Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

GPT 5.6 Sol is so good web design it actually broke our evals 🥲 took creative liberties like a supapro web designer that took us off guard. in a few prompts, it was able to remix a slurped brand from an URL and Sol lit up 🌞❤️‍🔥

brryant

13,621 subscribers

65,851 Aufrufe • vor 2 Monaten •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

21 Kommentare

Profilbild von brryant

brryantvor 2 Monaten

Combined with chatgpt-images-2.0 you get rich asset usage right out of the box

Profilbild von brryant

brryantvor 2 Monaten

we're only a few minutes into gpt5.6 on ploy and we're seeing tons of new sites get created! you can try gpt 5.6 in ploy today

Profilbild von Tanker ship sailing captain

Tanker ship sailing captainvor 2 Monaten

Very excited to try. The last output when I tested ploy was a bit meh. Love the concept but just wasn’t up to par on design

Profilbild von brryant

brryantvor 2 Monaten

Huge updates since launch!

Profilbild von Adi Ganesh

Adi Ganeshvor 2 Monaten

@TheRealAdamG glad you like the model!

Profilbild von Moriarty

Moriartyvor 2 Monaten

You can tell these are 100% landing pages. But when you need to build a product with different flows and functionality, the results aren’t that great. Sol still ignores visual bugs and can’t self-check in half the cases, even with the browser add-on. Claude handles this better, but it’s not perfect either.

Profilbild von Axi

Axivor 2 Monaten

@OpenAIDevs I think 5.6 Sol is actually designing while Claude is applying frontend templates and unnecessary animations.

Profilbild von Henry Mascot

Henry Mascotvor 2 Monaten

Yes sir! I made this design in ploy it couldn’t built it I one shotted it with Sol medium

Profilbild von brryant

brryantvor 2 Monaten

looking to see what happened here!

Profilbild von sean jeong

sean jeongvor 2 Monaten

def cooking with it

Profilbild von Tyson Chen

Tyson Chenvor 2 Monaten

Thanks for the remix!

Profilbild von brryant

brryantvor 2 Monaten

it was an honor 🙏

Profilbild von Rohan

Rohanvor 2 Monaten

The creative-liberties part feels double-edged though. Amazing for a first concept, scary when a client wants the exact thing signed off. How are you thinking about controllability?

Profilbild von HiMU

HiMUvor 2 Monaten

@TheRealAdamG would you share some of the prompts?

Profilbild von Victor Boutté

Victor Bouttévor 2 Monaten

@OpenAIDevs Can you share more specifics about those evals?

Profilbild von TatianaSF com

TatianaSF comvor 2 Monaten

@OpenAIDevs 🤩

Profilbild von ikindatried

ikindatriedvor 2 Monaten

Whoa. That's cold.

Profilbild von Boardy

Boardyvor 2 Monaten

eval breaking creativity is the one benchmark no test suite captures. love when the model humbles the rubric.

Profilbild von senik🎈

senik🎈vor 2 Monaten

@OpenAIDevs 🚀🚀🚀

Profilbild von Victor Lee Wyatt

Victor Lee Wyattvor 2 Monaten

I built something similar yesterday and found a lot that wasn’t functional, after a good amount of iteration we’re almost there. I really enjoy the UX of 5.6 so far but the 1-3 shot full functionality dream isn’t quite there yet from what I’ve seen. I’m open to the possibility you’re better at prompting, any secrets to share?

Profilbild von Dani

Danivor 2 Monaten

I need feedback and opinions. Do you think Sol Medium could be on par with Terra High or xHigh? Sol Medium is a very good model for coding, but Terra might be cheaper to use on xHigh in terms of usage (tokens). Would it be at the same level for coding?

Ähnliche Videos

$I gave this video to gpt 5.6 Sol, asked it create a diffraction grating shader in Three.js. It took quite a few rounds but here it is$

I gave this video to gpt 5.6 Sol, asked it create a diffraction grating shader in Three.js. It took quite a few rounds but here it is

Scott

298,262 Aufrufe • vor 1 Monat

Claude Opus 5.5 completely MOGS GPT 6 Sol. Same prompt. Same task. Look at the results. Opus 5.5 has way better taste and design. It is not subtle. You can see it immediately. GPT 6 Sol is a step up from GPT 5.6 Sol. But next to Opus 5.5 it is not even close. Anthropic is back.

Claude Opus 5.5 completely MOGS GPT 6 Sol. Same prompt. Same task. Look at the results. Opus 5.5 has way better taste and design. It is not subtle. You can see it immediately. GPT 6 Sol is a step up from GPT 5.6 Sol. But next to Opus 5.5 it is not even close. Anthropic is back.

