Loading video...

Video Failed to Load

Go Home

Shipped a multiplayer game in 12 days. Never wrote Rust before. YeeBall is real-time, works on phone, supports tons of concurrent games. Opus 4.5 for planning. GPT-5.2 for implementation. All inside Cursor. The planning technique is what made it possible.

RayFernando1337's profile picture

Ray Fernando

36,095 subscribers

13,719 views • 5 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

GPT 5.2 is "ridiculously better" than Opus 4.5 they said... I tested BOTH on identical bugs in OpenCode and recorded everything GPT 5.2 → 24 minutes for nothing Opus 4.5 → 4 minutes and done Full video proof (crazy) Always test yourself instead of trusting tweets
4:13

GPT 5.2 is "ridiculously better" than Opus 4.5 they said... I tested BOTH on identical bugs in OpenCode and recorded everything GPT 5.2 → 24 minutes for nothing Opus 4.5 → 4 minutes and done Full video proof (crazy) Always test yourself instead of trusting tweets

Melvyn • Builder

393,519 views • 5 months 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:
1:20

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

23,010 views • 29 days ago

GPT-5.2 Low just beat Opus 4.5 on a real code review. The cheapest reasoning setting caught issues the expensive model missed.
12:56

GPT-5.2 Low just beat Opus 4.5 on a real code review. The cheapest reasoning setting caught issues the expensive model missed.

Ray Fernando

47,817 views • 5 months ago

As promised, here's my full workflow of how to vibe code 2d games like this: - PhaserJs skill for gamedev - Playwright skill for testing - Opus 4.5 / Gpt 5.2 - Claude Code / Codex CLI / Cursor Step-by-step video below👇 Source code + agent .mds + playable links in reply
32:21

As promised, here's my full workflow of how to vibe code 2d games like this: - PhaserJs skill for gamedev - Playwright skill for testing - Opus 4.5 / Gpt 5.2 - Claude Code / Codex CLI / Cursor Step-by-step video below👇 Source code + agent .mds + playable links in reply

Chong-U

179,660 views • 5 months ago

Opus 4.5 in-a-loop builds Spiking Neural Net simulations in Cursor that is all :)
0:24

Opus 4.5 in-a-loop builds Spiking Neural Net simulations in Cursor that is all :)

echo.hive

42,700 views • 5 months ago

After a couple more days with Composer 2.5, I've got a pretty good sense of what it can do for game dev, specifically this mouse cursor racing game I'm building. It nailed ~80% of the features I threw at it, from planning to execution. Pretty amazing. I did have to switch to Opus 4.7 MAX a few times for features that need stronger visual understanding, like adding a 360 loop to the track or nailing a specific visual effect I had in mind. But man, Opus 4.7 MAX is expensive. Composer 2.5's visual understanding is weaker than Opus 4.7, but for most other things it's pretty damn close, and 10x cheaper. So it's now my default. The beauty of Cursor is I can switch models whenever I want, so I'm never stuck on one. Really excited for the larger incoming model. I have a feeling it's going to shine at planning. Can't wait!
0:59

After a couple more days with Composer 2.5, I've got a pretty good sense of what it can do for game dev, specifically this mouse cursor racing game I'm building. It nailed ~80% of the features I threw at it, from planning to execution. Pretty amazing. I did have to switch to Opus 4.7 MAX a few times for features that need stronger visual understanding, like adding a 360 loop to the track or nailing a specific visual effect I had in mind. But man, Opus 4.7 MAX is expensive. Composer 2.5's visual understanding is weaker than Opus 4.7, but for most other things it's pretty damn close, and 10x cheaper. So it's now my default. The beauty of Cursor is I can switch models whenever I want, so I'm never stuck on one. Really excited for the larger incoming model. I have a feeling it's going to shine at planning. Can't wait!

