Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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 Aufrufe • vor 6 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

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

23,105 Aufrufe • vor 1 Monat

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

171,643 Aufrufe • vor 1 Monat

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

299,181 Aufrufe • vor 2 Monaten

Grok 4.5 is first xAI model that win my heart 🫡 this is better then glm 5.2 and on par with current opus and gpt They cooked with the frontend too , like see this quality it made a website to showcase its benchmark and i asked it for water effects on background Elon Musk great job
0:26

Grok 4.5 is first xAI model that win my heart 🫡 this is better then glm 5.2 and on par with current opus and gpt They cooked with the frontend too , like see this quality it made a website to showcase its benchmark and i asked it for water effects on background Elon Musk great job

Chetaslua

47,636 Aufrufe • vor 9 Tagen

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

695,562 Aufrufe • vor 3 Monaten

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 Aufrufe • vor 7 Monaten

Grok 4.5 operates at Opus-level intelligence and Sonnet-level pricing! We tested it against Claude Opus 4.8, Sonnet 5, and GLM 5.2 on a SpaceX mission: liftoff, stage sep, orbit insertion, satellite deploy. Grok 4.5 animates it more accurately and vividly than Sonnet 5 and GLM 5.2. Opus is the fastest and most expensive. Grok burns more tokens but still lands ~40% cheaper than Opus, and a bit under Sonnet 5. Time / tokens / cost: Grok 4.5 — / 35k / $0.69 Opus 4.8 — / 13.7k / $1.10 Sonnet 5 — / 22.1k / $0.78 GLM 5.2 — / 92.7k / $0.13 yet GLM did the whole mission for $0.13 😮
0:45

Grok 4.5 operates at Opus-level intelligence and Sonnet-level pricing! We tested it against Claude Opus 4.8, Sonnet 5, and GLM 5.2 on a SpaceX mission: liftoff, stage sep, orbit insertion, satellite deploy. Grok 4.5 animates it more accurately and vividly than Sonnet 5 and GLM 5.2. Opus is the fastest and most expensive. Grok burns more tokens but still lands ~40% cheaper than Opus, and a bit under Sonnet 5. Time / tokens / cost: Grok 4.5 — / 35k / $0.69 Opus 4.8 — / 13.7k / $1.10 Sonnet 5 — / 22.1k / $0.78 GLM 5.2 — / 92.7k / $0.13 yet GLM did the whole mission for $0.13 😮

GMI Cloud

149,945 Aufrufe • vor 10 Tagen

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 Aufrufe • vor 6 Monaten

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 6 Monaten

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.
0:20

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.

Dan McAteer

190,313 Aufrufe • vor 10 Tagen

Never bet against Cursor. Subagents solve so many issues between different models it's kind of insane, especially with Composer 1. Composer 1 can quickly gather context for a model like GPT-5.2 Codex, which otherwise could take on the order of 10 mins just to search files. Definitely one of the most underrated models right now. Now you get the benefits of it's speed, but can handoff to a smarter model at implementation. The video I attached is just a simple example, but you can see how long GPT 5.2 takes to gather context on a very simple problem. For harder problems, the search time grows significantly.
0:50

Never bet against Cursor. Subagents solve so many issues between different models it's kind of insane, especially with Composer 1. Composer 1 can quickly gather context for a model like GPT-5.2 Codex, which otherwise could take on the order of 10 mins just to search files. Definitely one of the most underrated models right now. Now you get the benefits of it's speed, but can handoff to a smarter model at implementation. The video I attached is just a simple example, but you can see how long GPT 5.2 takes to gather context on a very simple problem. For harder problems, the search time grows significantly.

ostyn

19,631 Aufrufe • vor 5 Monaten

It is time to begin planning & preparing for a new, united Ireland. Westminster has never served, & will never serve, the best interests of workers, families & public services here. Only by taking control of our own affairs, with all decisions made at home, can we realise our full potential.
0:51

It is time to begin planning & preparing for a new, united Ireland. Westminster has never served, & will never serve, the best interests of workers, families & public services here. Only by taking control of our own affairs, with all decisions made at home, can we realise our full potential.

