortcut (Win+Shift+S) to snip just the logo off the screen. Went back to Paint. Imported it. Centered it. All on its own. No instructions to do any of that. It just improvised a better strategy when the first one failed. My prompt was "Draw the OpenAI logo" with Paint already opened on the computer. Sure, it's "cheating." But honestly? That's exactly what I'd do too. And the fact that it came up with this plan from nothing but a screenshot and a coordinate system is wild.

Clad3815

1,069,256 görüntüleme • 3 ay önce

I compared Claude Fable 5 to GPT-5.5 in this Power Rangers prompt Thing is, Fable 5 is using Low thinking effort and GPT-5.5 is using xhigh Safe to say, the results are... not even close. 5.5's output is bad across the board, from the UI to the actual voxel scene itself🥲 1st video: Claude Fable 5 (Low effort) 2nd video: GPT-5.5 (xhigh)

I compared Claude Fable 5 to GPT-5.5 in this Power Rangers prompt Thing is, Fable 5 is using Low thinking effort and GPT-5.5 is using xhigh Safe to say, the results are... not even close. 5.5's output is bad across the board, from the UI to the actual voxel scene itself🥲 1st video: Claude Fable 5 (Low effort) 2nd video: GPT-5.5 (xhigh)

Lentils

207,097 görüntüleme • 23 gün önce

Opus 4.6 vs GPT-5.4 (High) (6/9) Testing out how well these models to with cloth physics simulation, and honestly both where pretty close here but my god I am shocked how good GPT 5.4 is with optimizing this scene whilst opus 4.6 felt quite janky and lower fps. GPT 5.4 also got the cutting working properly whilst Opus was just floating about. I do want to heavily stress the fact that making this prompt, Opus 4.6 cost the whole 100% of the session ($20 pro plan) + $3 in credits whilst GPT 5.4 only cost 10% of the usage. prompt: Build a premium Vite + React interactive cloth simulation of a cozy room curtain using real particle/constraint physics, with structural + shear springs, damping, collisions, and stable real-time deformation. Users should be able to drag the curtain, add wind, and cut constraints, while the experience stays polished, visually elegant, and numerically stable.

Opus 4.6 vs GPT-5.4 (High) (6/9) Testing out how well these models to with cloth physics simulation, and honestly both where pretty close here but my god I am shocked how good GPT 5.4 is with optimizing this scene whilst opus 4.6 felt quite janky and lower fps. GPT 5.4 also got the cutting working properly whilst Opus was just floating about. I do want to heavily stress the fact that making this prompt, Opus 4.6 cost the whole 100% of the session ($20 pro plan) + $3 in credits whilst GPT 5.4 only cost 10% of the usage. prompt: Build a premium Vite + React interactive cloth simulation of a cozy room curtain using real particle/constraint physics, with structural + shear springs, damping, collisions, and stable real-time deformation. Users should be able to drag the curtain, add wind, and cut constraints, while the experience stays polished, visually elegant, and numerically stable.

Dev Ed

414,134 görüntüleme • 3 ay önce

Everyone keeps talking about the possibilities of making money with Openclaw, but nobody actually shows you how So, I made a skill for your Openclaw that transforms it into a one-man AI real estate marketing machine. This skill took me 2 weeks, 50+ hours and ~$800 in API credits to make With this skill, your Openclaw will autonomously make videos like the one below by simply scraping images from listings No approval gate. Fully autonomous. Output decided by your CRONs cadence. It's exactly what mine does, and that's exactly what you should be doing with yours. Run the CRON once a day; if you sell at least one video, you should make $300-$800 each. Also: total cost per video: ~$5.00 I truly believe this skill is one of the most practical ways you can actually make money with Openclaw in the lowest effort way possible. Most people will read this, maybe bookmark the tweet, and never take action. All I hope is that one of you guys actually takes action and makes money with this. Because of how long this skill took me to make, I'm only giving the entire thing away to my paid Subscribers on Twitter. You'll also have direct access to me for any troubleshooting + any other Skills I make like this in the future (one more dropping this week)! You just have to feed it to your Openclaw and link a few API keys. This will be the first of many Openclaw skills/overpowered AI that I only offer to my Subs! Full Skill + a lot more is waiting for you here for $25/m:

Everyone keeps talking about the possibilities of making money with Openclaw, but nobody actually shows you how So, I made a skill for your Openclaw that transforms it into a one-man AI real estate marketing machine. This skill took me 2 weeks, 50+ hours and ~$800 in API credits to make With this skill, your Openclaw will autonomously make videos like the one below by simply scraping images from listings No approval gate. Fully autonomous. Output decided by your CRONs cadence. It's exactly what mine does, and that's exactly what you should be doing with yours. Run the CRON once a day; if you sell at least one video, you should make $300-$800 each. Also: total cost per video: ~$5.00 I truly believe this skill is one of the most practical ways you can actually make money with Openclaw in the lowest effort way possible. Most people will read this, maybe bookmark the tweet, and never take action. All I hope is that one of you guys actually takes action and makes money with this. Because of how long this skill took me to make, I'm only giving the entire thing away to my paid Subscribers on Twitter. You'll also have direct access to me for any troubleshooting + any other Skills I make like this in the future (one more dropping this week)! You just have to feed it to your Openclaw and link a few API keys. This will be the first of many Openclaw skills/overpowered AI that I only offer to my Subs! Full Skill + a lot more is waiting for you here for $25/m:

ashen

22,822 görüntüleme • 3 ay önce

Opus 4.7 cs GPT 5.4 “make a flappy bird clone” I’ve been running this test for a few models now and this test was the hardest to objectively say who did better. Opus grabbed another version game assets compared to GPT 5.4, - GPT 5.4 however, grabbed the correct game assets. Opus 4.7 beat it on creativity where it grabbed assets (maybe unknowingly) that had a much more diverse set, including nighttime modes and different bird colors GPT 5.4 was able to get the pacing of the game the first shot, whereas Opus had the game running much too fast and then much too slow. But was able to place the metal perfectly in the game card at the end where GPT 5.4 struggled over 10 iterations. All in all both models had essentially made a near perfect game after three shots and are far ahead of the competition in terms of reasoning and effort.

Opus 4.7 cs GPT 5.4 “make a flappy bird clone” I’ve been running this test for a few models now and this test was the hardest to objectively say who did better. Opus grabbed another version game assets compared to GPT 5.4, - GPT 5.4 however, grabbed the correct game assets. Opus 4.7 beat it on creativity where it grabbed assets (maybe unknowingly) that had a much more diverse set, including nighttime modes and different bird colors GPT 5.4 was able to get the pacing of the game the first shot, whereas Opus had the game running much too fast and then much too slow. But was able to place the metal perfectly in the game card at the end where GPT 5.4 struggled over 10 iterations. All in all both models had essentially made a near perfect game after three shots and are far ahead of the competition in terms of reasoning and effort.

Chris

423,516 görüntüleme • 2 ay önce

This is a wonderful angle for the Kohli run-out. Tribute to athleticism, fitness and skill. One of the best you will see.

This is a wonderful angle for the Kohli run-out. Tribute to athleticism, fitness and skill. One of the best you will see.

Harsha Bhogle

1,201,874 görüntüleme • 2 yıl önce

One UI 8's latest version, ZYES, is the smoothest version I've ever experienced, smoother than all previous versions of One UI 7 and One UI 8. I can confirm that it has optimized the App startup animation again, making it more natural, smoother, and non-linear. Please watch the video I recorded. And the most important thing is that ZYES responds too fast. Watch my video, when I click the icons of One UI 8 and One UI 7 at the same time, you can see that the response speed of ZYES on the left is much faster. You know, One UI 7 already performed very well, and One UI 8 is obviously better. This shocked me, and I hope Samsung will continue to maintain it. Of course, some people will have some problems with this version. I think this may be because the cumulative number of installations is too many. I suggest that friends who have problems go back to the ZYDA version of One UI 7, and then directly install YDA→YEQ, and then install YEQ→YER and YER→YES in sequence. This is what I did, and I haven't found any bugs so far. You can also try this.

One UI 8's latest version, ZYES, is the smoothest version I've ever experienced, smoother than all previous versions of One UI 7 and One UI 8. I can confirm that it has optimized the App startup animation again, making it more natural, smoother, and non-linear. Please watch the video I recorded. And the most important thing is that ZYES responds too fast. Watch my video, when I click the icons of One UI 8 and One UI 7 at the same time, you can see that the response speed of ZYES on the left is much faster. You know, One UI 7 already performed very well, and One UI 8 is obviously better. This shocked me, and I hope Samsung will continue to maintain it. Of course, some people will have some problems with this version. I think this may be because the cumulative number of installations is too many. I suggest that friends who have problems go back to the ZYDA version of One UI 7, and then directly install YDA→YEQ, and then install YEQ→YER and YER→YES in sequence. This is what I did, and I haven't found any bugs so far. You can also try this.

PhoneArt

151,005 görüntüleme • 1 yıl önce