Danny Limanseta

171,419 views • 1 month ago

my new favorite coding workflow: gpt-4.5 for brainstorming and planning claude 3.7 sonnet for building windsurf for all the agentic stuff watch the video for a quick example
12:15

my new favorite coding workflow: gpt-4.5 for brainstorming and planning claude 3.7 sonnet for building windsurf for all the agentic stuff watch the video for a quick example

elvis

111,789 views • 1 year ago

It's been fun, but time to wrap up this project! Learnt so much about vibe coding 2d games: - PhaserJS agent skill - Tiny Swords asset Pixel Frog - TinyPRD for game design - Playwright for testing - Opus 4.5 w/ Claude Code - GPT 5.2 w/ Codex CLI Links in reply 👇
0:22

It's been fun, but time to wrap up this project! Learnt so much about vibe coding 2d games: - PhaserJS agent skill - Tiny Swords asset Pixel Frog - TinyPRD for game design - Playwright for testing - Opus 4.5 w/ Claude Code - GPT 5.2 w/ Codex CLI Links in reply 👇

Chong-U

30,705 views • 5 months ago

PhD Planning 101 Before my PhD I worked as CEO of a software company for years. I did *a lot* of planning. Here is what 90% of people get wrong: ❌Planning is not: WHAT and WHEN ✅Planning is the HOW to achieve goals Learn how to plan the HOW: 🧵⬇️ #AcademicChatter
0:35

PhD Planning 101 Before my PhD I worked as CEO of a software company for years. I did *a lot* of planning. Here is what 90% of people get wrong: ❌Planning is not: WHAT and WHEN ✅Planning is the HOW to achieve goals Learn how to plan the HOW: 🧵⬇️ #AcademicChatter

Ilya Shabanov

67,090 views • 3 years ago

Cursor shipped a /thermo-nuclear-code-review for the TOUGHEST AI code review possible. But is it any good? Let's dive in:
13:23

Cursor shipped a /thermo-nuclear-code-review for the TOUGHEST AI code review possible. But is it any good? Let's dive in:

Matt Pocock

134,442 views • 1 month ago

Very impressed with Composer 2.5 after about a day of usage. I've almost moved over to it exclusively from GPT 5.5, even using it for planning now. It's like Opus 4.7 on steroids, crazy fast. Fast models really get me into the flow of building, which is exhilarating. Also, a sneak peek of a weekend mini-project I'm building: a racing game where you race your mouse cursor.
0:26

Very impressed with Composer 2.5 after about a day of usage. I've almost moved over to it exclusively from GPT 5.5, even using it for planning now. It's like Opus 4.7 on steroids, crazy fast. Fast models really get me into the flow of building, which is exhilarating. Also, a sneak peek of a weekend mini-project I'm building: a racing game where you race your mouse cursor.

Danny Limanseta

298,872 views • 1 month ago

OPUS 4.6 WAS NERFED DUE TO DEMAND BUT OPUS 4.5 DOES NOT SEEM TO BE HIT this guy ran the same test on both models. Opus 4.6 fails consistently but Opus 4.5 passes every time he switched back to Opus 4.5 on Claude Code and said "what a difference, feels like i got Opus back finally" he is now using this test as a "quantization canary" that runs it at the start of every session before doing real work. if it fails, the model is degraded. five Opus 4.6 windows in a row failed the untransparent nerfing is pushing people to cancel their Max plans if you've been feeling like Opus got dumber lately, you're not imagining it i'd suggest switching to Opus 4.5 to see the difference for yourself
1:03

OPUS 4.6 WAS NERFED DUE TO DEMAND BUT OPUS 4.5 DOES NOT SEEM TO BE HIT this guy ran the same test on both models. Opus 4.6 fails consistently but Opus 4.5 passes every time he switched back to Opus 4.5 on Claude Code and said "what a difference, feels like i got Opus back finally" he is now using this test as a "quantization canary" that runs it at the start of every session before doing real work. if it fails, the model is degraded. five Opus 4.6 windows in a row failed the untransparent nerfing is pushing people to cancel their Max plans if you've been feeling like Opus got dumber lately, you're not imagining it i'd suggest switching to Opus 4.5 to see the difference for yourself

Om Patel

695,468 views • 2 months ago

Opus 4.5 is insane. Just shipped v2 of my compounding engineering plugin—watch the video for my full thoughts on the model. Compounding engineering plugin v2: This wouldn't have worked a week ago. Previous models would derail after the second parallel thread. Opus 4.5 held the context, made the right decisions, and shipped clean pull requests to both repos. New in the plugin: codify command (captures learnings automatically), updated plan mode, better prompting patterns for Opus 4.5's strengths. If you're coding with Claude, this is your new daily driver.
39:16

Opus 4.5 is insane. Just shipped v2 of my compounding engineering plugin—watch the video for my full thoughts on the model. Compounding engineering plugin v2: This wouldn't have worked a week ago. Previous models would derail after the second parallel thread. Opus 4.5 held the context, made the right decisions, and shipped clean pull requests to both repos. New in the plugin: codify command (captures learnings automatically), updated plan mode, better prompting patterns for Opus 4.5's strengths. If you're coding with Claude, this is your new daily driver.