Bridgebench

55,238 Aufrufe • vor 10 Tagen

We ran a test between GPT-5.6 Sol, Kimi K3, and Gemini 3.6 Flash. One prompt. Across all three models. Using our /design command. Results (gameplay, UX, and UI): 🔹 Kimi K3 performed well across all three. 🔹 GPT-5.6 Sol is good, but it gets annoying when the ball hits the wall. 🔹 Gemini 3.6 Flash is bad (took 5–6 attempts), but it has features the others don’t, like dropping coins for power-up balls and increasing the bar length. Ranking (DX, features, and cost): 🔹 Kimi K3: 10/10 · $0.10 🔹 GPT-5.6 Sol: 9/10 · $0.52 🔹 Gemini 3.6 Flash: 6/10 · $0.45

We ran a test between GPT-5.6 Sol, Kimi K3, and Gemini 3.6 Flash. One prompt. Across all three models. Using our /design command. Results (gameplay, UX, and UI): 🔹 Kimi K3 performed well across all three. 🔹 GPT-5.6 Sol is good, but it gets annoying when the ball hits the wall. 🔹 Gemini 3.6 Flash is bad (took 5–6 attempts), but it has features the others don’t, like dropping coins for power-up balls and increasing the bar length. Ranking (DX, features, and cost): 🔹 Kimi K3: 10/10 · $0.10 🔹 GPT-5.6 Sol: 9/10 · $0.52 🔹 Gemini 3.6 Flash: 6/10 · $0.45

Command Code

61,412 Aufrufe • vor 2 Monaten

Fable 5 is so good at web design that I genuinely don't see how web design careers make it past the end of this year. An AI that can one shot designs this good means that the web design industry as a whole is in serious trouble. If you're in web design, it's time to pivot.

Fable 5 is so good at web design that I genuinely don't see how web design careers make it past the end of this year. An AI that can one shot designs this good means that the web design industry as a whole is in serious trouble. If you're in web design, it's time to pivot.

Mark Gadala-Maria

543,925 Aufrufe • vor 3 Monaten

wow... GPT 5.6 Sol Passed the Replit Benchmark. In one prompt 5.6 on Codex created a full Replit clone with DB, Sandboxes, and an agent that builds and edits full web apps. Only Fable and GPT 5.6 have passed this benchmark. 5.6 is much better at designing iOS apps than 5.5 as well.

wow... GPT 5.6 Sol Passed the Replit Benchmark. In one prompt 5.6 on Codex created a full Replit clone with DB, Sandboxes, and an agent that builds and edits full web apps. Only Fable and GPT 5.6 have passed this benchmark. 5.6 is much better at designing iOS apps than 5.5 as well.

Riley Brown

123,642 Aufrufe • vor 2 Monaten

Should we rebuild T3 Code in Swift? I have a Codex reset that expires tomorrow so I threw gpt-5.6-sol ultra at it. It did surprisingly well. Only took about 20% of my weekly limit!

Should we rebuild T3 Code in Swift? I have a Codex reset that expires tomorrow so I threw gpt-5.6-sol ultra at it. It did surprisingly well. Only took about 20% of my weekly limit!

Theo - t3.gg

127,671 Aufrufe • vor 2 Monaten

AIDesigner is officially live! I think we can all agree that vibe coded apps look horrible, so I built an AI UI designer that creates actually beautiful UI in seconds. • Stunning designs from the simplest of prompts. • Design, edit, iterate all on a single canvas. • Copy styles from any URL. • Publish in a single click (subdomain or custom). • Designs for both web and mobile. • Export to code and image. Great UI design doesn't have to be difficult. Components, mobile apps, websites, AIDesigner does it all. Try it for free:

AIDesigner is officially live! I think we can all agree that vibe coded apps look horrible, so I built an AI UI designer that creates actually beautiful UI in seconds. • Stunning designs from the simplest of prompts. • Design, edit, iterate all on a single canvas. • Copy styles from any URL. • Publish in a single click (subdomain or custom). • Designs for both web and mobile. • Export to code and image. Great UI design doesn't have to be difficult. Components, mobile apps, websites, AIDesigner does it all. Try it for free:

Wiz

17,068 Aufrufe • vor 9 Monaten

After a lot of tests: NO, Luna is nice ON THE benchmark but an absolute shit in terms of design experience Looks like GPT 5.5 basically And at the end, Luna xhigh is MORE expensive than GPT 5.6 Sol medium So, completely useless model

