Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Creating physics simulations for education is a lot fun with GPT-4.1. Been experimenting via Windsurf and as Varun Mohan mentioned in the livestream, the difference shows. GPT-4.1 reads fewer unnecessary files, writes fewer junk changes, and doesn’t blabber as much.

Parul Pandey

8,199 subscribers

84,719 views • 1 year ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

7 Comments

Kevin Hou1 year ago

@windsurf_ai @_mohansolo whoa this is awesome

opolsce1 year ago

@windsurf_ai @_mohansolo

Ty1 year ago

@windsurf_ai @_mohansolo Totally agree. I almost have to nudge it a little bit to make it do a command. The precision is noticeable though!

PDF GPT2 years ago

This is my favorite AI tool for reviewing reports. Just upload a report, ask for a summary, and get one in seconds. It's like ChatGPT, but built for documents. Try it for free.

jake1 year ago

@windsurf_ai @_mohansolo Damn.

Mahali1 year ago

@windsurf_ai @_mohansolo This is crazy. 👌🏽

AChang1 year ago

@windsurf_ai @_mohansolo @HuoQubot

Related Videos

Thanks @openai for having me on the GPT-4.1 announcement livestream this morning! We've been testing 4.1 for the past couple weeks -- it's really good. And now, it's available in Windsurf. It's free for all users this week and will be discounted after. Go give it a try!

Thanks @openai for having me on the GPT-4.1 announcement livestream this morning! We've been testing 4.1 for the past couple weeks -- it's really good. And now, it's available in Windsurf. It's free for all users this week and will be discounted after. Go give it a try!

Varun Mohan

286,771 views • 1 year ago

Opus 4.8 for planning 🤝 GPT 5.5 for implementation Claude is a nicer conversation and /grilling partner than Codex in my experience, but GPT 5.5 on low cranks out higher quality code in fewer tokens. Here's how I divide up the work:

Opus 4.8 for planning 🤝 GPT 5.5 for implementation Claude is a nicer conversation and /grilling partner than Codex in my experience, but GPT 5.5 on low cranks out higher quality code in fewer tokens. Here's how I divide up the work:

Ben Holmes

23,105 views • 1 month ago

GPT-5 thinking has been incredible at coding so far i'm not a big fan of vibe coding, but just tried a "browser OS" test in one shot - gemini 2.5 pro failed - claude 4.1 handled flow better, but not as good overall - gpt-5 nailed it, and added all the standard features DEMO 👇

GPT-5 thinking has been incredible at coding so far i'm not a big fan of vibe coding, but just tried a "browser OS" test in one shot - gemini 2.5 pro failed - claude 4.1 handled flow better, but not as good overall - gpt-5 nailed it, and added all the standard features DEMO 👇

Haider.

43,656 views • 11 months ago

OpenAI researcher, Michelle Pokrass: the challenge in building GPT‑5 is finding the right balance between reasoning and conversation. o3 thinks hard, but it isn't ideal for casual chat. GPT‑4.1 improved at coding by sacrificing some chit-chat quality. now, the goal is to train a model that knows when to think hard and when to talk

OpenAI researcher, Michelle Pokrass: the challenge in building GPT‑5 is finding the right balance between reasoning and conversation. o3 thinks hard, but it isn't ideal for casual chat. GPT‑4.1 improved at coding by sacrificing some chit-chat quality. now, the goal is to train a model that knows when to think hard and when to talk

Haider.

