Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

OpenAI's new GPT-5.1-Codex-Max (Extra-High) - more advanced Golden Gate Bridge prompt with a couple of turns of 5-7 minutes each. This is definitely the best I ever got out of this type of prompt by far.

petergostev's profile picture

Peter Gostev (Visiting SF)

9,959 subscribers

198,884 görüntüleme • 8 ay önce •via X (Twitter)

EğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Qwen 3.7 Max can do some zero shots! Zombie apocalypse auto car battler with one prompt. This is definitely gpt 5.5 level of what I was seeing! Sorry but will probably spam a bunch of these tests today.
0:34

Qwen 3.7 Max can do some zero shots! Zombie apocalypse auto car battler with one prompt. This is definitely gpt 5.5 level of what I was seeing! Sorry but will probably spam a bunch of these tests today.

Loktar 🇺🇸

11,625 görüntüleme • 2 ay önce

Alright, here's a side-by-side comparison of OpenAI's new Codex vs Codebuff Codex took 5 minutes and didn't implement the client side of my request 😢 Codebuff took 1 minute and got it right! 🔥
5:17

Alright, here's a side-by-side comparison of OpenAI's new Codex vs Codebuff Codex took 5 minutes and didn't implement the client side of my request 😢 Codebuff took 1 minute and got it right! 🔥

James Grugett

43,750 görüntüleme • 1 yıl önce

How do the Top 10 open models really compare? We ran the “SF sea lion in front of the Golden Gate Bridge, as an SVG” test to find out. Prompt: “SVG sea-lion balancing a beach ball on its nose with the Golden Gate bridge in the background”
0:25

How do the Top 10 open models really compare? We ran the “SF sea lion in front of the Golden Gate Bridge, as an SVG” test to find out. Prompt: “SVG sea-lion balancing a beach ball on its nose with the Golden Gate bridge in the background”

lmarena.ai

13,527 görüntüleme • 8 ay önce

I've paid for Cursor again to test this - not hugely impressed. Did 5x tries of my Golden Gate Bridge prompt, 2x were ok, 3 were terrible. Left in Google's upcoming Gemini 3 Pro and GPT-5, GPT-5 and Sonnet 4.5 in there for comparison - all are much better.
1:17

I've paid for Cursor again to test this - not hugely impressed. Did 5x tries of my Golden Gate Bridge prompt, 2x were ok, 3 were terrible. Left in Google's upcoming Gemini 3 Pro and GPT-5, GPT-5 and Sonnet 4.5 in there for comparison - all are much better.

Peter Gostev

206,844 görüntüleme • 9 ay önce

The new 2026 AI workflow is going to destroy the old way of prototyping games. Workflow: GPT Image 2.0: cinematic + asset sheet Codex: “make this image playable” Prompt below 👇
0:34

The new 2026 AI workflow is going to destroy the old way of prototyping games. Workflow: GPT Image 2.0: cinematic + asset sheet Codex: “make this image playable” Prompt below 👇

Givros

36,852 görüntüleme • 2 ay önce

This is hands down the best clone of Minecraft I've ever seen This was built using multiple frontier coding models: Gemini 3 Pro, GPT 5.1 Codex, and Claude Opus 4.1. Switching between multiple models is such a superpower
0:23

This is hands down the best clone of Minecraft I've ever seen This was built using multiple frontier coding models: Gemini 3 Pro, GPT 5.1 Codex, and Claude Opus 4.1. Switching between multiple models is such a superpower

Aryan Vichare

93,980 görüntüleme • 8 ay önce

i recreated this with GPT 5.6 Sol & it costed me ~$5 only & 2 prompts >GPT 5.6 Sol Ultra as the main agent, admin & orchestrator >GPT 5.6 Luna Max as sub-agents >used the Codex app >used about 20% of my weekly limit on $100 plan ($100/4 * 20%) some bugs, and improvements would take another prompt but pretty good for $5!
1:00

i recreated this with GPT 5.6 Sol & it costed me ~$5 only & 2 prompts >GPT 5.6 Sol Ultra as the main agent, admin & orchestrator >GPT 5.6 Luna Max as sub-agents >used the Codex app >used about 20% of my weekly limit on $100 plan ($100/4 * 20%) some bugs, and improvements would take another prompt but pretty good for $5!

anul agarwal

15,718 görüntüleme • 7 gün önce

I had a great time chatting with three of Anthropic's top prompt engineers: Amanda Askell, Zack Witten, and David Hershey. We covered a few topics like: - what makes a good prompt engineer - practical tips for writing better prompts - what's happening inside an LLM - jailbreaks - the future of prompt engineering - and more If you want to understand how we think about prompt engineering, this may be the best resource out there. Here's the entire one hour and sixteen minutes of our conversation. Enjoy!
1:16:42

I had a great time chatting with three of Anthropic's top prompt engineers: Amanda Askell, Zack Witten, and David Hershey. We covered a few topics like: - what makes a good prompt engineer - practical tips for writing better prompts - what's happening inside an LLM - jailbreaks - the future of prompt engineering - and more If you want to understand how we think about prompt engineering, this may be the best resource out there. Here's the entire one hour and sixteen minutes of our conversation. Enjoy!