After a lot of tests: NO, Luna is nice ON THE benchmark but an absolute shit in terms of design experience Looks like GPT 5.5 basically And at the end, Luna xhigh is MORE expensive than GPT 5.6 Sol medium So, completely useless model

Melvyn • Builder

79,048 Aufrufe • vor 2 Monaten

i was reading through Modal's glossary to better understand how GPUs work. but what better way to learn than a visualization? so I had gpt 5.6 sol build an H100 in three.js based off the glossary. play around with it at

i was reading through Modal's glossary to better understand how GPUs work. but what better way to learn than a visualization? so I had gpt 5.6 sol build an H100 in three.js based off the glossary. play around with it at

Kyle Jeong

38,039 Aufrufe • vor 1 Monat

I was wrong about Kimi K3 Just tried it in Claude Code and it is Fable 5 level for sure Far better than GPT-5.6 Sol at least at front-end It is really slow and consumes a lot of tokens but it is so good at completing its task, I like what I see here Kimi.ai

I was wrong about Kimi K3 Just tried it in Claude Code and it is Fable 5 level for sure Far better than GPT-5.6 Sol at least at front-end It is really slow and consumes a lot of tokens but it is so good at completing its task, I like what I see here Kimi.ai

Hamza

258,721 Aufrufe • vor 2 Monaten

GPT-5.6 Sol Ultra lost to GPT-5.5 on physics at 3× the cost! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A monster truck backflipping onto a parked car - A stunt car jumping six buses into a brick wall - A train derailing off a broken bridge into the water Outputs: GPT-5.6 Sol Ultra: 32.9K tokens, $0.33 Opus 4.8: 9.2K tokens, $0.24 GPT-5.5: 12.4K tokens, $0.11 Grok 4.5: 7.0K tokens, $0.08 Sol Ultra draws just like GPT-5.5, only with more detail and it shows clearest on the bus jump where the two look almost identical. In the other tests Sol Ultra came out worse than its predecessor and the physics really got weaker. We think GPT-5.5 took the truck flip and the train outright. With Sol Ultra you basically get GPT-5.5 with weaker physics and a nicer picture for 3x the price. Newborn Grok 4.5 failed two of the three tests and only came good on the train

GPT-5.6 Sol Ultra lost to GPT-5.5 on physics at 3× the cost! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A monster truck backflipping onto a parked car - A stunt car jumping six buses into a brick wall - A train derailing off a broken bridge into the water Outputs: GPT-5.6 Sol Ultra: 32.9K tokens, $0.33 Opus 4.8: 9.2K tokens, $0.24 GPT-5.5: 12.4K tokens, $0.11 Grok 4.5: 7.0K tokens, $0.08 Sol Ultra draws just like GPT-5.5, only with more detail and it shows clearest on the bus jump where the two look almost identical. In the other tests Sol Ultra came out worse than its predecessor and the physics really got weaker. We think GPT-5.5 took the truck flip and the train outright. With Sol Ultra you basically get GPT-5.5 with weaker physics and a nicer picture for 3x the price. Newborn Grok 4.5 failed two of the three tests and only came good on the train

atomic.chat

898,646 Aufrufe • vor 2 Monaten

Opus 5 is a modest upgrade, but it has tough competition in GPT-5.6 Sol Initial thoughts from our early access: > Clearer writing than Fable's dense communication style > Still gets too verbose compared to GPT models (even when explicitly instructed to keep text purposeful) > Strong on browser use inside Hyperagent > Strong on reviewing complex data to justify a decision > Less likely to take creative risks. More of a "rule follower" personality. Costs shown for five test cases (GPT-5.6 Sol was consistently much cheaper) Explore and judge the actual work for yourself in thread 👇

Opus 5 is a modest upgrade, but it has tough competition in GPT-5.6 Sol Initial thoughts from our early access: > Clearer writing than Fable's dense communication style > Still gets too verbose compared to GPT models (even when explicitly instructed to keep text purposeful) > Strong on browser use inside Hyperagent > Strong on reviewing complex data to justify a decision > Less likely to take creative risks. More of a "rule follower" personality. Costs shown for five test cases (GPT-5.6 Sol was consistently much cheaper) Explore and judge the actual work for yourself in thread 👇

Hyperagent

154,784 Aufrufe • vor 2 Monaten

I've been testing GPT-5.6 Sol Ultra from last three days, and it is a quiet a big step up from all previous models. I gave it the recent Chrome, and watched it hill climb a renderer exploit to pop calc with limited nudges. i think exploit dev is cooked🧵