Kieran Klaassen

182,734 views • 7 months ago

I’ve never shipped a game with online multiplayer. I just did my first public test of online for my game. Watch my reaction. This is the #gamedev life 🤪
0:36

I’ve never shipped a game with online multiplayer. I just did my first public test of online for my game. Watch my reaction. This is the #gamedev life 🤪

Walaber

51,342 views • 2 years ago

Warp now supports GPT 5.2 Codex 🙌 We worked closely with the OpenAI team to tune our harness for the Codex series. GPT 5.2 Codex builds upon the strengths of GPT 5.2, excelling at long-horizon tasks (think 15 min+) Try GPT 5.2 codex and tell us what you think
0:20

Warp now supports GPT 5.2 Codex 🙌 We worked closely with the OpenAI team to tune our harness for the Codex series. GPT 5.2 Codex builds upon the strengths of GPT 5.2, excelling at long-horizon tasks (think 15 min+) Try GPT 5.2 codex and tell us what you think

Warp

32,708 views • 5 months ago

According to inside reports, After huge success of part-1 they are planning to extend the theatrical run and promote sequel in a bigger way.#Dhurandhar2 team are now scheduling a reshoot of few sequences and some patch works Team is planning for May window. Movies which are planning in May postpone all You aren't Yash to win against #Dhurandhar #Yash's #ToxicTheMovie releasing solo on 19th March 2026 #ToxicOnMARCH19th #YashBOSS
0:20

According to inside reports, After huge success of part-1 they are planning to extend the theatrical run and promote sequel in a bigger way.#Dhurandhar2 team are now scheduling a reshoot of few sequences and some patch works Team is planning for May window. Movies which are planning in May postpone all You aren't Yash to win against #Dhurandhar #Yash's #ToxicTheMovie releasing solo on 19th March 2026 #ToxicOnMARCH19th #YashBOSS

Kiran Patil

217,943 views • 5 months ago

Run AI Generated World on Your Laptop This is the coolest thing I've seen in a while. I wrote a 1-click launcher for not just the counter-strike game, but also the Atari games included in the project. Works on all platforms. Here's what it looks like on a 4090 (1X speed).
1:16

Run AI Generated World on Your Laptop This is the coolest thing I've seen in a while. I wrote a 1-click launcher for not just the counter-strike game, but also the Atari games included in the project. Works on all platforms. Here's what it looks like on a 4090 (1X speed).

cocktail peanut

57,525 views • 1 year ago

Right now on the App Store, there are tons of arcade games making $1M+ from ads. My million-dollar idea: I can vibe-code multiple games and turn them into TikTok, but for arcade games. I just tried vibe-coding a Pac-Man game and it was insanely simple. I could code it from scratch, but that would take about 1 month. Now it takes 5 minutes with just 3 simple steps: > Prompt it with GPT-5 > Build it using Opus 4.5 on Rork > Shipped from my phone I honestly think that combined with good TikTok marketing, making $10k–$50k/month from ads is totally realistic because TikTok users love free stuff. Bruh… AI genuinely surprised me.
0:22

Right now on the App Store, there are tons of arcade games making $1M+ from ads. My million-dollar idea: I can vibe-code multiple games and turn them into TikTok, but for arcade games. I just tried vibe-coding a Pac-Man game and it was insanely simple. I could code it from scratch, but that would take about 1 month. Now it takes 5 minutes with just 3 simple steps: > Prompt it with GPT-5 > Build it using Opus 4.5 on Rork > Shipped from my phone I honestly think that combined with good TikTok marketing, making $10k–$50k/month from ads is totally realistic because TikTok users love free stuff. Bruh… AI genuinely surprised me.

Alex Nguyen

72,381 views • 6 months ago