Alex Albert

333,662 görüntüleme • 1 yıl önce

ChatGPT is overhyped. This is what I told myself after months of trying (and failing) to use it well. Turns out, I was just a poor prompt writer. Now, I have these 7 prompts to upgrade any piece of writing:
1:29

ChatGPT is overhyped. This is what I told myself after months of trying (and failing) to use it well. Turns out, I was just a poor prompt writer. Now, I have these 7 prompts to upgrade any piece of writing:

Dickie Bush 🚢

11,851 görüntüleme • 1 yıl önce

Models like GPT 5.6 or Fable 5 are accelerating the commodification of software. For instance, I gave Fable a screenshot of the Stripe, OpenAI, and Anthropic websites with a simple prompt: “Create a pixel-perfect reproduction of this website.” It took only seconds and a simple prompt to duplicate the design. This is exciting because there are so many poorly designed websites, but now they are just a prompt away from achieving world-class design!!
0:27

Models like GPT 5.6 or Fable 5 are accelerating the commodification of software. For instance, I gave Fable a screenshot of the Stripe, OpenAI, and Anthropic websites with a simple prompt: “Create a pixel-perfect reproduction of this website.” It took only seconds and a simple prompt to duplicate the design. This is exciting because there are so many poorly designed websites, but now they are just a prompt away from achieving world-class design!!

Nicolas Bustamante

37,754 görüntüleme • 1 ay önce

Kind of shocking how much better GPT-5-Codex is vs the regular 'Thinking' models in ChatGPT. My subjective rankings for the fruit machine test: 1. GPT-5-Codex-Medium 2. GPT-5-Thinking-Heavy 3. GPT-5-Pro 4. GPT-5-Codex-High 5. GPT-5-Codex-Low 6. GPT-5-Thinking-Standard 7. GPT-5-Thinking-Extended 8. GPT-5-Thinking-Light OpenAI Codex team have suggested 'Medium' should be the default, but I didn't expect that it would actually beat the 'High' setting model in my test.
0:44

Kind of shocking how much better GPT-5-Codex is vs the regular 'Thinking' models in ChatGPT. My subjective rankings for the fruit machine test: 1. GPT-5-Codex-Medium 2. GPT-5-Thinking-Heavy 3. GPT-5-Pro 4. GPT-5-Codex-High 5. GPT-5-Codex-Low 6. GPT-5-Thinking-Standard 7. GPT-5-Thinking-Extended 8. GPT-5-Thinking-Light OpenAI Codex team have suggested 'Medium' should be the default, but I didn't expect that it would actually beat the 'High' setting model in my test.

Peter Gostev

101,848 görüntüleme • 10 ay önce

I ran the same prompt through Fable (in CC) at different reasoning levels, low effort too 12 minutes, max effort took nearly 2 hours. Prompt and the hosted version of this video below
0:55

I ran the same prompt through Fable (in CC) at different reasoning levels, low effort too 12 minutes, max effort took nearly 2 hours. Prompt and the hosted version of this video below

Peter Gostev

70,812 görüntüleme • 1 ay önce

New Golden Gate SOTA: GPT-5.1-Pro! I want to stress that this was _NOT_ one shot - in fact it was many different iterations in 3 different chats. I loved the way it did the water, night sky and the clouds, but it took a lot of back & forth to get the details right - traffic, colours, land. It was quite frustrating that GPT-5.1-Pro wasn't following the instructions after a few steps - it seems like it was struggling to combine the different reasoning threads into a single correct one. But still, this is the best result I got so far.
0:36

New Golden Gate SOTA: GPT-5.1-Pro! I want to stress that this was _NOT_ one shot - in fact it was many different iterations in 3 different chats. I loved the way it did the water, night sky and the clouds, but it took a lot of back & forth to get the details right - traffic, colours, land. It was quite frustrating that GPT-5.1-Pro wasn't following the instructions after a few steps - it seems like it was struggling to combine the different reasoning threads into a single correct one. But still, this is the best result I got so far.