John Finucane MP

17,391 Aufrufe • vor 3 Monaten

🚨 do you understand what happened to Claude.. Anthropic just shipped Opus 4.8 with something called dynamic workflows. It no longer works alone - it spins up hundreds of agents that argue, verify, and break each other's work until the answer is right. - A dev used it to port Bun from Zig to Rust in 11 days - 750,000 lines of Rust, 99.8 percent of tests passing - Hundreds of agents ran in parallel with two reviewers per file - Fast mode runs the same model 2.5x faster and 3x cheaper than before work you used to plan in quarters now finishes before the weekend
1:21

🚨 do you understand what happened to Claude.. Anthropic just shipped Opus 4.8 with something called dynamic workflows. It no longer works alone - it spins up hundreds of agents that argue, verify, and break each other's work until the answer is right. - A dev used it to port Bun from Zig to Rust in 11 days - 750,000 lines of Rust, 99.8 percent of tests passing - Hundreds of agents ran in parallel with two reviewers per file - Fast mode runs the same model 2.5x faster and 3x cheaper than before work you used to plan in quarters now finishes before the weekend

BuBBliK

431,265 Aufrufe • vor 1 Monat

The deadline for the Impossible UI with Rive challenge has been extended until May 8! Build a UI that simply should not exist. Like Neal Agarwal and Ashley Best 🏝's Cursor Camp: A live multiplayer playground for 1,000 real cursors to hang out in real time. Seriously, how is this even possible? Rive is wild!
2:28

The deadline for the Impossible UI with Rive challenge has been extended until May 8! Build a UI that simply should not exist. Like Neal Agarwal and Ashley Best 🏝's Cursor Camp: A live multiplayer playground for 1,000 real cursors to hang out in real time. Seriously, how is this even possible? Rive is wild!

Contra

19,742 Aufrufe • vor 2 Monaten

A SHOT AT DESTINY: What does playing a final mean and how are the boys approaching this game? After a couple of days of planning and training in Ahmedabad, it’s time for the most important match of the #IPL2025 and we’re ready to Play Bold ONE LAST TIME! This is bigbasket presents RCB Game Day. 👊 #PlayBold #ನಮ್ಮRCB #IPL2025
5:23

A SHOT AT DESTINY: What does playing a final mean and how are the boys approaching this game? After a couple of days of planning and training in Ahmedabad, it’s time for the most important match of the #IPL2025 and we’re ready to Play Bold ONE LAST TIME! This is bigbasket presents RCB Game Day. 👊 #PlayBold #ನಮ್ಮRCB #IPL2025

Royal Challengers Bengaluru

179,817 Aufrufe • vor 1 Jahr

Grok 4.5 is out!!! here is what you need to know : On cursor bench it matched fable 5 high at 83% cheaper, although the ui generation feels similar to gpt 5.5 in a bad way. Important to note, cursor bench was LEAKED to grok 4.5 and may have skewed the results! My initial thoughts are this could be a insanely cheap opus 4.8 level model that runs insanely fast. Will you be using grok build?
1:04

Grok 4.5 is out!!! here is what you need to know : On cursor bench it matched fable 5 high at 83% cheaper, although the ui generation feels similar to gpt 5.5 in a bad way. Important to note, cursor bench was LEAKED to grok 4.5 and may have skewed the results! My initial thoughts are this could be a insanely cheap opus 4.8 level model that runs insanely fast. Will you be using grok build?

Max Blade

18,675 Aufrufe • vor 10 Tagen

working with cloud agents in cursor feels the same as local, but the fact that i can shut down my computer and still have it running is amazing. one of my favorite use cases is planning in cursor, then send off to cloud agent for impl. here's a short demo
0:32

working with cloud agents in cursor feels the same as local, but the fact that i can shut down my computer and still have it running is amazing. one of my favorite use cases is planning in cursor, then send off to cloud agent for impl. here's a short demo

eric zakariasson

61,940 Aufrufe • vor 8 Monaten

Claude Fable 5 makes new things possible. I one shot a full horror game with it. One prompt. I have never seen AI output a game like this. This is the leap I've been waiting for. 80.3 on SWE-Bench Pro vs Opus 4.8 at 69.2, the biggest jump I have ever seen on that benchmark. It passed GPT 5.5 in both coding and intelligence on Artificial Analysis. I already canceled my $200 ChatGPT Pro plan. It fixed a Bridge Voice bug in one shot that GPT 5.5, Opus 4.7, and Opus 4.8 all failed to crack for 2 months. 10/10. Best model I have ever used. Full review below.
15:50

Claude Fable 5 makes new things possible. I one shot a full horror game with it. One prompt. I have never seen AI output a game like this. This is the leap I've been waiting for. 80.3 on SWE-Bench Pro vs Opus 4.8 at 69.2, the biggest jump I have ever seen on that benchmark. It passed GPT 5.5 in both coding and intelligence on Artificial Analysis. I already canceled my $200 ChatGPT Pro plan. It fixed a Bridge Voice bug in one shot that GPT 5.5, Opus 4.7, and Opus 4.8 all failed to crack for 2 months. 10/10. Best model I have ever used. Full review below.

BridgeMind

19,020 Aufrufe • vor 1 Monat