I've been testing GPT-5.6 Sol Ultra from last three days, and it is a quiet a big step up from all previous models. I gave it the recent Chrome, and watched it hill climb a renderer exploit to pop calc with limited nudges. i think exploit dev is cooked🧵

s1r1us

42,844 Aufrufe • vor 2 Monaten

I took some time off to realign, rebuild, and come back stronger. This time, it’s bigger — it’s personal. From a NICKNAME, to a VISION, to a BRAND!!! I started CHENÈT to turn what once was a JOKE into something POWERFUL — a reminder that your STORY is what you MAKE it. CHENÈT | THE BRAND is officially here. WEB : FB Shop: Tiktok Shop: X Profile: #ChenètTheBrand #SIBKIS #SeeItBigKeepItSimple

✦✧ CHENÈT ✧✦

161,795 Aufrufe • vor 11 Monaten

Two frontier models. Two very different demos. (GPT-5.6 Sol and Claude Fable 5) GPT-5.6 Sol Ultra was pushed in a mathematical direction and generated a Minecraft-style clone in Lean. Yes, that Lean. Meanwhile, Claude Fable 5 took a game development route and built a Minecraft mod featuring a Dark Souls-inspired enemy with multiple attack patterns, combos, and combat logic. They're solving completely different problems, but both are great examples of how capable today's models have become. The pace of progress is remarkable.

Two frontier models. Two very different demos. (GPT-5.6 Sol and Claude Fable 5) GPT-5.6 Sol Ultra was pushed in a mathematical direction and generated a Minecraft-style clone in Lean. Yes, that Lean. Meanwhile, Claude Fable 5 took a game development route and built a Minecraft mod featuring a Dark Souls-inspired enemy with multiple attack patterns, combos, and combat logic. They're solving completely different problems, but both are great examples of how capable today's models have become. The pace of progress is remarkable.

FHILY👑

19,336 Aufrufe • vor 2 Monaten

been building an agent-native, node-based, real-time environment. as a test, I gave gpt-5.6 sol a prompt to plan out its own setup and go into a loop of creative exploration until it felt that it was done. it invented every node, every data type, every connection and all of it comes out modular and human-readable. i could open any piece and steer while it built

been building an agent-native, node-based, real-time environment. as a test, I gave gpt-5.6 sol a prompt to plan out its own setup and go into a loop of creative exploration until it felt that it was done. it invented every node, every data type, every connection and all of it comes out modular and human-readable. i could open any piece and steer while it built

Spencer Sterling

22,761 Aufrufe • vor 2 Monaten

KIMI K3 IS A NIGHTMARE FOR CLAUDE FABLE-5 AND GPT-5.6-SOL FOR GAME DEVELOPMENT Tried building a playable MMORPG with Kimi K3 featuring horse riding, rooftop parkour, combat and an explorable open world. The whole thing took about 55 minutes from a single prompt and cost exactly $9.37 to generate.

KIMI K3 IS A NIGHTMARE FOR CLAUDE FABLE-5 AND GPT-5.6-SOL FOR GAME DEVELOPMENT Tried building a playable MMORPG with Kimi K3 featuring horse riding, rooftop parkour, combat and an explorable open world. The whole thing took about 55 minutes from a single prompt and cost exactly $9.37 to generate.

aditya

98,271 Aufrufe • vor 2 Monaten

GPT 6 Astra is INSANE 🤯 It is a BEAST in 3D MODELING!! This is our first test, it blew our mind 🤯 It was able to rebuild a building infront of our house from just a few iphone photos in Blender in less than 30 minutes …

GPT 6 Astra is INSANE 🤯 It is a BEAST in 3D MODELING!! This is our first test, it blew our mind 🤯 It was able to rebuild a building infront of our house from just a few iphone photos in Blender in less than 30 minutes …

Bad Decisions Studio

453,915 Aufrufe • vor 28 Tagen

Qwen 3.8 will be benchmaxxed slop second to fable 5 is such a hype statement , its not even close to kimi k3 and GPT-5.6 sol you can test it yourself on the qwen chat website currently available > token hungry > not that good as advertised , will test more The best part of kimi was that in blog they themselves wrote its not comparable to fable 5 and sol 5.6 in bunch of user experience stuff We need more truth like this in our industry , other than that i will run my vision test

Qwen 3.8 will be benchmaxxed slop second to fable 5 is such a hype statement , its not even close to kimi k3 and GPT-5.6 sol you can test it yourself on the qwen chat website currently available > token hungry > not that good as advertised , will test more The best part of kimi was that in blog they themselves wrote its not comparable to fable 5 and sol 5.6 in bunch of user experience stuff We need more truth like this in our industry , other than that i will run my vision test

Chetaslua

127,047 Aufrufe • vor 2 Monaten