Peter Gostev

100,088 görüntüleme • 8 ay önce

Made with Veo 3.1 This is my first set of tests with Veo 3.1 inside Flow by Google This was a combination of image and text to video I'm noticing more dynamic motion and the new Expand prompt feature is pretty clutch. More soon.
0:52

Made with Veo 3.1 This is my first set of tests with Veo 3.1 inside Flow by Google This was a combination of image and text to video I'm noticing more dynamic motion and the new Expand prompt feature is pretty clutch. More soon.

Dave Clark

84,201 görüntüleme • 9 ay önce

This is what happens when you prompt codex to generate an electronic device with tscircuit None of these boards were edited. No follow up prompts were allowed. Codex always started from scratch from a two sentence prompt.
3:10

This is what happens when you prompt codex to generate an electronic device with tscircuit None of these boards were edited. No follow up prompts were allowed. Codex always started from scratch from a two sentence prompt.

Seve

14,897 görüntüleme • 3 ay önce

A lot of people shat on GPT-5 when it came out All of those people are wrong. GPT-5 is actually insanely good. It just requires a different style of prompting than any other model If you prompt it correctly, it's the best AI model out there Here's exactly how to do that:
21:52

A lot of people shat on GPT-5 when it came out All of those people are wrong. GPT-5 is actually insanely good. It just requires a different style of prompting than any other model If you prompt it correctly, it's the best AI model out there Here's exactly how to do that:

Alex Finn

19,286 görüntüleme • 11 ay önce

Fable 5 vs GPT 5.5 tested both on High settings with the same prompt > Fable one shotted everything in 15 minutes and used 3% of weekly limits > GPT 5.5 took 20 minutes and used 3% of weekly limits 5.5 is not looking good here at all which one do you think won?
0:29

Fable 5 vs GPT 5.5 tested both on High settings with the same prompt > Fable one shotted everything in 15 minutes and used 3% of weekly limits > GPT 5.5 took 20 minutes and used 3% of weekly limits 5.5 is not looking good here at all which one do you think won?

J A Z I I

107,777 görüntüleme • 2 ay önce

Introducing Ideogram 1.0: the most advanced text-to-image model, now available on This offers state-of-the-art text rendering, unprecedented photorealism, exceptional prompt adherence, and a new feature called Magic Prompt to help with prompting.
1:00

Introducing Ideogram 1.0: the most advanced text-to-image model, now available on This offers state-of-the-art text rendering, unprecedented photorealism, exceptional prompt adherence, and a new feature called Magic Prompt to help with prompting.

Ideogram

256,099 görüntüleme • 2 yıl önce

Claude Opus 5 just one-shotted this FPS. Less than 1 hour from prompt to playable demo. Every weapon, enemy, mechanic and environment was generated from scratch. Prompt below 👇 There is no prompt below, because the first section is exactly the kind of post I’m tired of seeing every time a new model drops. A flashy demo, “one-shot” in the caption, “built in under an hour”… anything to farm impressions while conveniently hiding the actual process. If it was really made from a single prompt, show the prompt. That’s what I do on this account. When I claim something is a one-prompt prototype built with GPT-5.6 Sol Ultra and Codex, I share the prompt publicly so anyone can verify it. AI is already making game prototyping incredible. We don’t need fake “one-shot” stories to prove it. Original footage:
0:36

Claude Opus 5 just one-shotted this FPS. Less than 1 hour from prompt to playable demo. Every weapon, enemy, mechanic and environment was generated from scratch. Prompt below 👇 There is no prompt below, because the first section is exactly the kind of post I’m tired of seeing every time a new model drops. A flashy demo, “one-shot” in the caption, “built in under an hour”… anything to farm impressions while conveniently hiding the actual process. If it was really made from a single prompt, show the prompt. That’s what I do on this account. When I claim something is a one-prompt prototype built with GPT-5.6 Sol Ultra and Codex, I share the prompt publicly so anyone can verify it. AI is already making game prototyping incredible. We don’t need fake “one-shot” stories to prove it. Original footage:

Givros

14,794 görüntüleme • 14 gün önce

Make a few more of these ... Make a LOT more of these ... Gemini 2.0 native image output is enabling a new way to prompt: instructing with image and text together. Subtle shifts in how I draw change how Gemini interprets the same text prompt.
0:41

Make a few more of these ... Make a LOT more of these ... Gemini 2.0 native image output is enabling a new way to prompt: instructing with image and text together. Subtle shifts in how I draw change how Gemini interprets the same text prompt.

Alexander Chen

23,601 görüntüleme • 1 yıl önce