195,733 views • 1 year ago

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 and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

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 and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

Peter Gostev

257,111 views • 4 months ago

Congratulations to Varun Mohan, and the entire Windsurf team. Windsurf has become mission-critical for top engineering teams and opened up software creation to anyone with an idea. Proud to back this team as they continue to make history in how software gets built. A little throwback... ⬇️

Congratulations to Varun Mohan, and the entire Windsurf team. Windsurf has become mission-critical for top engineering teams and opened up software creation to anyone with an idea. Proud to back this team as they continue to make history in how software gets built. A little throwback... ⬇️

Kleiner Perkins

57,875 views • 1 year ago

.OpenAI's GPT-5.1 is live in Cline. After testing the last several weeks, here's what we've found makes GPT-5.1 an exceptional model in Cline: GPT-5.1 is an obsessive researcher. It reads everything before writing anything. Where other models grab context and go, GPT-5.1 investigates thoroughly first, even for one-line changes. We found this overkill for simple tasks, and modified GPT-5.1's prompting resultantly, but a superpower when channeled right. Here's what you should expect from GPT-5.1 in Cline: > deep, systematic investigation before any edits > follows constraints religiously (specs, todo lists, your requirements) > maintains coherent reasoning with large contexts > delivers complete features with fewer corrections How we optimized Cline for GPT-5.1: 1. redesigned prompts for execution focus and stricter Plan/Act transitions 2. tightened tool specs, GPT-5.1 internalizes rules with just single examples 3. split /deep-planning investigation into two phases (read first, then search) Result: GPT-5.1 is a model that finishes what it starts, even across dozens of files and thousands of lines. Both GPT-5.1 (272K context) and GPT-5.1-codex (400K context) available now in Cline. $1.25/M input, $10/M output. Enable native tool calling in settings for best results. Use /deep-planning to see GPT-5.1 at its best. Full technical breakdown linked below.

.OpenAI's GPT-5.1 is live in Cline. After testing the last several weeks, here's what we've found makes GPT-5.1 an exceptional model in Cline: GPT-5.1 is an obsessive researcher. It reads everything before writing anything. Where other models grab context and go, GPT-5.1 investigates thoroughly first, even for one-line changes. We found this overkill for simple tasks, and modified GPT-5.1's prompting resultantly, but a superpower when channeled right. Here's what you should expect from GPT-5.1 in Cline: > deep, systematic investigation before any edits > follows constraints religiously (specs, todo lists, your requirements) > maintains coherent reasoning with large contexts > delivers complete features with fewer corrections How we optimized Cline for GPT-5.1: 1. redesigned prompts for execution focus and stricter Plan/Act transitions 2. tightened tool specs, GPT-5.1 internalizes rules with just single examples 3. split /deep-planning investigation into two phases (read first, then search) Result: GPT-5.1 is a model that finishes what it starts, even across dozens of files and thousands of lines. Both GPT-5.1 (272K context) and GPT-5.1-codex (400K context) available now in Cline. $1.25/M input, $10/M output. Enable native tool calling in settings for best results. Use /deep-planning to see GPT-5.1 at its best. Full technical breakdown linked below.

Cline

72,096 views • 8 months ago

Here is a short video preview of the new ChatGPT Prototype - Gizmo V8. The feature previously known as "Magic Maker" for creating new GPTs is now called "GPT Builder". It seems that the "Welcome Message" has been removed, and GPT Builder can now also generate profile pictures for the new GPTs using DALL-E.

Tibor Blaho

222,818 views • 2 years ago

It is now way easier to build multi-agent workflows in n8n with the new AI Agent Tool node. Instead of juggling sub workflows a parent AI Agent can now use other Agents as tools even several layers deep. Max shows how a cheap GPT 4.1 nano Agent handles heavy data and sends summaries to a parent Agent saving token costs and making debugging simpler. Watch the full walkthrough:

It is now way easier to build multi-agent workflows in n8n with the new AI Agent Tool node. Instead of juggling sub workflows a parent AI Agent can now use other Agents as tools even several layers deep. Max shows how a cheap GPT 4.1 nano Agent handles heavy data and sends summaries to a parent Agent saving token costs and making debugging simpler. Watch the full walkthrough:

n8n.io

27,766 views • 11 months ago

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 views • 2 months ago

🇺🇦 Dnepropetrovsk is clogged with garbage as truck drivers stay home out of fear of being drafted "There are fewer and fewer garbage truck drivers. The garbage is simply growing in a conditionally geometric progression"

🇺🇦 Dnepropetrovsk is clogged with garbage as truck drivers stay home out of fear of being drafted "There are fewer and fewer garbage truck drivers. The garbage is simply growing in a conditionally geometric progression"

Lord Bebo

19,246 views • 6 months ago

I hooked up an iOS shortcut to GPT-4 and GitHub. Here’s how it works: - identifies the repo - identifies the target files - writes the code for me - creates a branch - commits changes Now I can code right on my Apple Watch with nothing but my voice!

I hooked up an iOS shortcut to GPT-4 and GitHub. Here’s how it works: - identifies the repo - identifies the target files - writes the code for me - creates a branch - commits changes Now I can code right on my Apple Watch with nothing but my voice!

Mckay Wrigley

1,283,885 views • 3 years ago

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

891,503 views • 5 days ago

GPT Image 2 is actually insane I made this video with the images from it and it looks so much better than NBP but imo NBP is still way better GPT was a pain in the arse to work with >Constant NSFW tags (on gym pics) >Cant create backgrounds like NBP >Cant swap characters as good as NBP >Less consistent So yeh I’ll be sticking with NBP for now Im going to test making the back grounds and character swaps in NBP then changing them to higher quality with GPT though

GPT Image 2 is actually insane I made this video with the images from it and it looks so much better than NBP but imo NBP is still way better GPT was a pain in the arse to work with >Constant NSFW tags (on gym pics) >Cant create backgrounds like NBP >Cant swap characters as good as NBP >Less consistent So yeh I’ll be sticking with NBP for now Im going to test making the back grounds and character swaps in NBP then changing them to higher quality with GPT though

Pounds

41,888 views • 2 months ago

“We noticed that along with extended thinking, with GPT-5.5, we were able to do something that we didn't think was possible,” Shopify’s goal is to have more entrepreneurs in the world and the way they do that is by removing as much friction as possible from the builder journey. There was life before Shopify with GPT-5.5, and after. We prefer after. ✨

“We noticed that along with extended thinking, with GPT-5.5, we were able to do something that we didn't think was possible,” Shopify’s goal is to have more entrepreneurs in the world and the way they do that is by removing as much friction as possible from the builder journey. There was life before Shopify with GPT-5.5, and after. We prefer after. ✨

Farhan Thawar

13,857 views • 20 days ago

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

Chris

228,126 views • 26 days ago

"Reform is a project built on accelerating the concentration of wealth in fewer and fewer hands, while simultaneously blaming all of the bad stuff that happens as a result of that on the most vulnerable." After Matt Goodwin was announced as the Reform candidate for the Gorton and Denton byelection, Kieran Andrieu explains on Novara Live why the GB News host is joining a group of "dangerous snake oil salesmen".

"Reform is a project built on accelerating the concentration of wealth in fewer and fewer hands, while simultaneously blaming all of the bad stuff that happens as a result of that on the most vulnerable." After Matt Goodwin was announced as the Reform candidate for the Gorton and Denton byelection, Kieran Andrieu explains on Novara Live why the GB News host is joining a group of "dangerous snake oil salesmen".

Novara Media

11,119 views • 5 months ago

‼️‘I think what we have to learn from Argentina is that we must fight against communism and the left without doubt and without hesitation. Fight, fight, fight — as Trump said. It’s difficult to work with fewer resources and fewer people, but we have the most valuable things: the truth and the best ideas. The ideas of progress, of capitalism. We have a lot of work to do in Europe.’Javier Negre EDATV

‼️‘I think what we have to learn from Argentina is that we must fight against communism and the left without doubt and without hesitation. Fight, fight, fight — as Trump said. It’s difficult to work with fewer resources and fewer people, but we have the most valuable things: the truth and the best ideas. The ideas of progress, of capitalism. We have a lot of work to do in Europe.’Javier Negre EDATV

Scarlett Karoleva

14,898 views • 1 year ago